Adaptive Rainfall Forecasting from Multiple Geographical Models Using Matrix Profile and Ensemble Learning

2025-09-10

AI Summary

Rainfall forecasting in Vietnam is hindered by complex topography and climatic heterogeneity, resulting in insufficient cross-basin generalizability, multi-scale accuracy, and prediction stability—limiting flood control and hydropower scheduling. To address this, we propose a dynamic weighted ensemble framework grounded in the Matrix Profile: the first application of Matrix Profile to detect covariant patterns and regime-switching behavior in multi-model forecast sequences, integrated with a redundancy-aware weight allocation mechanism for adaptive fusion of geospatial model outputs. Evaluated across eight major Vietnamese river basins and five forecast horizons (1–7 days), our method achieves significant improvements: average RMSE reduction of 18.3% and average prediction standard deviation reduction of 22.7%, outperforming both individual models and conventional ensemble approaches in both accuracy and robustness.

Technology Category

• Machine Learning: Ensemble Methods
• Intelligent Robots: State Estimation
• Reasoning under Uncertainty: Relational Probabilistic Models

Application Category

• Graph Algorithms and Modeling for the Web: Efficient manipulation of static and dynamic Web-related graphs
• Web Mining and Content Analysis: Models for Web evolution
• Systems and Infrastructure for Web, Mobile and WoT: Virtualization and resource management in Web systems and infrastructures

Abstract

Rainfall forecasting in Vietnam is highly challenging due to its diverse climatic conditions and strong geographical variability across river basins, yet accurate and reliable forecasts are vital for flood management, hydropower operation, and disaster preparedness. In this work, we propose a Matrix Profile-based Weighted Ensemble (MPWE), a regime-switching framework that dynamically captures covariant dependencies among multiple geographical model forecasts while incorporating redundancy-aware weighting to balance contributions across models. We evaluate MPWE using rainfall forecasts from eight major basins in Vietnam, spanning five forecast horizons (1 hour and accumulated rainfall over 12, 24, 48, 72, and 84 hours). Experimental results show that MPWE consistently achieves lower mean and standard deviation of prediction errors compared to geographical models and ensemble baselines, demonstrating both improved accuracy and stability across basins and horizons.

Problem

• Adaptive rainfall forecasting for diverse Vietnamese climatic conditions
• Dynamic integration of multiple geographical model forecasts
• Improving prediction accuracy and stability across basins

Innovation

• Matrix Profile-based Weighted Ensemble framework
• Dynamic covariant dependency capture across models
• Redundancy-aware weighting for balanced contributions