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

Abstract

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