Event-based landslide inventories are essential sources to broaden our understanding of the causal relationship between triggering events and the occurring landslides. Moreover, detailed inventories are crucial for the succeeding phases of landslide risk studies like susceptibility and hazard assessment. The openly available inventories differ in the quality and completeness levels. Event-based landslide inventories are created based on manual interpretation, and there can be significant differences in the mapping preferences among interpreters. To address this issue, we used two different datasets to analyze the potential of U-Net and machine learning approaches for automated landslide detection in the Himalayas. Dataset-1 is composed of five optical bands from the RapidEye satellite imagery. Dataset-2 is composed of the RapidEye optical data, and ALOS-PALSAR derived topographical data. We used a small dataset consisting of 239 samples acquired from several training zones and one testing zone to evaluate our models’ performance using the fully convolutional U-Net model, Support Vector Machines (SVM), K-Nearest Neighbor, and the Random Forest (RF). We created thirty-two different maps to evaluate and understand the implications of different sample patch sizes and their effect on the accuracy of landslide detection in the study area. The results were then compared against the manually interpreted inventory compiled using fieldwork and visual interpretation of the RapidEye satellite image. We used accuracy assessment metrics such as F1-score, Precision, Recall, and Mathews Correlation Coefficient (MCC). In the context of the Nepali Himalayas, employing RapidEye images and machine learning models, a viable patch size was investigated. The U-Net model trained with 128 × 128 pixel patch size yields the best MCC results (76.59%) with the dataset-1. The added information from the digital elevation model benefited the overall detection of landslides. However, it does not improve the model’s overall accuracy but helps differentiate human settlement areas and river sand bars. In this study, the U-Net achieved slightly better results than other machine learning approaches. Although it can depend on architecture of the U-Net model and the complexity of the geographical features in the imagery, the U-Net model is still preliminary in the domain of landslide detection. There is very little literature available related to the use of U-Net for landslide detection. This study is one of the first efforts of using U-Net for landslide detection in the Himalayas. Nevertheless, U-Net has the potential to improve further automated landslide detection in the future for varied topographical and geomorphological scenes.

In the domain of landslide risk science, landslide susceptibility mapping (LSM) is very important, as it helps spatially identify potential landslide-prone regions. This study used a statistical ensemble model (frequency ratio and evidence belief function) and two machine learning (ML) models (random forest and XGBoost; eXtreme Gradient Boosting) for LSM in the province of Belluno (region of Veneto, northeastern Italy). The study investigated the importance of the conditioning factors in predicting landslide occurrences using the mentioned models. In this paper, we evaluated the importance of the conditioning factors in the overall prediction capabilities of the statistical and ML algorithms. By the trial-and-error method, we eliminated the least “important” features by using a common threshold of 0.30 for statistical and 0.03 for ML algorithms. Conclusively, we found that removing the least important features does not impact the overall accuracy of LSM for all three models. Based on the results of our study, the most commonly available features, for example, the topographic features, contributes to comparable results after removing the least important ones, namely the aspect plan and profile curvature, topographic wetness index (TWI), topographic roughness index (TRI), and normalized difference vegetation index (NDVI) in the case of the statistical model and the plan and profile curvature, TWI, and topographic position index (TPI) for ML algorithms. This confirms that the requirement for the important conditioning factor maps can be assessed based on the physiography of the region.

Land subsidence affects many areas of the world, posing a serious threat to human structures and infrastructures. It can be effectively monitored using ground-based and remote sensing techniques, such as the Global Navigation Satellite System (GNSS) and Interferometric Synthetic Aperture Radar (InSAR). GNSS provides high precision measurements, but in a limited number of points, and is time-consuming, while InSAR allows one to obtain a very large number of measurement points, but only in areas characterized by a high and constant reflectivity of the signal. The aim of this work is to propose an approach to combine the two techniques, overcoming the limits of each of them. The approach was applied in the Po River Delta (PRD), an area located in Northern Italy and historically affected by land subsidence. Ground-based GNSS data from three continuous stations (CGNSS) and 46 non-permanent sites (NPS) measured in 2016, 2018, and 2020, and Sentinel-1 and COSMO-SkyMed SAR data acquired from 2016 to 2020, were considered. In the first phase of the method, InSAR processing was calibrated and verified through CGNSS measurements; subsequently, the calibrated interferometric data were used to validate the GNSS measurements of the NPS. In the second phase, the datasets were integrated to provide an efficient monitoring system, extracting high-resolution deformation maps. The results showed a good agreement between the different sources of data, a high correlation between the displacement rate and the age of the emerged surfaces composed of unconsolidated fine sediments, and high land subsidence rates along the coastal area (up to 16–18 mm/year), where the most recent deposits outcrop. The proposed approach makes it possible to overcome the disadvantages of each technique by providing more complete and detailed information for a better understanding of the ongoing phenomenon.

Land subsidence due to underground resources exploitation is a well-known problem that affects many cities in the world, especially the ones located along the coastal areas where the combined effect of subsidence and sea level rise increases the flooding risk. In this study, 25 years of land subsidence affecting the Municipality of Ravenna (Italy) are monitored using Advanced Differential Interferometric Synthetic Aperture Radar (A-DInSAR) techniques. In particular, the exploitation of the new Sentinel-1A SAR data allowed us to extend the monitoring period till 2016, giving a better understanding of the temporal evolution of the phenomenon in the area. Two statistical approaches are applied to fully exploit the informative potential of the A-DInSAR results in a fast and systematic way. Thanks to the applied analyses, we described the behavior of the subsidence during the monitored period along with the relationship between the occurrence of the displacement and its main driving factors.

Repeated temporal mapping of landslides is essential for investigating changes in landslide movements, legacy effects of the landslide triggering events, and susceptibility changes in the area. However, in order to perform such investigations, multi-temporal (MT) inventories of landslides are required. The traditional approach of visual interpretation from cloud-free optical remote sensing imageries is time consuming and expensive. Recent endeavors exploring Convolutional Neural Networks and deep learning models have made rapid and accurate mapping of landslides feasible but have not been applied for multi-temporal landslide mapping in the Himalayas, yet. Earlier models used a standard supervised learning approach, with a small landslide inventory over a limited area used for training, which is then utilized to predict landslides in nearby areas. We propose a new strategy, using geographically separate training samples to design a standard approach which can be utilized to create multi-temporal landslide inventories. RapidEye images of 5-meters spatial resolution are used to generate MT landslide inventories in the study area of Rasuwa district, Nepal. We test the effectiveness of the model by training with only 55 landslides and predicting for a different area. Then, using the weights attained from this first training phase, we use transfer learning to map landslides over a time period between 2013 and 2019 in the Rasuwa district attaining an average F1-score of 0.69 for the study area. We also perform a spatial comparison between the manual (observed) and predicted inventories to evaluate the differences between landslide densities and overall landslide statistics of landslide area distribution. The benefit of a transfer learning-based model training is that it circumvents the need for generating annual inventories for training a deep learning. A single event-based inventory is enough to generate landslide inventories over a number of years, at least until landslide conditioning factors do not change significantly. This application can enable automated workflows to generate MT landslide inventories of particular areas as the basis for landslide evolution and movement change analysis.