Using Artificial Neural Networks and Spectral Indices to Predict Water Availability in New Capital (IKN) and Its’ Surroundings

Abstract

This study aims to predict water availability in New Capital (IKN) and its surroundings using artificial neural networks and spectral indices as predictors. The study uses Sentinel-2 A imagery from the year 2022 analyzed directly from Google Earth Engine (GEE) to calculate three spectral indices, including the Land Surface Water Index (LSWI), Normalized Difference Vegetation Index (NDVI), and Normalized Difference Water Index (NDWI), and uses these indices as predictors in the artificial neural network model. The study carried out four simulations to determine the best prediction results, and the best results were obtained using ANN parameters: 2 hidden layers (HL); learning rate (LR) 0.01; momentum (M) 0.4; root mean square (RMS) 0.001 and iteration (I) 25,000 with overall accuracy (OA) 97.7% and kappa index 0.96. The results show that the percentage of water availability in the study area is high water/HW (0.51%), vegetation water/VW (20.41%), and non-water/NW (79.08%). The study concludes that artificial neural networks and spectral indices can effectively predict water availability.