From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Gao, Wentao, Li, Jiuyong, Liu, Lin, Le, Thuc Duy, Chen, Xiongren, Du, Xiaojing, Liu, Jixue, Zhao, Yanchang, Chen, Yun
Format: Preprint
Published: 2025
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866915493368037376
author Gao, Wentao
Li, Jiuyong
Liu, Lin
Le, Thuc Duy
Chen, Xiongren
Du, Xiaojing
Liu, Jixue
Zhao, Yanchang
Chen, Yun
author_facet Gao, Wentao
Li, Jiuyong
Liu, Lin
Le, Thuc Duy
Chen, Xiongren
Du, Xiaojing
Liu, Jixue
Zhao, Yanchang
Chen, Yun
contents Zero-inflated data pose significant challenges in precipitation forecasting due to the predominance of zeros with sparse non-zero events. To address this, we propose the Zero Inflation Diffusion Framework (ZIDF), which integrates Gaussian perturbation for smoothing zero-inflated distributions, Transformer-based prediction for capturing temporal patterns, and diffusion-based denoising to restore the original data structure. In our experiments, we use observational precipitation data collected from South Australia along with synthetically generated zero-inflated data. Results show that ZIDF demonstrates significant performance improvements over multiple state-of-the-art precipitation forecasting models, achieving up to 56.7\% reduction in MSE and 21.1\% reduction in MAE relative to the baseline Non-stationary Transformer. These findings highlight ZIDF's ability to robustly handle sparse time series data and suggest its potential generalizability to other domains where zero inflation is a key challenge.
format Preprint
id arxiv_https___arxiv_org_abs_2509_10501
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction
Gao, Wentao
Li, Jiuyong
Liu, Lin
Le, Thuc Duy
Chen, Xiongren
Du, Xiaojing
Liu, Jixue
Zhao, Yanchang
Chen, Yun
Machine Learning
Artificial Intelligence
Zero-inflated data pose significant challenges in precipitation forecasting due to the predominance of zeros with sparse non-zero events. To address this, we propose the Zero Inflation Diffusion Framework (ZIDF), which integrates Gaussian perturbation for smoothing zero-inflated distributions, Transformer-based prediction for capturing temporal patterns, and diffusion-based denoising to restore the original data structure. In our experiments, we use observational precipitation data collected from South Australia along with synthetically generated zero-inflated data. Results show that ZIDF demonstrates significant performance improvements over multiple state-of-the-art precipitation forecasting models, achieving up to 56.7\% reduction in MSE and 21.1\% reduction in MAE relative to the baseline Non-stationary Transformer. These findings highlight ZIDF's ability to robustly handle sparse time series data and suggest its potential generalizability to other domains where zero inflation is a key challenge.
title From Noise to Precision: A Diffusion-Driven Approach to Zero-Inflated Precipitation Prediction
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2509.10501