Talk · International Conference on Electronics, Computer and Computation · April 10, 2026
National-Scale Glacier Mass Balance Forecasting in Kyrgyzstan: Machine Learning Insights Into Domain Shift Until 2049
Zhazgul Ablakeeva, Tattybubu Arap kyzy, Timur Turatali, Ruslan Isaev, Andrei Ermakov, Emilbek Zholdoshbekov
Abstract
This study addresses the critical challenge of glacial degradation in the Tien Shan mountain system and its impact on the “water-energy nexus” of Central Asia. By utilizing the XGBoost machine learning algorithm, we provide a comprehensive nationwide forecast for 7,333 individual glaciers across the entire territory of the Kyrgyz Republic for the 2015-2049 period. Our approach employs statistical downscaling and bilinear interpolation to account for local topographical factors, bridging the gap between coarse global climate models (CMIP6) and the specific response of individual glacial units. The integration of highresolution geospatial filtering and seasonal feature engineering allows for a detailed diagnostic of mass balance trends at a national scale, providing a vital tool for regional climate adaptation and water security planning.
More by Ruslan Isaev
- Predicting Facial Soft Tissue Thickness from Skeletal Malocclusion Class and Statistically Engineered Features Using Machine Learning in Cambodian Adults2026
- A Deterministic Redstone Arithmetic Logic Unit in Minecraft: BCD Encoding, Two’s Complement Subtraction, and Seven-Segment VisualizationPreprints.org · 2026
- AgriMap: A Low-Cost Aerial Field-Monitoring Platform for Smallholder Farms Using an Open-Hardware F450 Quadcopter and a Geotagged Web DashboardPreprints.org · 2026
- Quantum Machine Learning for Diabetes Risk Prediction Using Patient Health DataPreprints.org · 2026