CLASSIFYING AND MAPPING GROUNDWATER LEVEL VARIATIONS USING MACHINE LEARNING MODELS

Abstract

Estimation of groundwater level variation is important for establishing a sustainable development plan of groundwater resources. Therefore, it is necessary to develop a method for accurate estimation of groundwater level variation. In this study we developed the machine learning model for estimating groundwater level variation and applied it to Chungcheong Province in South Korea using geological and hydrological factors. We clustered 58 groundwater observation wells using eight geological factors and K-means algorithm. Groundwater level variations were classified using machine learning models (random forest and support vector machine) based on geological and hydrological factors. In addition, groundwater level variation class maps were created using the result of the machine learning models and compared with in situ groundwater observation. The groundwater level variation map can be a useful tool for efficient groundwater management.