Simulating and predicting lake dynamics by fusing HBV modeling, machine learning approach and remote sensing data

This study provides a comprehensive analysis of the hydrological dynamics and land use changes in the Hongjiannao Lake Basin from 1990 to 2023, with projections extending to 2060. By integrating advanced hydrological modeling Hydrologiska Byrans Vattenbalansavdelning (HBV), a machine learning algorithm Random Forest (RF), Cellular Automata (CA) Markov, and remote sensing data, this research offers a robust framework for understanding the interactions between climate change, anthropogenic activities, and ecosystem responses. The historical analysis revealed remarkable fluctuations in the lake’s area, including a 25.5 % reduction between 2000 and 2011, followed by a recovery from 2012 to 2023. The lake area increased by 26.2 % during the recovery phase, highlighting a partial reversal of decline. Projections indicate that, under various future climate scenarios, the lake area could increase by 29 % by 2060, showcasing the resilience of the ecosystem despite ongoing climate and anthropogenic pressures. The RF model demonstrated strong predictive capabilities, with R² values of 0.92 during 1990–2013 calibration and 0.76 during 2014–2023 validation, coupled with root mean square errors of 0.12 km² and 0.26 km², respectively. Additionally, the CA-Markov model predicted vegetation growth and urbanization, highlighting potential for significant landscape changes. These findings stress the need for water management strategies to preserve the lake’s ecological health, advocating for the integration of climate, land use, and hydrological factors in management plans for sustainable conservation and restoration in semi-arid regions.