GIScience & Remote Sensing · 2022 · 28 citations · 56 references
ComputingEarth SciencesForestryComputer VisionGeospatial Artificial IntelligenceRemote SensingLand Cover Change DetectionLand Cover ClassificationLand UseLand Use Change DetectionRemote Sensing Image AnalysisRemote Sensing ImageryForest Degradation MappingForest MonitoringHigh-resolution Satellite Image AnalysisLand Use DataMulti-sensor SystemsSatellite Image AnalysisSatellite Image ClassificationSatellite Imagery Analysis
National-scale assessments of post-deforestation land-use are crucial for decreasing deforestation and forest degradation-related emissions. In this research, we assess the potential of different satellite data modalities (single-date, multi-date, multi-resolution, and an ensemble of multi-sensor images) for classifying land-use following deforestation in Ethiopia using the U-Net deep neural network architecture enhanced with attention. We performed the analysis on satellite image data retrieved across Ethiopia from freely available Landsat-8, Sentinel-2 and Planet-NICFI satellite data. The experiments aimed at an analysis of (a) single-date images from individual sensors to account for the differences in spatial resolution between image sensors in detecting land-uses, (b) ensembles of multiple images from different sensors (Planet-NICFI/Sentinel-2/Landsat-8) with different spatial resolutions, (c) the use of multi-date data to account for the contribution of temporal information in detecting land-uses, and, finally, (d) the identification of regional differences in terms of land-use following deforestation in Ethiopia. We hypothesize that choosing the right satellite imagery (sensor) type is crucial for the task. Based on a comprehensive visually interpreted reference dataset of 11 types of post-deforestation land-uses, we find that either detailed spatial patterns (single-date Planet-NICFI) or detailed temporal patterns (multi-date Sentinel-2, Landsat-8) are required for identifying land-use following deforestation, while medium-resolution single-date imagery is not sufficient to achieve high classification accuracy. We also find that adding soft-attention to the standard U-Net improved the classification accuracy, especially for small-scale land-uses. The models and products presented in this work can be used as a powerful data resource for governmental and forest monitoring agencies to design and monitor deforestation mitigation measures and data-driven land-use policy.
56
High-Resolution Global Maps of 21st-Century Forest Cover Change
Matthew C. Hansen, Peter Potapov, Rebecca Moore et al. · Science · 2013 · 11.6K citations
Good practices for estimating area and assessing accuracy of land change
Pontus Olofsson, Giles M. Foody, Martin Herold et al. · Remote Sensing of Environment · 2014 · 2.9K citations · Full text
Attention gated networks: Learning to leverage salient regions in medical images
Jo Schlemper, Ozan Oktay, Michiel Schaap et al. · Medical Image Analysis · 2019 · 1.9K citations · Full text