Integrated scheduling-assessing system for drought mitigation in the river-connected lake.

Area of Science:

• Hydrology
• Environmental Science
• Water Resource Management

Background:

• Lakes are vital inland water resources impacted by climate change and human activities, leading to global water depletion.
• Droughts in lakes connected to regulated rivers pose significant ecological and societal challenges.

Purpose of the Study:

• To develop and apply an integrated scheduling-assessing system (ISAS) for mitigating lake droughts in river-lake systems.
• To evaluate the effectiveness of ISAS in improving drought conditions for Poyang Lake using machine learning.

Main Methods:

• Developed an integrated scheduling-assessing system (ISAS) employing machine learning methodologies.
• Calibrated the ISAS model using observational data for a large river-lake system.
• Applied the ISAS to optimize reservoir operations for mitigating Poyang Lake drought in the middle Yangtze River.

Main Results:

• Optimal reservoir operation via ISAS can improve downstream lake drought situations.
• For Poyang Lake, ISAS delayed drought onset by 12-17 days and reduced drought duration by 19-21 days across different year types.
• While the lowest lake level was not significantly improved, the timing and duration of drought were positively impacted.

Conclusions:

• Accelerating reservoir filling and decelerating emptying speeds are effective strategies for alleviating drought in downstream river-connected lakes.
• The ISAS provides a viable tool for proactive management of lake droughts through optimized reservoir control.
• Machine learning-based approaches offer promising solutions for addressing water resource challenges in river-lake ecosystems.