Work

Unveiling climate-driven water surface dynamics in the largest tropical lake in Borneo: A machine learning approach using multi-source satellite imagery

Year: 2025

Type: article

Abstract: Lake Sentarum is an exotic area with fantastic biodiversity. As the largest lake in Borneo Island, this lake has abundant water resource potential. However, seasonal changes also affect the condition of the water area. In the dry season, sedimentation will fill the Sentarum area, changing it from a water-filled area to an empty plain. This task is incredibly challenging during the dry season, when water scarcity significantly threatens human life. This study explores the dynamics and potential of water resources in Lake Sentarum, Borneo, using a machine learning model, namely Gradient Tree Boosting (GTB). Using satellite imagery from Sentinel-1, Sentinel-2, and NICFI, we analyze changes in area size and classification between water and non-water areas. The results show significant classification accuracy, ranging from 80% to 97%, highlighting the potential application of this model in water resource management and environmental monitoring. These findings not only provide new insights into the ecosystem of Lake Sentarum but also offer an innovative approach to research in the field of geoscience.

Source: Artificial Intelligence in Geosciences

DOI: 10.1016/j.aiig.2025.100166

Authors: Mohamad Rifai, Harintaka

Institutions: Universitas Gadjah Mada, Ministry of Public Works, Republic of Indonesia

Language: English

Topic: Remote-Sensing Image Classification

Subfield: Media Technology

Field: Engineering

Domain: Physical Sciences

SDGs: Clean water and sanitation, Climate action, Life on land

Open Access status: gold

Estimated APC paid: $700