Forecasting Tibetan Plateau Lake Level Responses to Climate Change: An Explainable Deep Learning Approach Using Altimetry and Climate Models

The Tibetan Plateau's lakes, serving as critical water towers for over two billion people, exhibit divergent responses to climate change that remain poorly quantified. This study develops a deep learning framework integrating Synthetic Aperture Radar (SAR) altimetry from Sentinel-3A with bias-corrected CMIP6 (Coupled Model Intercomparison Project Phase 6) climate projections under Shared Socioeconomic Pathways (SSP) scenarios (SSP2-4.5 and SSP5-8.5, adjusted via quantile mapping) to predict lake-level changes across eight Tibetan Plateau (TP) lakes. Using a Feed-Forward Neural Network (FFNN) optimized via Bayesian optimization using the Optuna framework, we achieve robust water level projections (mean validation R² = 0.861) and attribute drivers through SHapley Additive exPlanations (SHAP) analysis. Results reveal a stark north-south divergence: glacier-fed northern lakes like Migriggyangzham will rise by +13.27 m under SSP5-8.5 due to meltwater inputs (temperature SHAP value = 0.41), consistent with the early (melt-dominated) phase of the IPCC’s ‘peak water’ framework. In comparison, evaporation-dominated southern lakes such as Langacuo face irreversible desiccation (−5.03 m by 2100) as evaporative demand surpasses precipitation gains. Transitional western lakes exhibit "peak water" inflection points (e.g., Lumajang Dong's 2060 maximum) signaling cryospheric buffer loss. These projections, validated through rigorous quantile mapping and rolling-window cross-validation, provide the first process-aware assessment of TP Lake vulnerabilities, informing adaptation strategies under the Sustainable Development Goals (SDGs) for water security (SDG 6) and climate action (SDG 13). The methodological framework establishes a transferable paradigm for monitoring high-altitude freshwater systems globally.