MP-MoE: Matrix Profile-Guided Mixture of Experts for Precipitation Forecasting

Read full text Summarise with VIRAT
Authors: Huyen Ngoc Tran, Dung Trung Tran, Hong Nguyen, Ngoc Vu, Xuan-Vu Phan, Nam‐Phong Nguyen
Cited by: 0
References: 24

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Precipitation forecasting remains a persistent challenge in tropical regions like Vietnam, where complex topography and convective instability often limit the accuracy of Numerical Weather Prediction (NWP) models. While data-driven post-processing is widely used to mitigate these biases, most existing frameworks rely on point-wise objective functions, which suffer from the ``double penalty'' effect under minor temporal misalignments. In this work, we propose the Matrix Profile-guided Mixture of Experts (MP-MoE), a framework that integrates conventional intensity loss with a structural-aware Matrix Profile objective. By leveraging subsequence-level similarity rather than point-wise errors, the proposed loss facilitates more reliable expert selection and mitigates excessive penalization caused by phase shifts. We evaluate MP-MoE on rainfall datasets from two major river basins in Vietnam across multiple horizons, including 1-hour intensity and accumulated rainfall over 12, 24, and 48 hours. Experimental results demonstrate that MP-MoE outperforms raw NWP and baseline learning methods in terms of Mean Critical Success Index (CSI-M) for heavy rainfall events, while significantly reducing Dynamic Time Warping (DTW) values. These findings highlight the framework's efficacy in capturing peak rainfall intensities and preserving the morphological integrity of storm events.

Fields of Study & Subjects

Hydrological Forecasting Using AI Meteorological Phenomena and Simulations Precipitation Measurement and Analysis

Publication details

Journal / source
International Conference on Communications and Electronics (ICCE)
Pages
403–408
Publication date
1 July 2026
Language
EN