Hurdle-IMDL: An Imbalanced Learning Framework for Infrared Rainfall Retrieval

TL;DR

Hurdle-IMDL is a novel framework that effectively addresses data imbalance in infrared rainfall retrieval, significantly improving the accuracy for heavy rain detection by decomposing the problem into zero inflation and long tail components.

Contribution

It introduces a divide-and-conquer approach using a hurdle model and IMDL to mitigate imbalance effects, enhancing retrieval performance for rare, high-impact rainfall events.

Findings

Outperforms conventional methods in rainfall retrieval accuracy.

Significantly improves heavy rain detection and underestimation mitigation.

Demonstrates generalizability to other environmental variable imbalances.

Abstract

Artificial intelligence has advanced quantitative remote sensing, yet its effectiveness is constrained by imbalanced label distribution. This imbalance leads conventionally trained models to favor common samples, which in turn degrades retrieval performance for rare ones. Rainfall retrieval exemplifies this issue, with performance particularly compromised for heavy rain. This study proposes Hurdle-Inversion Model Debiasing Learning (IMDL) framework. Following a divide-and-conquer strategy, imbalance in the rain distribution is decomposed into two components: zero inflation, defined by the predominance of non-rain samples; and long tail, defined by the disproportionate abundance of light-rain samples relative to heavy-rain samples. A hurdle model is adopted to handle the zero inflation, while IMDL is proposed to address the long tail by transforming the learning object into an unbiased ideal inverse model. Comprehensive evaluation via statistical metrics and case studies investigating rainy weather in eastern China confirms Hurdle-IMDL's superiority over conventional, cost-sensitive, generative, and multi-task learning methods. Its key advancements include effective mitigation of systematic underestimation and a marked improvement in the retrieval of heavy-to-extreme rain. IMDL offers a generalizable approach for addressing imbalance in distributions of environmental variables, enabling enhanced retrieval of rare yet high-impact events.