Mapping cashew monocultures in the Western Ghats using optical and radar imagery in Google Earth Engine

Tropical deforestation is increasingly driven by the expansion of agricultural commodity production. Mapping crops an important step towards monitoring commodity-driven deforestation. Advances in remote sensing technology, such as availability high-resolution imagery and combination optical radar have enabled detection tree-like which are difficult to distinguish from forest cover. Cashew example a crop that grows areas with high cover biodiversity. reported occupy ∼7.1 million ha globally yet mapping it has been constrained unclear boundaries due spatial mixing forests, indistinct spectral signature, structural composition resembles forests. We employed optical, radar, two types detect map cashew monocultures south Maharashtra, India for 2020. performed land classification on Google Earth Engine using Random Forest, Classification And Regression Trees Support Vector Machine algorithms. The Sentinel-2 Sentinel-1 SAR Forest algorithm yielded highest unbiased overall accuracy (83%) producer's user's accuracies 71% 86% respectively was considered best approach. According our approach, monoculture plantations 53,350.37 total area Sawantwadi- Dodamarg landscape India. This study shows can be used Western Ghats, future studies could modify these methods other landscapes. contributes growing body literature supporting use both detecting