@misc{Daempfling2021,
  type      = {Master Thesis},
  author    = {D{\"a}mpfling, Helge Leoard Carl},
  title     = {DeepGeoMap},
  doi       = {10.25932/publishup-52057},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-520575},
  school      = {Universit{\"a}t Potsdam},
  pages     = {ii, 81},
  year      = {2021},
  abstract  = {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.},
  language  = {en}
}
@misc{SeleemAyzelCostaTomazdeSouzaetal.2022,
  author    = {Seleem, Omar and Ayzel, Georgy and Costa Tomaz de Souza, Arthur and Bronstert, Axel and Heistermann, Maik},
  title     = {Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany},
  series = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  journal   = {Zweitver{\"o}ffentlichungen der Universit{\"a}t Potsdam : Mathematisch-Naturwissenschaftliche Reihe},
  number    = {1297},
  issn      = {1866-8372},
  doi       = {10.25932/publishup-57680},
  url       = {http://nbn-resolving.de/urn:nbn:de:kobv:517-opus4-576806},
  pages     = {1640 -- 1662},
  year      = {2022},
  abstract  = {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.},
  language  = {en}
}
@article{SeleemAyzelCostaTomazdeSouzaetal.2022,
  author    = {Seleem, Omar and Ayzel, Georgy and Costa Tomaz de Souza, Arthur and Bronstert, Axel and Heistermann, Maik},
  title     = {Towards urban flood susceptibility mapping using data-driven models in Berlin, Germany},
  series = {Geomatics, natural hazards and risk},
  volume    = {13},
  journal   = {Geomatics, natural hazards and risk},
  number    = {1},
  publisher = {Taylor \& Francis},
  address   = {London},
  issn      = {1947-5705},
  doi       = {10.1080/19475705.2022.2097131},
  pages     = {1640 -- 1662},
  year      = {2022},
  abstract  = {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.},
  language  = {en}
}
@article{SchoenfeldtWinocurPaneketal.2022,
  author    = {Sch{\"o}nfeldt, Elisabeth and Winocur, Diego and P{\´a}nek, Tom{\´a}š and Korup, Oliver},
  title     = {Deep learning reveals one of Earth's largest landslide terrain in Patagonia},
  series = {Earth \& planetary science letters},
  volume    = {593},
  journal   = {Earth \& planetary science letters},
  publisher = {Elsevier},
  address   = {Amsterdam [u.a.]},
  issn      = {0012-821X},
  doi       = {10.1016/j.epsl.2022.117642},
  pages     = {13},
  year      = {2022},
  abstract  = {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.},
  language  = {en}
}