Spatial and temporal deep learning methods for deriving land-use following deforestation: A pan-tropical case study using Landsat time series
| Autor: | Martin Herold, Robert N. Masolele, Jan Verbesselt, Christopher Martius, Veronique De Sy, Diego Marcos, Adugna G. Mullissa, Fabian Gieseke |
|---|---|
| Jazyk: | angličtina |
| Rok vydání: | 2021 |
| Předmět: |
Soil Science
Land-use following deforestation Laboratory of Geo-information Science and Remote Sensing Deforestation Reducing emissions from deforestation and forest degradation Laboratorium voor Geo-informatiekunde en Remote Sensing Computers in Earth Sciences Remote sensing Land use Deep learning methods business.industry Continental models Deep learning Landsat imagery Geology PE&RC Geography Large-scale land-use classification Satellite imagery time series Pan-tropical model Scalability Spatial ecology Satellite Spatio-temporal Artificial intelligence business Scale (map) Cartography |
| Zdroj: | Remote Sensing of Environment, 264 Remote Sensing of Environment Remote Sensing of Environment 264 (2021) |
| ISSN: | 0034-4257 |
| Popis: | Assessing land-use following deforestation is vital for reducing emissions from deforestation and forest degradation. In this paper, for the first time, we assess the potential of spatial, temporal and spatio-temporal deep learning methods for large-scale classification of land-use following tropical deforestation using dense satellite time series over six years on the pan-tropical scale (incl. Latin America, Africa, and Asia). Based on an extensive reference database of six forest to land-use conversion types, we find that the spatio-temporal models achieved a substantially higher F1-score accuracies than models that account only for spatial or temporal patterns. Although all models performed better when the scope of the problem was limited to a single continent, the spatial models were more competitive than the temporal ones in this setting. These results suggest that the spatial patterns of land-use within a continent share more commonalities than the temporal patterns and the spatial patterns across continents. This work explores the feasibility of extending and complementing previous efforts for characterizing follow-up land-use after deforestation at a small-scale via human visual interpretation of high resolution RGB imagery. It supports the usage of fast and automated large-scale land-use classification and showcases the value of deep learning methods combined with spatio-temporal satellite data to effectively address the complex tasks of identifying land-use following deforestation in a scalable and cost effective manner. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full Text from ScienceDirect