Comparison of Three Water Indices for Tropical Aquaculture Ponds Extraction using Google Earth Engine

Information on the spatial distribution of aquaculture ponds, especially inland brackish aquaculture, is crucial for effective and sustainable management. Google Earth Engine (GEE) has been utilized to quickly map ponds in different parts world, but application still limited tropical regions. Selection an optimal water index essential accurately from Landsat 8 satellite images that are available GEE. This study aims evaluate capability three indices, namely Normalized Difference Water Index (NDWI), Modified (MNDWI) Automated Extraction (AWEI), mapping Sungai Udang, Pulau Pinang, Malaysia. The results show MNDWI best extraction with accuracy 81.87% Kappa coefficient 0.61. Meanwhile, NDWI AWEI as compared digitized 58.21 61.60%, 0.33 0.36, respectively. Then, was applied calculate changes 2014 2020. result indicates area expanded by 26.16% since past seven years.