Aquaculture has a vital function in ecology, environment, and economy. Without adequate monitoring and management, aquaculture might have negative environmental repercussions. In terms of managing and design the industry's long-term operations, it is necessary to map the distribution of aquaculture ponds. Aquaculture ponds can now be detected and mapped using remote sensing. A large-scale mapping can be performed fast due to the recent advancements in cloud computing and big data. In this study, 10 m Sentinel 2 images were used to classify aquaculture in Sungai Udang, Pulau Pinang. This study aims to compare three machine learning classifiers such as Support Vector Machine (SVM), Random Forest (RF) and Classification and Regression Tree (CART) that available in the Google Earth Engine (GEE) cloud computing platform in mapping aquaculture ponds. From 2016 to 2020, the SVM, CART, and RF generated 97.35%, 93.86%, and 93.48% overall accuracy, respectively. In general, SVM was the most accu.....

276 hits