For evaluating the progresses towards achieving the Sustainable Development Goals(SDGs),a global indicator framework was developed by the UN Inter-Agency and Expert Group on Sustainable Development Goals Indicators.In...For evaluating the progresses towards achieving the Sustainable Development Goals(SDGs),a global indicator framework was developed by the UN Inter-Agency and Expert Group on Sustainable Development Goals Indicators.In this paper,we propose an improved methodology and a set of workflows for calculating SDGs indicators.The main improvements consist of using moderate and high spatial resolution satellite data and state-of-the-art deep learning methodology for land cover classification and for assessing land productivity.Within the European Network for Observing our Changing Planet(ERA-PLANET),three SDGs indicators are calculated.In this research,harmonized Landsat and Sentinel-2 data are analyzed and used for land productivity analysis and yield assessment,as well as Landsat 8,Sentinel-2 and Sentinel-1 time series are utilized for crop mapping.We calculate for the whole territory of Ukraine SDG indicators:15.1.1–‘Forest area as proportion of total land area’;15.3.1–‘Proportion of land that is degraded over total land area’;and 2.4.1–‘Proportion of agricultural area under productive and sustainable agriculture’.Workflows for calculating these indicators were implemented in a Virtual Laboratory Platform.We conclude that newly available high-resolution remote sensing products can significantly improve our capacity to assess several SDGs indicators through dedicated workflows.展开更多
基金This work was supported by the European Commission‘Horizon 2020 Program’that funded ERA-PLANET/GEOEs-sential,ERA-PLANET/SMURBS(Grant Agreement no.689443)NASA project‘Crop Yield Assessment and Mapping by a Combined use of Landsat-8,Sentinel-2 and Sentinel-1 Images’(grant number 80NSSC18K0336)‘Intelligent technologies for satellite monitoring of environment based on deep learning and cloud computing’InTeLLeCT(STCU project no.6386).
文摘For evaluating the progresses towards achieving the Sustainable Development Goals(SDGs),a global indicator framework was developed by the UN Inter-Agency and Expert Group on Sustainable Development Goals Indicators.In this paper,we propose an improved methodology and a set of workflows for calculating SDGs indicators.The main improvements consist of using moderate and high spatial resolution satellite data and state-of-the-art deep learning methodology for land cover classification and for assessing land productivity.Within the European Network for Observing our Changing Planet(ERA-PLANET),three SDGs indicators are calculated.In this research,harmonized Landsat and Sentinel-2 data are analyzed and used for land productivity analysis and yield assessment,as well as Landsat 8,Sentinel-2 and Sentinel-1 time series are utilized for crop mapping.We calculate for the whole territory of Ukraine SDG indicators:15.1.1–‘Forest area as proportion of total land area’;15.3.1–‘Proportion of land that is degraded over total land area’;and 2.4.1–‘Proportion of agricultural area under productive and sustainable agriculture’.Workflows for calculating these indicators were implemented in a Virtual Laboratory Platform.We conclude that newly available high-resolution remote sensing products can significantly improve our capacity to assess several SDGs indicators through dedicated workflows.
