PreprintArticleVersion 2Preserved in Portico This version is not peer-reviewed
Genus-Physiognomy-Ecosystem Map with Solar Panels Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images
Version 1
: Received: 10 January 2022 / Approved: 10 January 2022 / Online: 10 January 2022 (15:02:47 CET)
Version 2
: Received: 1 April 2022 / Approved: 4 April 2022 / Online: 4 April 2022 (10:40:26 CEST)
How to cite:
Sharma, R.C. Genus-Physiognomy-Ecosystem Map with Solar Panels Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images. Preprints2022, 2022010123 (doi: 10.20944/preprints202201.0123.v2).
Sharma, R.C. Genus-Physiognomy-Ecosystem Map with Solar Panels Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images. Preprints 2022, 2022010123 (doi: 10.20944/preprints202201.0123.v2).
Cite as:
Sharma, R.C. Genus-Physiognomy-Ecosystem Map with Solar Panels Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images. Preprints2022, 2022010123 (doi: 10.20944/preprints202201.0123.v2).
Sharma, R.C. Genus-Physiognomy-Ecosystem Map with Solar Panels Produced at 10m-resolution First-time in a Country Scale through Machine Learning of Multi-temporal Satellite Images. Preprints 2022, 2022010123 (doi: 10.20944/preprints202201.0123.v2).
Abstract
This research introduces Genus-Physiognomy-Ecosystem (GPE) mapping at a prefecture level through machine learning of multi-spectral and multi-temporal satellite images at 10m spatial resolution, and later integration of prefecture wise maps into country scale for dealing with 88 GPE types to be classified from a large size of training data involved in the research effectively. This research was made possible by harnessing entire archives of Level-2A product, Bottom of Atmosphere reflectance images collected by MultiSpectral Instruments onboard a constellation of two polar-orbiting Sentinel-2 mission satellites. The satellite images were pre-processed for cloud masking and monthly median composite images consisting of 10 multi-spectral bands and 7 spectral indexes were generated. The ground truth labels were extracted from extant vegetation survey maps by implementing systematic stratified sampling approach and noisy labels were dropped out for preparing a reliable ground truth database. Graphics Processing Unit (GPU) implementation of Gradient Boosting Decision Trees (GBDT) classifier was employed for classification of 88 GPE types from 204 satellite features. The classification accuracy computed with 25% test data varied from 65-81% in terms of F1-score across 48 prefectural regions. This research produced seamless maps of 88 GPE types first time at a country scale with an average 72% F1-score. In addition, mapping of solar panels and vegetation disturbance are added.
Keywords
Sentinel-2; Land cover; Vegetation; Mapping; Plant communities; Machine learning; Genus-Physiognomy-Ecosystem; Gradient Boosting Decision Trees; Solar panel; Vegetation disturbance
Subject
EARTH SCIENCES, Geoinformatics
Copyright:
This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.
