Landslide risk mitigation is limited by data scarcity; however, this could be improved using continuous landslide detection systems. To investigate which image types and machine learning models are most useful for landslide detection in a Norwegian setting, we compared the performance of five different machine learning models, for the Jølster case study (30 July 2019), in Western Norway. These included three globally pre-trained models; (i) the continuous change detection and classification (CCDC) algorithm, (ii) a combined k-means clustering and random forest classification model, and (iii) a convolutional neural network (CNN), and two locally trained models, including; (iv) classification and regression Trees and (v) a U-net CNN model. Images used included Sentinel-1, Sentinel-2, as well as digital elevation model (DEM) and slope. The globally trained models performed poorly in shadowed areas and were all outperformed by the locally trained models. A maximum Matthew’s correlation coefficient (MCC) score of 89% was achieved with a CNN U-net deep learning model, using combined Sentinel-1 and -2 images as input. This is one of the first attempts to apply deep learning to detect landslides with both Sentinel-1 and -2 images. Using Sentinel-1 images only, the locally-trained deep-learning model significantly outperformed the conventional machine learning model. These findings contribute to developing a national continuous monitoring system for landslides.

Wetlands are important habitats for biodiversity and provide ecosystem services such as climate mitigation and carbon storage. The current wetland mapping techniques in Norway are tedious and costly, and remote sensing provides an opportunity for large-scale mapping and ecosystem accounting. We aimed to implement a deep learning approach to mapping wetlands with Sentinel-2 and LiDAR data over southern Norway. Our U-Net model, implemented through Google Earth Engine and TensorFlow, produced a wetland map with a balanced accuracy rate of 90.9% when validated against an independent ground-truth sample. This represents an improvement upon manually digitized land cover maps in Norway, which achieved accuracy rates of 46.8% (1:50,000 map) and 42.4% (1:5000 map). Using our map, we estimated a total wetland coverage area of 12.7% in southern Norway, which is double the previous benchmark estimates (5.6%). We followed an iterative model training and evaluation approach, which revealed that increasing the quantity and coverage of labeled wetlands greatly increases the model performance. We highlight the potential of satellite-based wetland maps for the ecosystem accounting of changes in wetland extents over time—something that is not feasible with traditional mapping methods.

Cold-water coral reefs are hotspots of biological diversity and play an important role as carbonate factories in the global carbon cycle. Reef-building corals can be found in cold oceanic waters around the world. Detailed knowledge on the spatial location and distribution of coral reefs is of importance for spatial management, conservation and science. Carbonate mounds (reefs) are readily identifiable in high-resolution multibeam echosounder data but systematic mapping programs have relied mostly on visual interpretation and manual digitizing so far. Developing more automated methods will help to reduce the time spent on this laborious task and will additionally lead to more objective and reproducible results. In this paper, we present an attempt at testing whether rule-based classification can replace manual mapping when mapping cold-water coral carbonate mounds. To that end, we have estimated and compared the accuracies of manual mapping, pixel-based terrain analysis and object-based image analysis. To verify the mapping results, we created a reference dataset of presence/absence points agreed upon by three mapping experts. There were no statistically significant differences in the overall accuracies of the maps produced by the three approaches. We conclude that semi-automated rule-based methods might be a viable option for mapping carbonate mounds with high spatial detail over large areas.

Landslide risk mitigation is limited by data scarcity. This could be improved using continuous landslide detection systems. In order to investigate which image types and machine learning (ML) models are most useful for landslide detection in a Norwegian setting, we compared the performance of five different ML models, for the Jølster case study (30-July-2019), in Western Norway. These included three globally pre-trained models; i) the Continuous Change Detection and Classification (CCDC) algorithm, ii) a combined k-means clustering and Random Forest classification model, and iii) a convolutional neural network (CNN), and two locally-trained models, including; iv) Classification and Regression Trees and v) a U-net CNN model. Images used included Sentinel-1, Sentinel-2, digital elevation model (DEM) and slope. The globally-trained models performed poorly in shadowed areas, and were all outperformed by the locally-trained models. A maximum Matthew’s correlation coefficient (MCC) score of 89% was achieved with model v, using combined Sentinel-1 and -2 images as input. This is one of the first attempts to apply deep-learning to detect landslides with both Sentinel-1 and -2 images. Using Sentinel-1 images only, the locally-trained deep-learning model significantly outperformed the conventional ML model. These findings contribute towards developing a national continuous monitoring system for landslides.