Identifying Soil Erosion Processes in Alpine Grasslands on Aerial Imagery with a U-Net Convolutional Neural Network
Open Access
- 18 December 2020
- journal article
- research article
- Published by MDPI AG in Remote Sensing
- Vol. 12 (24) , 4149
Abstract
Erosion in alpine grasslands is a major threat to ecosystem services of alpine soils. Natural causes for the occurrence of soil erosion are steep topography and prevailing climate conditions in combination with soil fragility. To increase our understanding of ongoing erosion processes and support sustainable land-use management, there is a need to acquire detailed information on spatial occurrence and temporal trends. Existing approaches to identify these trends are typically laborious, have lack of transferability to other regions, and are consequently only applicable to smaller regions. In order to overcome these limitations and create a sophisticated erosion monitoring tool capable of large-scale analysis, we developed a model based on U-Net, a fully convolutional neural network, to map different erosion processes on high-resolution aerial images (RGB, 0.25–0.5 m). U-Net was trained on a high-quality data set consisting of labeled erosion sites mapped with object-based image analysis (OBIA) for the Urseren Valley (Central Swiss Alps) for five aerial images (16 year period). We used the U-Net model to map the same study area and conduct quality assessments based on a held-out test region and a temporal transferability test on new images. Erosion classes are assigned according to their type (shallow landslide and sites with reduced vegetation affected by sheet erosion) or land-use impacts (livestock trails and larger management affected areas). We show that results obtained by OBIA and U-Net follow similar linear trends for the 16 year study period, exhibiting increases in total degraded area of 167% and 201%, respectively. Segmentations of eroded sites are generally in good agreement, but also display method-specific differences, which lead to an overall precision of 73%, a recall of 84%, and a F-score of 78%. Our results show that U-Net is transferable to spatially (within our study area) and temporally unseen data (data from new years) and is therefore a method suitable to efficiently and successfully capture the temporal trends and spatial heterogeneity of degradation in alpine grasslands. Additionally, U-Net is a powerful and robust tool to map erosion sites in a predictive manner utilising large amounts of new aerial imagery.
Keywords
Funding Information
- Schweizerischer Nationalfonds zur Förderung der Wissenschaftlichen Forschung (407540_167333)
This publication has 58 references indexed in Scilit:
- Automated Extraction of Shallow Erosion Areas Based on Multi-Temporal Ortho-ImageryRemote Sensing, 2013
- Unmanned Aerial Vehicle (UAV) for Monitoring Soil Erosion in MoroccoRemote Sensing, 2012
- Spatial and temporal variability of rainfall erosivity factor for SwitzerlandHydrology and Earth System Sciences, 2012
- Object-oriented analysis of multi-temporal panchromatic images for creation of historical landslide inventoriesISPRS Journal of Photogrammetry and Remote Sensing, 2012
- Object-based gully feature extraction using high spatial resolution imageryGeomorphology, 2011
- Estimating vegetation parameter for soil erosion assessment in an alpine catchment by means of QuickBird imageryInternational Journal of Applied Earth Observation and Geoinformation, 2010
- Process identification of soil erosion in steep mountain regionsHydrology and Earth System Sciences, 2010
- Methods to describe and predict soil erosion in mountain regionsLandscape and Urban Planning, 2008
- Impacts of anthropogenic and environmental factors on the occurrence of shallow landslides in an alpine catchment (Urseren Valley, Switzerland)Natural Hazards and Earth System Sciences, 2008
- Effects of land use in alpine grasslands on the probability of landslidesBasic and Applied Ecology, 2003