Mapping landslides using automated methods is a challenging task, which is still largely done using human efforts. Today, the availability of high-resolution EO data products is increasing exponentially, and one of the targets is to exploit this data source for the rapid generation of landslide inventory. Conventional methods like pixel-based and object-based machine learning strategies have been studied extensively in the last decade. In addition, recent advances in CNN (convolutional neural network), a type of deep-learning method, has been widely successful in extracting information from images and have outperformed other conventional learning methods. In the last few years, there have been only a few attempts to adapt CNN for landslide mapping. In this study, we introduce a modified U-Net model for semantic segmentation of landslides at a regional scale from EO data using ResNet34 blocks for feature extraction. We also compare this with conventional pixel-based and object-based methods. The experiment was done in Douglas County, a study area selected in the south of Portland in Oregon, USA, and landslide inventory extracted from SLIDO (Statewide Landslide Information Database of Oregon) was considered as the ground truth. Landslide mapping is an imbalanced learning problem with very limited availability of training data. Our network was trained on a combination of focal Tversky loss and cross-entropy loss functions using augmented image tiles sampled from a selected training area. The deep-learning method was observed to have a better performance than the conventional methods with an MCC (Matthews correlation coefficient) score of $0.495$ and a POD (probability of detection) rate of $0.72$ .

In this contribution, we present a review of scientific research results that address seismo-hydromechanically coupled processes relevant for the development of a sustainable heat exchanger in low-permeability crystalline rock and introduce the design of the In situ Stimulation and Circulation (ISC) experiment at the Grimsel Test Site dedicated to studying such processes under controlled conditions. The review shows that research on reservoir stimulation for deep geothermal energy exploitation has been largely based on laboratory observations, large-scale projects and numerical models. Observations of full-scale reservoir stimulations have yielded important results. However, the limited access to the reservoir and limitations in the control on the experimental conditions during deep reservoir stimulations is insufficient to resolve the details of the hydromechanical processes that would enhance process understanding in a way that aids future stimulation design. Small-scale laboratory experiments provide fundamental insights into various processes relevant for enhanced geothermal energy, but suffer from (1) difficulties and uncertainties in upscaling the results to the field scale and (2) relatively homogeneous material and stress conditions that lead to an oversimplistic fracture flow and/or hydraulic fracture propagation behavior that is not representative of a heterogeneous reservoir. Thus, there is a need for intermediate-scale hydraulic stimulation experiments with high experimental control that bridge the various scales and for which access to the target rock mass with a comprehensive monitoring system is possible. The ISC experiment is designed to address open research questions in a naturally fractured and faulted crystalline rock mass at the Grimsel Test Site (Switzerland). Two hydraulic injection phases were executed to enhance the permeability of the rock mass. During the injection phases the rock mass deformation across fractures and within intact rock, the pore pressure distribution and propagation, and the microseismic response were monitored at a high spatial and temporal resolution.

Rapid mapping of event landslides is crucial to identify the areas affected by damages as well as for effective disaster response. Traditionally, such maps are generated with visual interpretation of remote sensing imagery (manned/unmanned airborne systems or spaceborne sensors) and/or using pixel-based and object-based methods exploiting data-intensive machine learning algorithms. Recent works have explored the use of convolutional neural networks (CNN), a deep learning algorithm, for mapping landslides from remote sensing data. These methods follow a standard supervised learning workflow that involves training a model using a landslide inventory covering a relatively small area. The trained model is then used to predict landslides in the surrounding regions. Here, we propose a new strategy, i.e., a progressive CNN training relying on combined inventories to build a generalized model that can be applied directly to a new, unexplored area. We first prove the effectiveness of CNNs by training and validating on event landslides inventories in four regions after earthquakes and/or extreme meteorological events. Next, we use the trained CNNs to map landslides triggered by new events spread across different geographic regions. We found that CNNs trained on a combination of inventories have a better generalization performance, with a bias towards high precision and low recall scores. In our tests, the combined training model achieved the highest (Matthews correlation coefficient) MCC score of 0.69 when mapping landslides in new unseen regions. The mapping was done on images from different optical sensors, resampled to a spatial resolution of 6 m, 10 m, and 30 m. Despite a slightly reduced performance, the main advantage of combined training is to overcome the requirement of a local inventory for training a new deep learning model. This implementation can facilitate automated pipelines providing fast response for the generation of landslide maps in the post-disaster phase. In this study, the study areas were selected from seismically active zones with a high hydrological hazard distribution and vegetation coverage. Hence, future works should also include regions from less vegetated geographic locations.

A comprehensive worldwide permeability data set has been compiled consisting of 29,000 in situ permeabilities from 221 publications and reports and delineating the permeability distribution in crystalline rocks into depths of 2000 meters below ground surface (mbgs). We analyze the influence of technical factors (measurement method, scale effects, preferential sampling, and hydraulic anisotropy) and geological factors (lithology, current stress regime, current seismotectonic activity, and long‐term tectonogeological history) on the permeability distribution with depth, by using regression analysis and k‐means clustering. The influence of preferential sampling and hydraulic anisotropy are negligible. A scale dependency is observed based on calculated rock test volumes equaling 0.6 orders of magnitude of permeability change per order of magnitude of rock volume tested. Based on the entire data set, permeability decreases as log(k) = −1.5 × log(z) − 16.3 with permeability k (m²) and positively increasing depth z (km), and depth is the main factor driving the permeability distribution. The permeability variance is about 2 orders of magnitude at all depths, presumably representing permeability variations around brittle fault zones. Permeability and specific yield/storage exhibit similar depth trends. While in the upper 200 mbgs fracture flow varies between confined and unconfined, we observe confined fracture and matrix flow below about 600 mbgs depth. The most important geological factors are current seismotectonic activity (determined by peak ground acceleration) and long‐term tectonogeological history (determined by geological province). The impact of lithology is less important. Based on the regression coefficients derived for all the geological key factors, permeability ranges of crystalline rocks at site scale can be predicted. First tests with independent data sets are promising.