Topics for BSc/MSc theses

• Spatial Scale: Inter-regional
• Temporal Scale: 2023 Fire Season
• Data: European Forest Fire Information System (EFFIS). Local, regional and national media
• Methods: Data collection, comparison and analysis
• Possible Supervisors: Christopher Marrs, Eric Kosczor
• Update: Topic open after 2023-08-31
• Description: Agricultural fires appear to be underestimated by operational monitoring systems such as European Forest Fire Information System (EFFIS). During the fire season of 2023 large areas of agricultural land burnt and reported in the media, but not recorded by EFFIS. The aim of this BSc Thesis is quantify the number of fires and amount of crops lost to fire, record and compare with fire detection and burnt area data from EFFIS. A good basic understanding of the German language is needed.
• References (As a starting point)

San-Miguel-Ayanz, J., Schulte, E., Schmuck, G., Camia, A., Strobl, P., Libertà, G., Giovando, C., Boca, R., Sedano, F., Kempeneers, P., McInerney, D., Withmore, C., Oliveira, S., Rodrigues, M., Durrant, T., Corti, P., Oehler, F., Vilar, L., Amatulli, G., 2012. Comprehensive Monitoring of Wildfires in Europe: The European Forest Fire Information System (EFFIS), in: Approaches to Managing Disaster - Assessing Hazards, Emergencies and Disaster Impacts. https://doi.org/10.5772/28441

Hall, J.V., Zibtsev, S.V., Giglio, L., Skakun, S., Myroniuk, V., Zhuravel, O., Goldammer, J.G., Kussul, N., 2021. Environmental and political implications of underestimated cropland burning in Ukraine. Environ Res Lett 16, 064019. https://doi.org/10.1088/1748-9326/abfc04

• Update: Thema dauerhaft verfügbar seit 2021-11-28
• Inhaltlich-technische Betreuung: Für weitere Fragen zum Thema wenden Sie sich bitte an Lucas Kugler.

Beschreibung: Frühe Erdbeobachtungsaufnahmen sind seit den 1960er Jahren von dem vormaligen Spionageprogramm "Keyhole" der CIA verfügbar. Daber wurden panchromatische Aufnahmen mit dem "Corona"-Kamerasystem angefertigt, die eine hohe räumliche Auflösung aufweisen. Diese Aufnahmen ermöglichen die großflächige Bestimmung der Landbedeckung bevor die operationelle Erdbeobachtung begann und sind daher für die Analyse historischer Veränderungen der Landbedeckung und -nutzung nützlich. Im Rahmen einer Bachelor-Arbeit können Sie selbst für ein frei gewähltes Untersuchungsgebiet innerhalb des Freistaates Sachsens oder benachbarter Regionen Corona-Aufnahmen nutzen und eine Veränderungsanalyse durchführen.

Aufgaben

• Festlegung eines Untersuchungsgebietes innerhalb des Freistaates Sachsen (idealerweise ein Gebiet, das Sie selbst etwas kennen), in Rücksprache mit uns
• Georeferenzierung eines Corona-Bildstreifens aus den 1960er und 1970er Jahren und Ausschneiden des Untersuchungsgebietes (ArcGIS oder QGIS)
• Manuelle Ausweisung von Landbedeckungs-/nutzungsklassen (ArcGIS oder QGIS)
• Statistische Auswertung der Landbedeckung beider Bilder (vorzugsweise in R oder einer äquivalenten Sprache)
• Auswertung der Änderung der Landnutzung zwischen 1960/1970 und heute (anhand aktueller Corine-LC)
• Zusammenfassung der Ergebnisse in der BSc-Arbeit (Einleitung, Daten und Methoden, Ergebnisse, Diskussion) und Abgabe der Ergebnisse in digitaler Form

© EnvRS

• Keywords:
  • spatial scale: regional
  • temporal scale: daily-weekly
  • data: Sentinel-2, Sentinel-3 LAI, VIIRS, Sentinel-5p TROPOMI, meteorological data, field data
  • methods: time series analysis, model-data fusion
• Possible supervisor: For further questions related to this topic, please contact M. Forkel
• Suited for: GIT, Geodesy, Cartography
• Update: topic open since 2022-12-03

Description: The forest fire in the Bohemian-Saxon Switzerland in July and August 2022 caused major emissions of smoke which was transported over hundreds of kilometres. Several approahces exist to estimate fire emissions of smoke and trace gases by using remote sensing data. As part of the ESA-funded Sense4Fire project, a satellite data-model fusion approach (S4F model) was developed to estimate ecosystem fuel loads, fuel consumption and fire emissions. The objective of this MSc thesis is gather and analyse various satellite datasets of vegetation cover change (Sentinel-2), LAI (Sentinel-3) and others and to adapt the S4F model to the Bohemian-Saxon Switzerland in order to estimate fuel consumption and fire emissions. The estimated fire emissions should be then compared with observations of atmospheric CO concentration provided by Sentinel-5p.

References (comparable approaches):

van Wees, D., van der Werf, G. R., Randerson, J. T., Rogers, B. M., Chen, Y., Veraverbeke, S., Giglio, L., and Morton, D. C.: Global biomass burning fuel consumption and emissions at 500-m spatial resolution based on the Global Fire Emissions Database (GFED), Geoscientific Model Development Discussions, 1–46, https://doi.org/10.5194/gmd-2022-132, 2022.

• Keywords:
  • spatial scale: regional to national
  • temporal scale: annual/static
  • data: Sentinel-2, Landsat-8/9, forest inventroy data, Copernicus services
  • methods: multi-source data fusion
• Possible supervisors: For further questions related to this topic, please contact  C. Marrs. Potentially further supervisors from e.g. the FirEUrisk project or from research institutions in the Czech Republic
• Update: topic open since 2022-12-03

Description: The modelling and prediction of forest fires requires a mapping of fire-related vegetation propoerties, or so called fuel properties. A common approach is to classify fuel types, which are groups with similar vegetation and surface litter properties. By merging observation from e.g. Sentinel-2, Landsat, and satellite products of land cover and canopy height fuel types can be mapped. The objective of this MSc thesis is to adapt a previously developed methodology to map fuel types to Germany and to develop a fuel type map at 10-20 m spatial resolution for at least one German state (e.g. Saxony, Brandenburg or larger).

References (as starting point):

Aragoneses, E., García, M., Salis, M., Ribeiro, L. M., and Chuvieco, E.: Classification and mapping of European fuels using a hierarchical-multipurpose fuel classification system, Earth System Science Data Discussions, 1–38, https://doi.org/10.5194/essd-2022-184, 2022.

Scott, J. H. and Burgan, R. E.: Standard fire behavior fuel models: a comprehensive set for use with Rothermel’s surface fire spread model, Gen. Tech. Rep. RMRS-GTR-153. Fort Collins, CO: U.S. Department of Agriculture, Forest Service, Rocky Mountain Research Station. 72 p., 153, https://doi.org/10.2737/RMRS-GTR-153, 2005.

• Keywords:
  • spatial scale: regional to national (Saxony, Saxony-Anhalt ...)
  • temporal scale: short-term change detection
  • data: Sentinel-2, Landsat-8/9, Copernicus services
  • methods: change detection, land cover classification
• Possible supervisors: For further questions related to this topic, please contact  Chris Marrs and Eric Kosczor.
• Update: topic open since 2023-07-21

Description: The occurrence of fires in agricultural fields appears to be underestimated by operational monitoring systems such as the European Forest Fire Information System (EFFIS) leading to an underestimation of fire emissions. The aim of this MSc thesis is to quantify this potential underestimation by using information from local and regional media articles, fire brigade records and satellite imagery from Sentinel-2 and possibly Landsat-8/9 and comparing the results with the EFFIS.

References (as starting point):

Deshpande, M.V., Pillai, D., Jain, M., 2022. Agricultural burned area detection using an integrated approach utilizing multi spectral instrument based fire and vegetation indices from Sentinel-2 satellite. MethodsX 9, 101741. https://doi.org/10.1016/j.mex.2022.101741

Ramo, R., Roteta, E., Bistinas, I., Wees, D. van, Bastarrika, A., Chuvieco, E., and Werf, G. R. van der: African burned area and fire carbon emissions are strongly impacted by small fires undetected by coarse resolution satellite data, PNAS, 118, https://doi.org/10.1073/pnas.2011160118, 2021.

Hall, J.V., Zibtsev, S.V., Giglio, L., Skakun, S., Myroniuk, V., Zhuravel, O., Goldammer, J.G., Kussul, N., 2021. Environmental and political implications of underestimated cropland burning in Ukraine. Environ Res Lett 16, 064019. https://doi.org/10.1088/1748-9326/abfc04

• Keywords:
  • Spatial scale: regional
  • Temporal scale: at least monthly
  • Data: Global Ecosystem Dynamics Investigation (GEDI), Sentinel-1
  • Methods: time series analyses, radar scattering modelling, machine learning
• Possible supervisor: For further questions related to this topic, please contact Xiao Liu
• Update: topic open since 2022-11-21

Description: Canopy structure is the distribution of leaves, branches and stems in the canopy. It changes because of multiple factors such as tree species, temperature, soil water and radiation etc. Continuous monitoring of canopy structure dynamics will improve our understanding about carbon and water cycle in forests. The space-borne waveform lidar GEDI has the potential of measuring these seasonal changes at global scale. However, both temporal and spatial coverage of GEDI depend on the arrangement of International Space Station’s orbit. In order to fill these gaps, this study will explore the possibility about using Sentinel-1 data (e.g., VV/VH ratio) to interpolate the GEDI-based vertical structure metrics at different height level (e.g., plant area index between 20 to 30 m level). Both regression methods and radar backscattering model will be tested.

References (as a starting point):

• Boucher, P.B., Hancock, S., Orwig, D.A., Duncanson, L., Armston, J., Tang, H., Krause, K., Cook, B., Paynter, I., Li, Z., Elmes, A., Schaaf, C., 2020. Detecting Change in Forest Structure with Simulated GEDI Lidar Waveforms: A Case Study of the Hemlock Woolly Adelgid (HWA; Adelges tsugae) Infestation. Remote Sensing 12, 1304. https://doi.org/10.3390/rs12081304
• Dostálová, A., Milenković, M., Hollaus, M., Wagner, W., 2016. Influence of Forest Structure on the Sentinel-1 Backscatter Variation- Analysis with Full-Waveform LiDAR Data.
• Tang, H., Dubayah, R., 2017. Light-driven growth in Amazon evergreen forests explained by seasonal variations of vertical canopy structure. Proc. Natl. Acad. Sci. U.S.A. 114, 2640–2644. https://doi.org/10.1073/pnas.1616943114

• Supervisors:
  • Matthias Forkel and Naixin Fan
  • For further questions related to this topic, please contact Naixin Fan .
  • Update: topic open since 2023-01-08

Description: 

Spatial maps of forest biomass from satellite sensors are available since around 12 years. However, mapping and quantification of the changes forest biomass is still an active area of research. The envrionmental remote sensing group developed recently an approach to estimate biomass changes by combining stallite products of aboveground biomass with time series of land cover, leaf area index and vegetation optical depth. The aim of this MSc topic is to calibrate, test and apply this new method to different study regions and to compare the estimates with datasets from other groups.

Literature:

Santoro, M., Cartus, O., Carvalhais, N., Rozendaal, D. M. A., Avitabile, V., Araza, A., de Bruin, S., Herold, M., Quegan, S., Rodríguez-Veiga, P., Balzter, H., Carreiras, J., Schepaschenko, D., Korets, M., Shimada, M., Itoh, T., Moreno Martínez, Á., Cavlovic, J., Cazzolla Gatti, R., da Conceição Bispo, P., Dewnath, N., Labrière, N., Liang, J., Lindsell, J., Mitchard, E. T. A., Morel, A., Pacheco Pascagaza, A. M., Ryan, C. M., Slik, F., Vaglio Laurin, G., Verbeeck, H., Wijaya, A., and Willcock, S.: The global forest above-ground biomass pool for 2010 estimated from high-resolution satellite observations, Earth System Science Data, 13, 3927–3950, https://doi.org/10.5194/essd-13-3927-2021, 2021.

Santoro, M., Cartus, O., Wegmüller, U., Besnard, S., Carvalhais, N., Araza, A., Herold, M., Liang, J., Cavlovic, J., and Engdahl, M. E.: Global estimation of above-ground biomass from spaceborne C-band scatterometer observations aided by LiDAR metrics of vegetation structure, Remote Sensing of Environment, 279, 113114, https://doi.org/10.1016/j.rse.2022.113114, 2022.

• Keywords:
  • spatial scale: global
  • temporal scale: daily to multi-year
  • data: passive microwave VOD (e.g. VODCA dataset, SMOS), Proba-V/Sentinel-3 LAI and others
  • methods: model optimization, time series analysis
• Possible supervisor: For further questions related to this topic, please contact Luisa Schmidt
• Required skills: first knowledge and interest to further learn R
• Update: topic open since 2022-12-03

Description: The water content in vegetation is an important control on various ecosystem processes such as palnt productivity, transpiration or fire danger. The Vegetation Optical Depth (VOD) from passive microwave satellites is a metric that is sensitive to the biomass and water content of vegetation. However, only few methods have been developed so far to estimate Vegetation Water Content (VWC) from satellite VOD data. The EnvRS group is currently developing model-data fusion approach that allows to estimate VWC from VOD observations in short and long microwave wavelengths. The objective of this MSc thesis is to estimate VWC by integrating VOD and satellite datasets of leaf area index and above-ground biomass with the data-model fusion approach through model parameter estimation. The result will be estimates of vegetation water content with an approxiamtely 10-daily temporal resolution.

References (as starting point):

Forkel, M., Schmidt, L., Zotta, R.-M., Dorigo, W., and Yebra, M.: Estimating leaf moisture content at global scale from passive microwave satellite observations of vegetation optical depth, Hydrology and Earth System Sciences Discussions, 1–43, https://doi.org/10.5194/hess-2022-121, 2022.

Frappart, F., Wigneron, J.-P., Li, X., Liu, X., Al-Yaari, A., Fan, L., Wang, M., Moisy, C., Le Masson, E., Aoulad Lafkih, Z., Vallé, C., Ygorra, B., and Baghdadi, N.: Global Monitoring of the Vegetation Dynamics from the Vegetation Optical Depth (VOD): A Review, Remote Sensing, 12, 2915, https://doi.org/10.3390/rs12182915, 2020.

(MSc) Dynamics of modern land-use changes within the Ruiru catchment, Central Kenya (1950 to present)

Supervisors

• Dr. Esther Githumbi  (TUD Soil Science and Site Ecology)

• Prof. Dr. Karl-Heinz Feger   (TUD Soil Science and Site Ecology)

• JProf. Dr. Matthias Forkel  

• For further questions related to this topic, please contact Esther Githumbi.

• Update: topic open since 2023-09-14

Description

The Ruiru reservoir catchment in the highlands of Central Kenya covers an area of 51 km². The reservoir is served by the Ruiru river and its tributaries which have been dammed to provide water for the Nairobi city and its environ through the Ruiru dam (0.4 km²). Sedimentation into the Ruiru dam is caused by a combination of the topography, climate and the land-uses within the catchment.

The Ruiru catchment is characterized by an annual mean rainfall of 1300 – 1500 mm and temperature ranges from 17°C (uplands) to 34°C (lowlands). At present, land-use is dominated by smallholder farming and tea plantations. Since the construction of the dam in the late 1940s, land-cover in the catchment has changed from natural forests to tea\coffee plantations, dairy farming, mixed-cropping and settlement. Quantification of the area under the different land-use units since 1950 is needed to understand the impacts of each land-use unit on sedimentation load to the reservoir through time. Using topographical\cadastral maps and aerial images for the earlier time periods (1950 to 1975) and satellite images (1975 to present) the spatio-temporal dynamics of land-use changes shall be visualized and quantified. Lower resolution is expected for the earlier time period (1950-1975) due to data scarcity however since the launch of the satellites there is more data available and so higher resolution can be achieved. The MSc thesis is embedded in an ongoing DFG-funded research project with partners in TU Dresden and Jomo Kenyatta University of Agriculture and Technology (Kenya).

Required skills

• spatial analysis
• georeferencing of aerial photographs
• land-use classification of satellite imagery
• visualization and quantitative analysis of land-use change

In cooperation with the Chair of Land Management

• Keywords: image classification, machine learning, regional, high resolution
• Supervisors: M. Forkel, A. Weitkamp
• Suited for: Geodesy, GIT
• Update: currently available
• References (as a starting point): Eine umfassende Literaturrecherche ist Teil der Arbeit.
  • Ge, W., Yang, H., Zhu, X., Ma, M., Yang, Y., 2018. Ghost City Extraction and Rate Estimation in China Based on NPP-VIIRS Night-Time Light Data. ISPRS International Journal of Geo-Information 7, 219. https://doi.org/10.3390/ijgi7060219
  • Leichtle, T., Lakes, T., Zhu, X.X., Taubenböck, H., 2019. Has Dongying developed to a ghost city? - Evidence from multi-temporal population estimation based on VHR remote sensing and census counts. Computers, Environment and Urban Systems 78, 101372. https://doi.org/10.1016/j.compenvurbsys.2019.101372

Identification of approaches for deriving an indicator for determining vegetative drought stress in grassland sites based on remote sensing data in Saxony

Study

MSc Geodesy

Date of defence

10.08.2023

Supervisor

Christine Wessollek, Sebastian Goihl (LfULG)

Abstract

Drought stress is becoming increasingly important in times of climate change. The primary objective of this study is to develop a method for deriving an indicator that can be used to identify drought in grassland areas of Saxony. This indicator should have the potential to be integrated into the Saxon climate impact monitoring of the Landesamt für Umwelt, Landwirtschaft und Geologie (LfULG), with whose cooperation this work was developed. Four study areas in Saxony were chosen for the development of the method. These are located in the agricultural comparison areas (german: Vergleichsgebiete) 111 Düben-Dahlener Heide, 221 Sächsiche Elbtalniederung, 232 Elbsandsteingebirge und Zittauer Gebirge and 351 Erzgebirgskamm. The agricultural comparative areas of Saxony are summaries of areas in the Free State of Saxony with similar location factors such as soil properties, climate and altitude or relief. The data basis is formed by freely available Sentinel-2 data and monthly DWD precipitation data that have been atmospherically adjusted with Sen2Cor. The following indices were calculated with the available Sentinel-2 data: Normalized difference vegetation index (NDVI), Normalized difference water index (NDWI), Normalized difference drought index (NDDI), Normalized multi-band drought index (NMDI), Vegetation Condition Index (VCI) of the NDVI and NDWI. The Standardized Precipitation Index (SPI) was calculated from the monthly precipitation data. This data forms the basis for testing two machine learning approaches, specifically Random Forest and Support Vector Regression. Using these data and approaches, this work tested whether annual yield for grassland can serve as an indicator of drought or drought stress and whether yield estimation is possible using the aforementioned drought indices. The study period includes the years 2015 to 2021 and the months April to September. Averaged annual yields of the respective comparison areas serve as the target value for training the machine learning approaches. Three main research questions were addressed in this work: 1. Can annual yield serve as an indicator for drought in grassland areas in Saxony? 2. is it possible to estimate the annual yield of grassland using satellite indices from Sentinel-2 data used for drought monitoring and the SPI? 3. Can machine learning, especially random forest and support vector regression, be used for yield estimation? For estimating missing values, due to cloud cover for example, two methods were used. On the one hand, rfImpute from the randomForest package and on the other hand bagImpute from the caret package in R were used. The results with the test dataset of the two machine-learning approaches, which includes all grassland areas of the four study sites in 2018, give an RMSE of 12.57 dt/ha and 11.25 dt/ha with the best tuning parameters at absolute yields between 26.75 dt/ha and 42.55 dt/ha. With the present results of this work, the research questions could not be answered sufficiently. Some model improvements are recommended. Among them, the use of grassland yields with a higher spatial and temporal resolution for training and the use of indices with a lower correlation among them.

© Benedikt Scholz

Comparison of flooding area mapping algorithms using Sentinel-1 data

Study

MSc Geoinformation Technologies

Date of defence

03.05.2023

Supervisor

Matthias Forkel, Sebastian Goihl (LfULG)

Abstract

In this master thesis, a comparative analysis of flood mapping algorithms using Sentinel-1 data is conducted, focusing on Mean Thresholding, Otsu Thresholding, Multi-Otsu Thresholding, and the Random Forest (RF) machine learning algorithm. The primary objective of the study is to evaluate the effectiveness and accuracy of these algorithms in detecting and mapping flood-affected areas. The regions studied include the Ahrtal and Sauer and Kyll river valley regions in Germany, with the data divided into separate parts for model training and validation. An extensive literature review was performed using the Web of Science database to identify relevant studies and methodologies employed in flood mapping using remote sensing data. The performance of each algorithm is assessed through accuracy, Kappa coefficient, and other evaluation metrics. A comprehensive dataset, including Sentinel-1 data and terrain and hydrological metrics, is employed for model training and validation. The results indicate that the Random Forest algorithm outperforms the thresholding methods, with higher accuracies and improved overall flood detection capabilities. This thesis provides valuable insights into the applicability of different flood mapping algorithms using Sentinel-1 data and offers recommendations for selecting appropriate methods for specific flood scenarios. The findings contribute to the growing body of knowledge on flood mapping using remote sensing data and support decision-makers in disaster management and mitigation planning.

Evaluation of the competence to identify deep fake satellite images

Study

Bachelor Geodesy and Geoinformation

Date of defence

21.04.2023

Supervisor

Christine Wessollek, Lucas Kugler

Abstract

Due to current tensions in international security policy, the discussion about fake satellite images not only concerns experts and politicians, but also increasingly the general public. The presented work makes an empirical contribution to this discussion and illustrates that the dangers posed by the falsification of satellite images using generative neural networks must be taken seriously. Therefore, it is even more important that the fake satellite images are reliably detectable. Specifically, the purely visual detection of the deep fakes is evaluated in this work. Additionally, the influence of competence on the detection result is also investigated. To answer the research questions, based on self-generated deep fake satellite images, a survey was conducted and a technical approach to detect the generated deep fakes was developed. The survey showed that fake satellite images are not reliably detectable and competence has no influence on the detection results. On the other hand, the technical detection approach can efficiently expose fakes. The results illustrate the dangers of deep fakes. It is therefore important to raise the awareness of the dangers and to develop continuously these detection methods so that deep fakes can also be reliably detected in the future.

© Robert Marmai

Forest fires in the Bohemian-Saxon Switzerland in 2022: Mapping and analysis of fuel types, fire dynamics and severity using remote sensing data

Study

MSc Geoinformation Technologies

Date of defence

23.03.2023

Supervisor

Matthias Forkel, Dr. Annika Busse (Nationalpark Sächsische Schweiz)

Abstract

The forest fires in Bohemian-Saxon Switzerland in 2022 demonstrated the need for comprehensive fire research and management strategies in the National Parks to better understand the main drivers and to predict fires and fire behaviour in the future. The developed fuel type classification and mapping in the study area and the crosswalk to the Standard Fire Behaviour Fuel Models from Scott and Burgan (2005) set the basis to analyse fire behaviour in different fuel types and can be further employed in fire models like FlamMap. For the fuel type mapping, the classification scheme of Aragoneses et al. (2022) and the Alaska Fuel Model Guide Task Group (2018) was combined and adapted to the study area using different input data sets: habitat data covering both National Parks, tree coverage data from Copernicus and bark beetle-infested forest data. For the bark beetle-infested forests in the Bohemian Switzerland National Park, a Random Forest model was built and trained with the corresponding bark beetle data from the Saxon Switzerland National Park and the bands of a Landsat 8 image as well as the Normalized Burn Ratio (NBR), the Normalized Difference Vegetation Index (NDVI) and the Normalized Difference Moisture Index (NDMI) as predictor variables. Particular focus is set on the influence of bark beetle-infested forests since it is widespread over the National Parks and the fuel type that burned the most (41%). The green band and the NDMI had the strongest influence on the model and an overall accuracy of around 90% was achieved. Also, the burn severity is estimated by the Difference Normalized Burn Ratio (dNBR) through Landsat 8, 9, and Sentinel-2 images, resulting in moderate burn severities. For the calculation of the dNBR, the difference from the NBR pre-fire image to the NBR post-fire image is taken. Therefore, satellite imagery from mid-August and September 2021 and images from the same period in 2022 after the fire were employed. To validate the dNBR, 21 field surveys were undertaken to measure the Composite Burn Index (CBI), in September and the beginning of October 2022. Significant correlations (r = 0.62, p < 0.01) have been found with the Spearman correlation coefficient when evaluating the relationship between dNBR and the CBI upper canopy (strata D and E). No correlation was found between the CBI (all strata) and dNBR. However, the CBI understorey strata revealed higher burn severities, which the passive sensors could not detect. The burn severity dNBR was highest in dead spruce stands and other forest fuel types. Dead spruce stands indicated especially high char heights and torching in the field caused by the high amount of dead and dry fuel when compared to broadleaved and mixed forests.

© Kristina Beetz

Classification of fire types in savannahs of southern Africa using Sentinel data

Study

MSc Geodesy

Date of defence

20.01.2023

Supervisor

Dr. Christine Wessollek, MSc. Tichaona Tavare Mukunga (TU Wien, Department of Geodesy and Geoinformation)

Abstract

Fires are a part of the natural process in savannah areas. It is estimated that 300-1600 Teragram Carbon (TgC) per year are released by these fires. To analyse these fires regarding the land cover type and burn severity, a fire classification method was developed based on the use of land cover datasets and Sentinel-2 data. In order to do this, the ESA WorldCover 2020 land cover model was selected in an observation area in Zambia and compared with the ESA CCI LAND COVER - S2 prototype 2016. This observation area had an extent of 14.8°-15.2°S and 25.7°-26.1°E and contained all of the four main land cover types representative of savannah, tree cover, shrubland, grassland and cropland.
After selecting the first data to be used for classifying the fires, the Sentinel-2 data was processed from L1C to L2A using the processing software FORCE by David Frantz. In addition to atmospherically correcting the Sentinel-2 data, the data was topospherically corrected using the DEM_SRTM1 dataset. The difference Normalized Burn Ratio (dNBR) was then calculated from the Sentinel-2 L2A data as the difference between the Normalized Burn Ratio (NBR) before and after fires. From this, the burn severity was determined as a measure of fire effect levels for burned area based on the method of Key and Benson.
From the land cover and fire severity, sixteen fire classes were defined. These fire classes were then evaluated qualitatively by comparing the results with corresponding climate and soil moisture data. It became evident, that the yearly progression of fires was linked to the precipitation and the corresponding soil moisture of the previous months. In addition, the relationships between these fire classes and the Fire Radiative Power (FRP) were analysed. For this purpose, VIIRS 375m FRP data were compared with the individual fire classes for each year. From the data it became evident, that higher severity in the classified fires corresponds to higher FRP values. Overall, a classification of the detected fires was achieved and the results of which were found to be compatible with available weather and soil moisture data. Furthermore, a correlation between the different fire classes and the measured FRP was determined.

© David Schleehahn

Comparing the German Forest Fire Danger Index and medium-resolution satellite Products for the Quantification of Fire Occurrence in central Europe

Study

MSc Geoinformation Technologies

Date of defence

13.01.2023

Supervisor

Matthias Forkel, Dr. Dirk Pflugmacher (Humboldt-Universität zu Berlin), Christopher Marrs

Abstract

 In this work, the German Forest Fire Danger Index (WBI) was investigated and compared with two Random Forest (RF) classifier models, that aim to predict the forest fire occurrence probability. These models were trained with remote sensing data and past fire events from the year 2020. Specifically, satellite data about the Leaf Area Index (LAI), the Land Surface Temperature (LST), the Surface Soil Moisture (SSM), the Soil Water Index (SWI) as well as other static spatial data about forest type, forest height, slope, aspect, day in the year of the fire event and population density were integrated. The first model included variables which were linked to the WBI, to create comparability. The second model included additional parameters that provide information about the fire ignition.

The evaluation of the WBI, with information on past fire events, burned area, land cover and its causes showed that the WBI does not warn according to its highest fire danger class. Furthermore, the WBI danger classes do not show distinct values in the satellite variables, which means that the warning levels cannot be clearly distinguished from each other. The results of the RF models predicting fire occurrence have an accuracy of 0.67 and 0.71, which can be rated as good.

Colouring and interactive visualization of historical Earth observation data

Study

MSc Cartography

Date of defence

23.09.2022

Supervisor

Matthias Forkel, Mathias Gröbe, Lucas Kugler

Abstract

In the 1960s, the US launched a series of satellite projects aimed at building a reconnaissance system. The CORONA project was in operation between 1960 and 1972. During the operation, a large number of satellite images were taken. Until 1995, these images remained classified. Since 1995 numerous researchers have exploited the CORONA images, primarily to study surface cover changes across the globe. This study adapts the existing DeOldify model, which is dedicated to colourising images to specifically colourise CORONA satellite images through retraining the model using the CORONA image dataset. The CORONA image dataset consists of greyscale CORONA images and colour reference images covering the same region and having little or no change in the image content. A generative adversarial network is used for building this model. A U-Net-based generator network and a binary-classifier-based critic network train in an alternative approach. To improve the training efficiency, transfer learning and NoGAN training techniques are implemented. The generated images are evaluated both quantitatively, using RMSE and PSNR, and qualitatively, using a user study asking the participant if the displayed colour image looks natural. Results show that generated images with good performance using RMSE and PSNR do not necessarily have plausible colours. Compared with the original DeOldify model, the retained model can produce images with more natural and plausible colours, achieving a result of 70.1% of the participants thinking they are real, although these images have poorer reconstructing quality. To visualise the results, a web mapping application is developed with Geoserver and Leaflet. The server stores data and publishes it through WMTS or WFS. Cache service and image pyramid are used to accelerate the response on the client side. The web map client provides an interactive map interface for the users to control the displayed layers and download the selected layer in a self-defined ROI through WPS.

Differentiation of Calluna vulgaris in seed germination and stock sprouting in the Kyritz-Ruppiner Heide in relation with maintenance activities

Study

MSc Spatial Development and Natural Resource Management

Date of defence

14.04.2022

Supervisor

Matthias Forkel, Dr. Carsten Neumann (GFZ Potsdam)

Abstract

The loss of biodiversity is evident in many areas. It is becoming increasingly visible and has many faces, with human influence playing a significant role. Humans are reshaping the planet through immense changes in land use. This influence also contributes to the preservation and creation of new ecosystems. Heathlands are an example of the (un)conscious action of humans, as this habitat was created and shaped by traditional human management. However, this habitat is now also under threat, as traditional agriculture has given way to industrial agriculture and management techniques have changed as a result. It was precisely these that ensured the resilience and thus the preservation of the habitat. Meanwhile, many of the heathland areas are over-aged and in poor to very poor condition. The 2019 FHH report additionally states that their condition will continue to deteriorate (BFN, 2019). The preservation of these habitats is thus dependent on human care.

The promotion of maintenance measures to rejuvenate the heather (Calluna vulgaris) stands is essential to build up a better structure and thus resilience of the entire habitat. The distinction between seed germination and re-sprouting is relevant here (Watt, 1955; Whittaker & Gimingham, 1962; Miller & Miles, 1970; Webb, 1986).
To distinguish between these vegetation types, it was hypothesised that there are differences in growth and flower formation. To validate this hypothesis, areas in the Kyritz-Ruppiner Heide were maintained by burning and mowing. The re-sprouting was recorded by means of regular drone recordings, which serve as data basis for this work. By using different indices, a classification of the individuals heather plants took place, which allowed conclusions to be drawn about the variables: area size, growth difference and flower formation. Based on the assumption that Calluna seedlings have a lower growth rate than re-sprouts, differences in area size and growth height can be assumed. Due to these dynamics, a later and shorter flowering period can also be assumed. Threshold values in the growth dynamics could be identified by means of stepwise adjustment of the variables and subsequent data analysis. In addition, links between flowering periods, growth periods and maintenance measures were identified. Natural areas created by humans develop through and with the influence of humans. To protect and maintain the biodiversity of these habitats, various measures are needed.

Model-based estimation of Live Fuel Moisture Content with Sentinel-1 radar data

Study

MSc Geoinformation Technologies

Date of defence

04.04.2022

Supervisor

Matthias Forkel, Dipl.-Ing. Ruxandra-Maria Zotta (TU Wien, Department of Geodesy and Geoinformation)

Abstract

The assessment of wildfire risk is of great importance worldwide, not least because of climate change. One important risk indicator is the live fuel moisture content (LFMC) defined as the ratio between plant water content and dry biomass, since a higher water content of vegetation decreases the probability of fire ignition and the speed of fire propagation.

Several studies demonstrated the potential of optical satellite data to estimate LFMC at the regional and global scale. However, since the use of optical sensors is limited by atmospheric influences and cloud coverage, microwave satellite data offers a potential alternative. This thesis focused on the potential of Sentinel-1 radar data for the retrieval of LFMC by modifying the approach of Wang et al. (2019), which combines the water cloud model (WCM) and a linear bare soil backscatter model. Since the above-mentioned approach does not consider influences of changes in biomass, vegetation structure and soil moisture on the radar backscatter, biophysical variables of vegetation and soil-related parameters were introduced as additional input in the WCM with the aim to assess their impact on the model’s accuracy. The model was first trained and validated with in-situ measurements available for study sites in the United States of America and subsequently transferred to forest locations in Europe, where LFMC measurements are few.

Using the additional variables, LFMC ground measurements, leaf area index (LAI) and volumetric soil moisture (VSW), the modified WCM was able to accurately simulate the contributions of soil and vegetation to the total radar backscatter. Compared to VSW, LAI exerted a stronger influence on model performance (R²) during the calibration process. To invert the model for the estimation of LFMC, an optimised look-up table (LUT) was built by running the WCM forward using all possible combinations of a predetermined range of values for the input variables. The inclusion of LAI and VSW in the minimisation of a cost function, used to retrieve the optimal LFMC from the LUT, enabled the transfer of the WCM to Europe, since the model accuracy depended primarily on relations between backscatter, LAI, LFMC and VSW. The relations were found to vary with the heterogeneity in prevalent vegetation species and the fraction of vegetation coverage. The derived LFMC values were classified into coniferous, broadleaved and mixed forest, and then validated with the MODIS LFMC product based on the algorithm by Yebra et al. (2018). Promising results for root mean square error (RMSE = 25 %, 26%) and coefficients of determination (R² = 0.50, 0.42) were obtained for deciduous and mixed forests, while the WCM resulted in higher inaccuracies for coniferous forests (RMSE = 45 %, R² = 0.17).

© Johanna Kranz

Predicting spatial patterns of forest fire using random forest machine learning algorithm in the Terai Arc Landscape of Nepal

Study

MSc Tropical Forestry and Management

Date of defence

14.01.2022

Supervisor

Matthias Forkel, Mir A. Matin

Abstract

Increasing forest fire events present novel challenges to forest ecosystems and human well-being. Early detection of forest fires and understanding interrelationship between forest fires and forest fire driving factors are considered important for effective fire management. Unerstanding the perception of decision-makers of existing fire management infrastructure and initiatives is equally important in order to implement preventive measures. We used VIIRS fire dataset (2012-2021), climatic, topographic, and infrastructure predictor variables aggregated over time to generate a fire susceptibility map from random forest (RF) machine learning algorithm. A key-informant questionnaire survey was also undertaken with the forestry professionals working in the TAL region to understand their perception of existing fire management initiatives. RF model achieved an overall accuracy of 72.8% and a sensitivity value of 88% in the evaluation dataset indicating a good predictive ability of fire occurrence. Most parts of the TAL region were susceptible to fire. Our findings of increased fire risk in some districts located at the south-west and north-east part of the TAL were unique to the findings of previous fire-related studies in TAL. Fire occurrence was lowest in 2020 (0.42%) followed by sharp increase in 2021 (19%). Broad-leaved forests were highly susceptible to fire. An increased number of fire events were observed with high temperatures. Fire events were higher in proximity to roads and settlements. Respondents were of the opinion that there is a need for effective management initiatives to improve existing quality and condition of fuel management infrastructure and fire management initiatives. These findings will assist in in the effective decision-making process of fire prevention and suppression reducing the potential future damage due to forest fires in the TAL region of Nepal.

Comparison of deep learning model structures for land cover classification using historical Corona satellite imagery

Study

MSc Geodesy

Date of defence

05.01.2022

Supervisor

Matthias Forkel, Philipp Körner

Abstract

Climate is strongly influenced by the characteristics of land cover, where water, energy and trace gases interact directly with the atmosphere. It is therefore not surprising that a change in land cover also causes a change in local climate and material cycles. Remote sensing has played a fundamental role in continuous earth observation and land cover change detection — at least since the launch of the Landsat satellite program (1972). In 1995, the Central Intelligence Agency from the United States of America released previously secret spy satellite images. These images are pan-chromatic satellite images taken from 1960 onwards with near-global coverage. The satellite images are particularly interesting because they contain information about land cover from 10 years before the beginning of civilian Earth observation. Nevertheless, there are a scarcely studied data source to date. Building on initial approaches, the present work investigates applying different neuronal networks to automatically extract land cover from CORONA data. The particular focus of the work is on the transferability of the approaches to unknown CORONA data. In the long term, the landscape cover is to be extracted from CORONA data on a large scale. To investigate the transferability, seven spatially and temporally distributed test areas in the the federal state Saxony, Germany were selected for cross-validation.

In the present study, a total of four different U-Net architectures were used. A U-Net is a deep neural network for semantic segmentation of image data. All four architectures have different capabilities and are optimised for different land cover classification challenges. As input three different image compositions. The first compostion is the original pixel values (one channel), the second is the GLCM texture measures (ten channels). The third composition is a simulated RGB image (three channels). These three compositions were combined into one image with 14 channels. In addition, semantic masks were created for all test areas to serve as reference data. For this purpose, the landscape coverage was divided into six classes. From these input data, seven different training datasets and test
datasets were derived for cross-validation. Based on the training datasets — four archi-
tectures were trained for each test area and then applied to the corresponding test data.   
Resulting from the training it could first be deduced that a classification of land cover from
CORONA data with the used architectures is possible. In all test areas, all architectures
achieved a training IOU above 85%. Poor to moderate IOU values were achieved for the
individual test areas. The best mean segmentation accuracy is 30.50%, while the worst
value for a test area is 12.71%. Strong accuracy variations were detected among the classes. Classes that have a lot of sample data achieve significantly better IOU values than
underrepresented classes. The best segmentation performance, with an average IOU of
54.51%, was obtained for the agricultural land class, closely followed by forest with 52.80%. For the classes shrub vegetation, open areas and water bodies mostly only IOU
values below 10% were achieved. For classes with many sample data, moderate to good segmentation accuracy was achieved for both spatial and temporal transferability. Since
the data set does not cover all factors for generalised transferability, transferability could
only be ensured under certain framework conditions. For example, the study does not
cover handling of clouds or CORONA data of poor quality.

As a conclusion it was recognised that a combination of results from different architectures might improve the outcome. As a outcome, it was recommended to consider this issue for further developments. 

Assessing the Spatial Variability of Above-ground Forest Carbon using Sentinel-1, Sentinel-2 and Field Inventory Data of the Miombo Woodlands in Songwe District, Tanzania.

Study

MSc Tropical Forestry

Date of defence

29.11.2021

Supervisor

Matthias Forkel, Hamidu Seki ( University of Dar es Salaam - Mkwawa University College of Education, Tanzania)

Abstract

Accurate estimates of above-ground biomass and carbon (AGC) are needed to understand the role of forests in the global carbon cycle. To achieve this, recent forest monitoring and assessment techniques now rely on integrating remote sensing and field inventory data to map and monitor carbon changes in tropical forests. More importantly, AGC spatial distribution is intricately linked to climate, soil, topography, and anthropogenic  disturbances, whose influences should be understood so that their spatial effects are utilised to sustain forest carbon. Hence, this study combined Sentinel-1 and Sentinel-2 variables with field inventory data in a generalised additive model (GAM) to map the Tanzanian Miombo AGC while explaining its spatial variability. Fifteen (15) models were trained and tested using the leave-one-out cross-validation in GAM. Model 6, containing selected predictors – B11 (Shortwave Infrared 1), NDVI (normalized difference vegetation index) and tree canopy cover (%tcc), indicated best prediction accuracy (R²  = 0.87) with the least error (RMSE = 5.24 tC/ha) and an upper bound prediction of 114.87 tC/ha. A combination of Sentinel-2 variables (B11 & NDVI) and %tcc are better predictors for mapping AGC in the study area. Overall, the spatial drivers explained 65.5 % of AGC spatial variability with elevation having the highest predictive power (21.65 %), followed by mean annual temperature (MAT; 21.10 %), the interaction effect of elevation and distance to settlement (20.99 %), distance to settlement (18.24 %) and silt content (18.02 %). The study also showed that AGC increases with increasing elevations and silt content and decreases  with increasing MAT and distance to settlement. More so, AGC increases accordingly with increasing interaction effect between elevation and distance to settlement. Therefore, understanding the impact of these factors on the distribution of AGC will be necessary for adequate forest planning and management.

Predicting, understanding, and visualizing fire dynamics with neural networks

Study

MSc Cartography

Date of defence

22.11.2021

Supervisor

Matthias Forkel, Tichaona Tavare Mukunga MSc. (TU Wien)

Abstract

As machine learning techniques are contributing to scientific research and advancement, the interpretability and visualisation of these algorithms grow in importance. These techniques have introduced many improvements to advance our understanding of fire regime dynamics outperforming process-based approaches. Neural networks have achieved great accuracy with fire modelling, however, challenges arise with unbalanced time series. In this thesis, LSTM neural networks, which are designed for sequence modeling and handling unbalanced data, are investigated to explore their ability to predict fire ignition points. The research is conducted for a small area in western Africa using monthly meteorological variables and fAPAR as an indicator for vegetation for a period spanning from 2003 to 2016. The chosen methodology is based on training one LSTM for each pixel independently. Datasets are pre-processed, structured as a multivariate time series and then arranged to fit LSTM 3D data format. The network architecture was chosen by conducting multiple experiments. The pixel-based LSTM was able to capture the seasonal and spatial varieties with RMSE value computed at 3.333. However, it underestimated the high values of ignitions during the peak of fire season and was not able to record sudden events. To better understand LSTM behavior, multiple interpretation techniques were investigated to evaluate their abilities to determine the most important features and visualise their dependencies. Permutation feature importance gave an overview of overall feature importance while variance-based feature importance was able to map the spatial distribution of each feature. SHAP summary plots gave a detailed interpretation of feature importance of precedent time steps. The most important features to predict fire ignitions were found to be fAPAR, precipitation and maximum temperature. Recent conditions were found more important north of the study area, whereas, in the middle and southern regions, precedent year conditions were of higher importance. SHAP dependence plots were able to depict feature-output relationships. Using these plots, it was observed that LSTM represented the fire-predictor relationship correctly only for a few variables. For feature interactions, a 3D extension of SHAP dependence plot with added color visual variable was found to be the best visualisation technique. Visualisation of LSTM helped with understanding how the model is learning and which variables were modelled correctly. From here, further improvements could be applied leading to increasing trust in machine learning approaches.

Increasing the accuracy of tree species classification in Sentinel-2 data through better informed feature selection

Study

MSc Geoinformation Technologies

Date of defence

15.10.2021

Supervisor

Matthias Forkel, Dzhaner Emin (iABG mbH)

Abstract

The tree species composition of forests plays a central role in sustainable forestry and nature conservation. With the help of multispectral remote sensing data and machine learning methods, tree species can be classified objectively and over a wide area with good results, as previous studies have shown. The aim of this master thesis is to increase the classification accuracy for tree species based on Sentinel-2 data using informed feature selection. The classification is based on inventory data of Thuringia, and the study area is located in western Thuringia and the five most common tree species there are classified. To increase the classification accuracy of the tree species, their spectral behaviour, phenology and topography are included in the classification. For this purpose, the Sentinel-2 scenes were first preprocessed with the free processing software FORCE and the spectral and phenological features were then derived from the Sentinel-2 time series and the topographic features from the SRTM-DEM. These were then used to conduct an exploratory data analysis to better understand the relationships between tree species and their species-specific characteristics, especially to gain insights for their classification. Finally, the tree species were classified in different random forest models with their spectral, phenological and topographic features and the importance of these features for their differentiation was determined using the "Mean Decrease Gini". The investigations show that the integration of the phenological and topographical features increased the classification accuracy by about 5 percent to 90 percent. The most important input features include the phenological features of the beginning and peak of the growing season, as well as the elevation and spectral bands of the SWIR. By applying a "second majority vote" on the different values of the spectral features, the classification accuracy could even be increased by several percent. The developed workflow for tree species classification and the gained knowledge should serve as inspiration for future tree species classifications and help to better understand tree species characteristics.

© Johannes Albert

Evaluation of the real land use in ATKIS with digital orthophotos and convolutional neural networks

Study

MSc Geoinformation Technologies

Date of defence

08.10.2021

Supervisor

Matthias Forkel, Gotthard Meinel (Leibniz Institute of Ecological Urban and Regional Development)

Abstract

The ATKIS-Basis-DLM is one of the most important databases in Germany regarding the modelling of the earth's surface. Based on the attribute "Real land use", numerous sustainability indicators are calculated in the IÖR-Monitor of the Leibniz Institute of Ecological Urban and Regional Development. However, there are still no reliable data on the quality of the Real land use.

The aim of this thesis was therefore to determine the quality of the recording of the Real land use in ATKIS. Regarding a possible automation of the process, it was tested in parallel whether and to what extent machine learning methods are suitable to take over this task. For this purpose, an artificial neural network was programmed to determine the Real land use based on high-resolution ortho-air images.

The starting point of the investigations was a manual classification of the Real land use in a randomly selected sample of 1,000 aerial images from the years 2012 and 2019. The basic selection of the sample was based on four different types of land use from the categories of non-urban and settlement. Both ATKIS and the neural network were compared with the manually created reference. It was found that ATKIS had the correct Real land use in 93.98% of cases examined. The neural network was able to detect the correct usage in 93.7% of cases. The general weaknesses of the two products are partially complementary to each other, so in the future a combined procedure could be developed to improve the quality of the Real land use in ATKIS.

© Denis Reiter

Estimating tree heights from mangrove forests using machine learning algorithms on combined Sentinel-1 and Sentinel-2 data

Study

MSc Geoinformation Technologies

Date of defence

30.09.2021

Supervisor

Matthias Forkel,  Uday Pimple (King Mongkuts University of Technology, Thonburi, Thailand)

Abstract

Mangrove forests are highly productive ecosystems that also offer coastal and inland protection against natural hazards such as tsunamis or hurricanes. As they are also one of the most threatened ecosystems, several projects now focus on natural regeneration and rehabilitation of formerly destroyed mangrove forests. With mangrove tree height, monitoring, regeneration and rehabilitation efforts can be observed and optimised as well supporting the estimation of above-ground biomass and analysing health status and effectiveness of CO₂ sequestration. Furthermore, tree heights can be used as a level of protection against natural hazards. Field measurements in Trat, Thailand, resulted in three transect lines that run perpendicular to the coast and consist in sum of 59, 10 m × 10 m, plots containing the mean tree height per plot. With two Sentinel-2 scenes, the spectral vegetation indices Normalised Difference Vegetation Index (NDVI) and Chlorophyll Vegetation Index (CVI) were calculated as well as the red-edge band "B8A" was extracted for the analysis. Mean Vertical-Horizontal (VH)-backscatter coefficients of four low tide ground range detected Sentinel-1 scenes support the Sentinel-2 variables as independent observations for a Random Forest Regression (RFR) and a Support Vector Regression (SVR). A site-specific division into training and test plots resulted in meaningful validation results with Root Mean Squared Errors (RMSE) of approx. 1.60 m and two models that can be used to estimate mangrove tree heights of the entire mangrove forest in Trat. A tree height distribution map shows that vertical structural diversity varies along the intertidal zones. Additionally, a three-fold cross validation gave an overview of possible accuracies that a model can achieve, depending on the selection of training and test samples. When calculating the average tree height from the estimations of all three models from each fold, a standard deviation (SD) map can reveal prediction errors. Especially the RFR-SD map was able to detect uncertainties because of clouds in a used Sentinel-2 scene. A comparison of the mangrove tree height distribution map with a species distribution map revealed that regeneration efforts in Trat were successful.

© Nadja Krause

Estimating high-resolution land surface temperature by integrating Landsat-8, Sentinel-1 and Sentinel-2 using a Random Forest algorithm

Study

MSc Geodesy

Date of defence

20.09.2021

Supervisor

Matthias Forkel, Anette Eltner

Abstract

Land Surface Temperature (LST) observations enable a better understanding of the ecosystem since LST is connected to water, energy and carbon fluxes. A couple of satellite systems provide relevant information for the calculation of LST using thermal infrared (TIR) bands. However, the data is available either at high spatial or temporal resolution which disables monitoring approaches at small scale. In order to fill the gap between the spatial and temporal resolution, downscaling algorithms have been developed, reaching a spatial resolution of 30m. The aim of this master thesis is to develop an algorithm that is able to contribute higher spatial resolution of 10m getting closer to monitoring approaches at small scale. The combination of both Sentinel-1 (S1) and Sentinel-2 (S2) data is a promising benefit since both contribute high spatial resolution. Further, S1 data is sensitive to the water content in vegetation and therefore correlates with LST. Together with a digital elevation model (DEM), features derived from S1 and S2 serve as predictors in order to train a Random Forest model. Four strategies were tested, each consisting in a set of features, an evaluation method and a specified training and target resolution. The first strategy uses the same satellite scene at different spatial resolution. Therefore, a Random Forest model trains features against Sentinel-3 (S3) LST at 1000m, while it is tested against Landsat-8 (L8) LST at 30m. Spatial Cross Validation (SCV) serves as evaluation method in all other strategies, separating the study area into four subsets. In doing so, they train a Random Forest model where the training dataset holds three subsets while the remaining one acts as testing dataset. These strategies are conducted with data at 1000m on the one hand and on the other with data at 30m spatial resolution. Since the datasets at 30m are trained against L8 LST, S3 LST is included as feature in one of the strategies. Best results were achieved with spatial cross validation at 30m resolution containing B12, DEM, NDVI, NDWI, SRWI and S3 LST as feature. Comparing predicted and observed LST, the Root Mean Square Error (RMSE) is 1.62K while the coefficient of determination (R²) is 0.73 and the correlation coefficient amounts to 0.86. In general, the trained Random Forest model tends to predict lower temperatures for urban areas and higher ones for forests. Features derived from S1 do not improve the results. The reason  could be found in different acquisition times of the data or that other research use soil moisture derived from S1 backscatter instead of S1 observations themselves. However, spatial cross validation was not found to be well suited as evaluation method and could have an impact on the results making them less reliable. The outcomes also present that some information is missing to fully explain the relationship between LST and features. To solve this issue, other combinations of features and the addition of new ones, e.g. soil moisture, fractional green vegetation cover and air temperature, should be considered.

Assessing environmental controls on phenology with dense Landsat and Sentinel-2 time series in Andean Araucaria forests of Chile

Study

MSc Geodesy

Date of defence

19.08.2021

Supervisor

Matthias Forkel,  Jaime Hernández (Universidad de Chile)

Abstract

Araucaria araucana, commonly called “monkey puzzle tree”, is an endemic, evergreen conifer native to the temperate woodlands of the South American Andes and has a high cultural importance for indigenous tribes and Chilean identity. It typically occurs together with several southern beech species (Nothofagus spp.), forming the characteristic Araucaria-Nothofagus forests. Human exploitation and lack of preservation have led to widespread landscape fragmentation in south-central Chile and Argentina, their only natural habitat. The effects of ongoing climate change are another major threat to the forest ecosystem. Analysing the phenological traits of terrestrial vegetation is one of the key factors in assessing long- and short-term trends of plant growth. However, no detailed study has ever been conducted that investigates the phenology of Araucaria forest stands. In this master’s thesis, the natural phenological variability of undisturbed Araucaria forests in a Chilean national park was analysed between 2016 and 2020 using high-resolution satellite imagery. Dense NDVI and EVI time series of Landsat 8 and Sentinel-2 observations were smoothed and interpolated and phenological parameters, such as the onsets of greenness and senescence were extracted after carefully examining various suitable techniques. These metrics were then closely evaluated and compared with variations in topography, climate, species composition and tree height using a Random Forest model in order to identify the drivers of phenology changes. The results showed high dependencies of start and end of season on elevation with forest stands over 1400 m experiencing an increasingly delayed reaction. The maximum value of vegetation greenness throughout the year was also positively correlated with the timing of phenological events. Furthermore, it was identified that growth started earlier on average in areas where the dominant species is Nothofagus dombeyi and later where Nothofagus antarctica dominates the forest. A possibly related finding could be made for tree height with taller trees experiencing an advanced start of season and vice versa. End-of-season events showed much fewer spatial differences. Temporally, no explicit trend was detected in the study period, but smaller connections to climate could be revealed for most years. It was also discovered that EVI serves as a much better indicator of plant productivity in the region than NDVI. The results prove that several phenological differences exist within the complex Araucaria forest ecosystem. These characteristics and their influence factors help to better understand the dynamics of untouched forest stands in the region, especially with regard to future challenges caused by climate change and can be a basis for local authorities in developing better forest management and conservation strategies within and outside of protected areas. As part of a joint project between TU Dresden and Universidad de Chile, this master’s thesis also delivers important contributions to ongoing research activities about the impact of human influence on the Araucaria forest ecosystem.

© Eric Koszor

Capability of CNNs for analyzing land cover using historical CORONA data

Study

MSc Geography

Date of defence

15.10.2020

Supervisor

Matthias Forkel,   Pierre Karrasch

Abstract

Land cover and the climate system are closely interlinked components. This interlinkage means that the decades-long change in land cover also plays a significant role in climate change. With the help of remote sensing and the civilian Landsat satellites, it has been possible to monitor land cover since 1972 continuously. There have also been earlier efforts to monitor the earth with satellites. The military satellite program CORONA was able to take single-channel images of the earth's surface from 1959 to1972. These images were not made available to the public until 1995. Until today they are a barely used data source for land cover change worldwide. This work aims to develop a Convolutional Neural Network (CNN), which can automatically extract land cover from CORONA images. The  CNN  was trained and evaluated based on the study areas Saxon Switzerland and Zittau Mountains. Germany in 1965. CNN is a method of machine learning, which is particularly suitable for the processing of image data. In remote sensing, CNNs have already been successfully used for object recognition and classification of multispectral data. So far, however, there are no detailed studies on the use of single-channel images for land cover classification.

For this study, three different input data were generated from the CORONA data: the first is the unchanged, original pixel values of the CORONA images; the second is calculated GLCM texture measures, which include the neighbouring pixels for calculation; the last are the original pixel values together with the landscape metrics of a previous segmentation. Based on these input data and existing information about the land cover of the study area in 1965, image sections for the individual land cover classes were extracted. The learning and training of CNN needed these image sections. In total, six different training options were investigated. The first finding from the training was the very low accuracy of the CNNs that trained on the landscape metrics. With an accuracy of less than 50%, they were far below the results of the other two input data of 85% to 90%. As a result, the landscape metrics were not considered for the rest of the study. The training accuracies were compared, and the best three with accuracies of 83% were applied to the two study areas. One model classified on the Original Pixel Values and the other two on the Texture Measures.

Using an iterating search window, the CNN models were deployed to the study areas. Classification accuracies between 69% and 75% were achieved for the study area Saxon Switzerland. The application to the study area Zittau Mountains did not achieve such high values. The Original Pixel Values attained an accuracy of 61% while the Texture Measures only yielded an accuracy of 1.8% and 3.5%. These results indicate an overtraining of the model since drastically reduced accuracies were achieved in the Zittau Mountains region. Reasons for this could be an unequal distribution of the training data for the individual land cover classes, differences between the two CORONA images, and homogeneity of the image values between the individual land cover classes. A concluding analysis of the land cover change between 1965 and 2012 showed an increase in urban and agricultural areas. The open-cast mining and the subsequent natural conversion characterises the Zittau Mountains area. The forested area has not changed significantly in the 47 years.

© Susanne Otto

Potential of multi-temporal Sentinel-2 data to retrieve leaf live-fuel moisture content

Study

BSc Geodesy and Geoinformation

Date of defence

08.10.2020

Supervisor

Matthias Forkel, Luisa Schmidt

Abstract

The objectives of this thesis are the evaluation of already proven spectral indices, development of new approaches using the red-edge and the development of
multi-variate regression models in terms of Live Fuel Moisture Content (LFMC)
approximation. The data used in this thesis is multi-spectral bottom of the atmosphere Sentinel-2 data and LFMC in-situ data from the National Fuel Moisture Database (NFMD). The results of other studies regarding correlations between short wave infrared (SWIR) indices and LFMC cannot be confirmed. However the results of indices using bands of the red-edge or near red-edge bands are promising in that regard. In addition to this, when developing new models based on Sentinel-2 data for LFMC approximation, a new method is developed. For the purpose of model development, a new method is being developed that uses explorative factor analysis (EFA) to derive latent factors of strongly correlated
indices in order to solve the problem of multi-variant models with multicollinearity. In this context, a workflow for the development with this method is proposed. Furthermore, these derived latent factors are combined with other indices in multi-variate regression models. These are developed for the land cover types bushland and grassland and yield both similar results with R² = 0.610 for shrubland and R² = 0.666 for grassland. The developed models will also be tested individually on individual vegetation species and locations. These tests show the robustness of the developed latent factors and the developed LFMC models in comparison to the individual indices.

Developing Data Cylinders to map changes and feedbacks between Arctic Sea Ice and Vegetation

Study

MSc Cartography

Date of defence

28.09.2020

Supervisor

Matthias Forkel, Dr. Paulo Raposo (University of Twente)

Abstract

Arctic sea ice hits second-lowest level on record in 2020 and a “new Arctic” climate era is commencing (Landrum & Holland, 2020). Living on a planet which is facing a global climate change, the understanding and the communication of those vast environmental changes have great importance. The objective of this thesis is the development of a three-dimensional spatio-temporal visual, in a cylindrical shape due to the circularity of the Arctic region, depicting the analysis of the changes of the sea ice and vegetation in the Arctic. Level4 remote sensing data is used for the vegetation and sea ice concentration in a pan-arctic scale for the needs of this research. Its main outcomes are the changes themselves mirrored through their anomalies, and the creation of one cartographic product which illustrates these phenomena in the best suitable way.The representation of time and space in a single visual has been viewed as a challenge in the field of modern cartography for many decades. While data-cubes have been proposed for regional or even global geographical data visualisation, the polar regions seem not suitable for such cubes. The proposed cartographic representation of the Arctic space and time into “Data-Cylinders” responds to the challenging befitting of physical phenomena along space and time.The context of the “Data-Cylinders” includes the visualisation of the changes of climatic and physical phenomena in the form of time-series. A cylinder in this case could be described as many circular maps on top of the other in chronological order. “Space” in this scenario is placed across cycles, while “time” is given along the height of the cylinder.