There is a growing demand for detailed and accurate landslide maps and inventories around the globe, but particularly in hazard-prone regions such as the Himalayas. Most standard mapping methods require expert knowledge, supervision and fieldwork. In this study, we use optical data from the Rapid Eye satellite and topographic factors to analyze the potential of machine learning methods, i.e., artificial neural network (ANN), support vector machines (SVM) and random forest (RF), and different deep-learning convolution neural networks (CNNs) for landslide detection. We use two training zones and one test zone to independently evaluate the performance of different methods in the highly landslide-prone Rasuwa district in Nepal. Twenty different maps are created using ANN, SVM and RF and different CNN instantiations and are compared against the results of extensive fieldwork through a mean intersection-over-union (mIOU) and other common metrics. This accuracy assessment yields the best result of 78.26% mIOU for a small window size CNN, which uses spectral information only. The additional information from a 5 m digital elevation model helps to discriminate between human settlements and landslides but does not improve the overall classification accuracy. CNNs do not automatically outperform ANN, SVM and RF, although this is sometimes claimed. Rather, the performance of CNNs strongly depends on their design, i.e., layer depth, input window sizes and training strategies. Here, we conclude that the CNN method is still in its infancy as most researchers will either use predefined parameters in solutions like Google TensorFlow or will apply different settings in a trial-and-error manner. Nevertheless, deep-learning can improve landslide mapping in the future if the effects of the different designs are better understood, enough training samples exist, and the effects of augmentation strategies to artificially increase the number of existing samples are better understood.

This study introduces Landslide4Sense , a reference benchmark for landslide detection from remote sensing. The repository features 3,799 image patches fusing optical layers from Sentinel-2 sensors with the digital elevation model and slope layer derived from ALOS PALSAR. The added topographical information facilitates an accurate detection of landslide borders, which recent researches have shown to be challenging using optical data alone. The extensive data set supports deep learning (DL) studies in landslide detection and the development and validation of methods for the systematic update of landslide inventories. The benchmark data set has been collected at four different times and geographical locations: Iburi (September 2018), Kodagu (August 2018), Gorkha (April 2015), and Taiwan (August 2009). Each image pixel is labelled as belonging to a landslide or not, incorporating various sources and thorough manual annotation. We then evaluate the landslide detection performance of 11 state-of-the-art DL segmentation models: U-Net, ResU-Net, PSPNet, ContextNet, DeepLab-v2, DeepLab-v3+, FCN-8s, LinkNet, FRRN-A, FRRN-B, and SQNet. All models were trained from scratch on patches from one quarter of each study area and tested on independent patches from the other three quarters. Our experiments demonstrate that ResU-Net outperformed the other models for the landslide detection task. We make the multi-source landslide benchmark data (Landslide4Sense) and the tested DL models publicly available at https://www.iarai.ac.at/landslide4sense, establishing an important resource for remote sensing, computer vision, and machine learning communities in studies of image classification in general and applications to landslide detection in particular.

Recent landslide detection studies have focused on pixel-based deep learning (DL) approaches. In contrast, intuitive annotation of landslides from satellite imagery is based on distinct features rather than individual pixels. This study examines the feasibility of the integration framework of a DL model with rule-based object-based image analysis (OBIA) to detect landslides. First, we designed a ResU-Net model and then trained and tested it in the Sentinel-2 imagery. Then we developed a simple rule-based OBIA with only four rulesets, applying it first to the original image dataset and then to the same dataset plus the resulting ResU-Net heatmap. The value of each pixel in the heatmap refers to the probability that the pixel belongs to either landslide or non-landslide classes. Thus, we evaluate three scenarios: ResU-Net, OBIA, and ResU-Net-OBIA. The landslide detection maps from three different classification scenarios were compared against a manual landslide inventory map using thematic accuracy assessment metrics: precision, recall, and f1-score. Our experiments in the testing area showed that the proposed integration framework yields f1-score values 8 and 22 percentage points higher than those of the ResU-Net and OBIA approaches, respectively.

Recently, global climate change discussions have become more prominent, and forests are considered as the ecosystems most at risk by the consequences of climate change. Wildfires are among one of the main drivers leading to losses in forested areas. The increasing availability of free remotely sensed data has enabled the precise locations of wildfires to be reliably monitored. A wildfire data inventory was created by integrating global positioning system (GPS) polygons with data collected from the moderate resolution imaging spectroradiometer (MODIS) thermal anomalies product between 2012 and 2017 for Amol County, northern Iran. The GPS polygon dataset from the state wildlife organization was gathered through extensive field surveys. The integrated inventory dataset, along with sixteen conditioning factors (topographic, meteorological, vegetation, anthropological, and hydrological factors), was used to evaluate the potential of different machine learning (ML) approaches for the spatial prediction of wildfire susceptibility. The applied ML approaches included an artificial neural network (ANN), support vector machines (SVM), and random forest (RF). All ML approaches were trained using 75% of the wildfire inventory dataset and tested using the remaining 25% of the dataset in the four-fold cross-validation (CV) procedure. The CV method is used for dealing with the randomness effects of the training and testing dataset selection on the performance of applied ML approaches. To validate the resulting wildfire susceptibility maps based on three different ML approaches and four different folds of inventory datasets, the true positive and false positive rates were calculated. In the following, the accuracy of each of the twelve resulting maps was assessed through the receiver operating characteristics (ROC) curve. The resulting CV accuracies were 74%, 79% and 88% for the ANN, SVM and RF, respectively.