ARTIFICIAL NEURAL NETWORKS FOR THE CLASSIFICATION OF SHRIMP FARM FROM SATELLITE IMAGERY

: Shrimp production was the high demand for the popular in the global market in Thailand. The change of land use is important for the management and monitoring of land use changed. The objectives of this paper to (1) classification of shrimp farm using artificial neural networks (ANN) technique from the Sentinel-2 imagery. (2) change detection of land use changes map among 2015, 2018, and 2020. The land use classification based on ANN technique and the accuracy assessment by used the confusion matrices and kappa coefficient. The classify of land use classes divide into built-up, forest, water bodies, paddy field, shrimp farm, and field crop. The change detection methods used was the image differencing technique was performed to the land use changes map. The result of land use classification show that the field crop area was 80% cover the most area. The result of land use changed show that built-up, paddy field, and shrimp farm increased throughout between year 2015 to 2020. The shrimp farm between year 2015 to 2020 to increasing trend of related with the shrimp production was the high demand for the popular in the global market. layer. The several ANN models have been applied in land use classification such as Hopfield network, self-organizing competition, radial basis function, multilayer perception,