TY  - THES
A1  - Dämpfling, Helge Leoard Carl
T1  - DeepGeoMap
BT  - a deep learning convolutional neural network architecture for geological hyperspectral classification and mapping
N2  - In recent years, deep learning improved the way remote sensing data is processed. The classification of hyperspectral data is no exception. 2D or 3D convolutional neural networks have outperformed classical algorithms on hyperspectral image classification in many cases. However, geological hyperspectral image classification includes several challenges, often including spatially more complex objects than found in other disciplines of hyperspectral imaging that have more spatially similar objects (e.g., as in industrial applications, aerial urban- or farming land cover types). In geological hyperspectral image classification, classical algorithms that focus on the spectral domain still often show higher accuracy, more sensible results, or flexibility due to spatial information independence. In the framework of this thesis, inspired by classical machine learning algorithms that focus on the spectral domain like the binary feature fitting- (BFF) and the EnGeoMap algorithm, the author of this thesis proposes, develops, tests, and discusses a novel, spectrally focused, spatial information independent, deep multi-layer convolutional neural network, named  'DeepGeoMap’, for hyperspectral geological data classification. More specifically, the architecture of DeepGeoMap uses a sequential series of different 1D convolutional neural networks layers and fully connected dense layers and utilizes rectified linear unit and softmax activation, 1D max and 1D global average pooling layers, additional dropout to prevent overfitting, and a categorical cross-entropy loss function with Adam gradient descent optimization. DeepGeoMap was realized using Python 3.7 and the machine and deep learning interface TensorFlow with graphical processing unit (GPU) acceleration. This 1D spectrally focused architecture allows DeepGeoMap models to be trained with hyperspectral laboratory image data of geochemically validated samples (e.g., ground truth samples for aerial or mine face images) and then use this laboratory trained model to classify other or larger scenes, similar to classical algorithms that use a spectral library of validated samples for image classification. The classification capabilities of DeepGeoMap have been tested using two geological hyperspectral image data sets. Both are geochemically validated hyperspectral data sets one based on iron ore and the other based on copper ore samples. The copper ore laboratory data set was used to train a DeepGeoMap model for the classification and analysis of a larger mine face scene within the Republic of Cyprus, where the samples originated from. Additionally, a benchmark satellite-based dataset, the Indian Pines data set, was used for training and testing. The classification accuracy of DeepGeoMap was compared to classical algorithms and other convolutional neural networks. It was shown that DeepGeoMap could achieve higher accuracies and outperform these classical algorithms and other neural networks in the geological hyperspectral image classification test cases. The spectral focus of DeepGeoMap was found to be the most considerable advantage compared to spectral-spatial classifiers like 2D or 3D neural networks. This enables DeepGeoMap models to train data independently of different spatial entities, shapes, and/or resolutions.
N2  - In den letzten Jahren hat Deep Learning die Verarbeitung von Fernerkundungsdaten verbessert. Die Klassifizierung hyperspektraler Daten ist keine Ausnahme. 2D- oder 3D-Convolutional Neural Networks haben in vielen Fällen klassische Algorithmen zur hyperspektralen Bildklassifizierung übertroffen. Die Klassifikation geologischer hyperspektraler Bilder beinhaltet jedoch mehrere Herausforderungen, die oft räumlich komplexere Objekte umfassen als in anderen Disziplinen der hyperspektralen Bildanalyse, die in der Regel räumlich ähnlichere Objekte aufweisen (z. B. in industriellen Anwendungen, städtischen oder landwirtschaftlichen Luftaufnahmen). Bei der geologischen hyperspektralen Bildklassifizierung zeigen klassische Algorithmen, die sich auf den Spektralbereich konzentrieren, oft noch eine höhere Klassifizierungsgenauigkeit, sinnvollere Ergebnisse oder Flexibilität aufgrund räumlicher Informationsunabhängigkeit. Im Rahmen dieser Arbeit, inspiriert von klassischen maschinellen Lernalgorithmen, die sich auf den spektralen Bereich konzentrieren, wie dem Binary Feature Fitting- (BFF) und dem EnGeoMap-Algorithmus, schlägt der Autor dieser Arbeit ein neuartiges, spektral fokussiertes, räumlich unabhängiges, tiefes mehrschichtiges neuronales Faltungsnetzwerk (Deep Convolutional Neural Network) mit dem Namen "DeepGeoMap" für die hyperspektrale geologische Datenklassifizierung vor. Genauer gesagt verwendet die Architektur von DeepGeoMap eine sequenzielle Reihe verschiedener „1D-Convolutional-Layer“ und „1D-Dense-Layer“ und verwendet ReLU und Softmax-Aktivierung, "1D-Max- und 1D-Global-Average-Pooling-Layer“, ein zusätzliches "Dropout-Layer", um ein „Overfitting“ zu verhindern, und eine kategoriale Kreuzentropieverlustfunktion mit Adam-Gradientenabstiegsoptimierung. DeepGeoMap wurde mit Python 3.7 und der Machine- und Deep-Learning-Schnittstelle TensorFlow mit Grafikartenbeschleunigung (GPU) realisiert. Diese spektral fokussierte 1D-Architektur ermöglicht das Trainieren von DeepGeoMap-Modellen mit hyperspektralen Laborbilddaten geochemisch validierter Proben (nach dem Vorbild klassischer Algorithmen, die eine Spektralbibliothek validierter Proben zur Bildklassifizierung verwenden). Die Klassifizierungsfähigkeiten von DeepGeoMap wurden mit zwei geologischen hyperspektralen Bilddatensätzen getestet. Bei beiden handelt es sich um geochemisch validierte hyperspektrale Datensätze, von denen einer auf Eisenerz und der andere auf Kupfererzproben basiert. Der Kupfererz-Labordatensatz wurde verwendet, um ein DeepGeoMap-Modell für die Klassifizierung und Analyse einer größeren Tagebauwandszene in der Republik Zypern, aus der die Proben stammten, zu trainieren. Darüber hinaus wurde ein satellitenbasierter Benchmark-Datensatz, der Indian Pines-Datensatz, für Training und Tests verwendet. Die Klassifikationsgenauigkeit von DeepGeoMap wurde mit klassischen Algorithmen und anderen neuronalen Faltungsnetzen verglichen. Es wurde gezeigt, dass DeepGeoMap höhere Genauigkeiten erreichen und diese klassischen Algorithmen und andere neuronale Netze in den Testfällen der geologischen hyperspektralen Bildklassifizierung übertreffen kann. Der spektrale Fokus von DeepGeoMap erwies sich als der größte Vorteil gegenüber spektral-räumlichen Klassifikatoren wie 2D- oder 3D-Convolutional Neural Networks. Dadurch können DeepGeoMap-Modelle Daten unabhängig von unterschiedlichen räumlichen Einheiten, Formen und/oder Auflösungen trainieren.
KW  - deep learning
KW  - convolutional neural network
KW  - geological hyperspectral image classification
KW  - deep learning
KW  - faltendes neuronales Netzwerk
KW  - geologische hyperspektrale Bildklassifikation
Y1  - 2021
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-520575
ER  - 
TY  - GEN
A1  - Seleem, Omar
A1  - Ayzel, Georgy
A1  - Costa Tomaz de Souza, Arthur
A1  - Bronstert, Axel
A1  - Heistermann, Maik
T1  - Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany
T2  - Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe
N2  - Identifying urban pluvial flood-prone areas is necessary but the application of two-dimensional hydrodynamic models is limited to small areas. Data-driven models have been showing their ability to map flood susceptibility but their application in urban pluvial flooding is still rare. A flood inventory (4333 flooded locations) and 11 factors which potentially indicate an increased hazard for pluvial flooding were used to implement convolutional neural network (CNN), artificial neural network (ANN), random forest (RF) and support vector machine (SVM) to: (1) Map flood susceptibility in Berlin at 30, 10, 5, and 2 m spatial resolutions. (2) Evaluate the trained models' transferability in space. (3) Estimate the most useful factors for flood susceptibility mapping. The models' performance was validated using the Kappa, and the area under the receiver operating characteristic curve (AUC). The results indicated that all models perform very well (minimum AUC = 0.87 for the testing dataset). The RF models outperformed all other models at all spatial resolutions and the RF model at 2 m spatial resolution was superior for the present flood inventory and predictor variables. The majority of the models had a moderate performance for predictions outside the training area based on Kappa evaluation (minimum AUC = 0.8). Aspect and altitude were the most influencing factors on the image-based and point-based models respectively. Data-driven models can be a reliable tool for urban pluvial flood susceptibility mapping wherever a reliable flood inventory is available.
T3  - Zweitveröffentlichungen der Universität Potsdam : Mathematisch-Naturwissenschaftliche Reihe - 1297 
KW  - Urban pluvial flood susceptibility
KW  - convolutional neural network
KW  - deep learning
KW  - random forest
KW  - support vector machine
KW  - spatial resolution
KW  - flood predictors
Y1  - 2023
U6  - http://nbn-resolving.de/urn/resolver.pl?urn:nbn:de:kobv:517-opus4-576806
SN  - 1866-8372
IS  - 1297
SP  - 1640
EP  - 1662
ER  - 
TY  - JOUR
A1  - Seleem, Omar
A1  - Ayzel, Georgy
A1  - Costa Tomaz de Souza, Arthur
A1  - Bronstert, Axel
A1  - Heistermann, Maik
T1  - Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany
JF  - Geomatics, natural hazards and risk
N2  - Identifying urban pluvial flood-prone areas is necessary but the application of two-dimensional hydrodynamic models is limited to small areas. Data-driven models have been showing their ability to map flood susceptibility but their application in urban pluvial flooding is still rare. A flood inventory (4333 flooded locations) and 11 factors which potentially indicate an increased hazard for pluvial flooding were used to implement convolutional neural network (CNN), artificial neural network (ANN), random forest (RF) and support vector machine (SVM) to: (1) Map flood susceptibility in Berlin at 30, 10, 5, and 2 m spatial resolutions. (2) Evaluate the trained models' transferability in space. (3) Estimate the most useful factors for flood susceptibility mapping. The models' performance was validated using the Kappa, and the area under the receiver operating characteristic curve (AUC). The results indicated that all models perform very well (minimum AUC = 0.87 for the testing dataset). The RF models outperformed all other models at all spatial resolutions and the RF model at 2 m spatial resolution was superior for the present flood inventory and predictor variables. The majority of the models had a moderate performance for predictions outside the training area based on Kappa evaluation (minimum AUC = 0.8). Aspect and altitude were the most influencing factors on the image-based and point-based models respectively. Data-driven models can be a reliable tool for urban pluvial flood susceptibility mapping wherever a reliable flood inventory is available.
KW  - Urban pluvial flood susceptibility
KW  - convolutional neural network
KW  - deep
KW  - learning
KW  - random forest
KW  - support vector machine
KW  - spatial resolution;
KW  - flood predictors
Y1  - 2022
U6  - https://doi.org/10.1080/19475705.2022.2097131
SN  - 1947-5705
SN  - 1947-5713
VL  - 13
IS  - 1
SP  - 1640
EP  - 1662
PB  - Taylor & Francis
CY  - London
ER  - 
TY  - JOUR
A1  - Schönfeldt, Elisabeth
A1  - Winocur, Diego
A1  - Pánek, Tomáš
A1  - Korup, Oliver
T1  - Deep learning reveals one of Earth's largest landslide terrain in Patagonia
JF  - Earth & planetary science letters
N2  - Hundreds of basaltic plateau margins east of the Patagonian Cordillera are undermined by numerous giant slope failures. However, the overall extent of this widespread type of plateau collapse remains unknown and incompletely captured in local maps. To detect giant slope failures consistently throughout the region, we train two convolutional neural networks (CNNs), AlexNet and U-Net, with Sentinel-2 optical data and TanDEM-X topographic data on elevation, surface roughness, and curvature. We validated the performance of these CNNs with independent testing data and found that AlexNet performed better when learned on topographic data, and UNet when learned on optical data. AlexNet predicts a total landslide area of 12,000 km2 in a study area of 450,000 km2, and thus one of Earth's largest clusters of giant landslides. These are mostly lateral spreads and rotational failures in effusive rocks, particularly eroding the margins of basaltic plateaus; some giant landslides occurred along shores of former glacial lakes, but are least prevalent in Quaternary sedimentary rocks. Given the roughly comparable topographic, climatic, and seismic conditions in our study area, we infer that basalts topping weak sedimentary rocks may have elevated potential for large-scale slope failure. Judging from the many newly detected and previously unknown landslides, we conclude that CNNs can be a valuable tool to detect large-scale slope instability at the regional scale. However, visual inspection is still necessary to validate results and correctly outline individual landslide source and deposit areas.
KW  - landslide detection
KW  - convolutional neural network
KW  - Patagonia
Y1  - 2022
U6  - https://doi.org/10.1016/j.epsl.2022.117642
SN  - 0012-821X
SN  - 1385-013X
VL  - 593
PB  - Elsevier
CY  - Amsterdam [u.a.]
ER  -