<![CDATA[Introduction/Main Objectives: This study aims to develop a 1 km × 1 km level estimation model of safe drinking water access using multisource satellite imagery, point of interest (POI), and aquifer productivity maps. Background Problems: There is a lack of alternative data sources for estimating safe drinking water access that are cost-, time-, and labor-efficient while maintaining high accuracy and frequent updates. Novelty: This study integrates Multi-Criteria Decision Analysis (MCDA) and machine learning methods to estimate and map safe drinking water access at a 1 km × 1 km resolution. Research Methods: Multisource geospatial data were used to construct the model. Within the MCDA approach, the Weighted Product Model (WPM) was employed to develop the Safe Drinking Water Access Index (SDWAI). Meanwhile, the machine learning regression algorithms Adaptive Boosting Regression (ABR) and Gradient Boosting Regression (GBR) were applied to estimate safe drinking water access at a fine spatial scale. The study was conducted in Bengkulu Province, Indonesia. Finding/Results: WPM yielded the best MCDA performance ( = 0.3699, RMSE = 10.6566, MAE = 9.5427, MAPE = 0.1405), while ABR showed the best machine learning performance ( = 0.4361, RMSE = 10.0813, MAE = 8.3750, MAPE = 0.1333).]]>
Copyrights © 2025
