← Back to all news
arXiv Machine Learning

Hurdle-RMIL: Addressing Zero Inflation and Long-Tailed Imbalance in Infrared Rainfall Retrieval

The paper introduces Hurdle‑RMIL, a two‑stage model that first separates zero‑inflated rainfall from the long‑tailed distribution of positive rainfall and then applies a Bayes‑based transformation to learn a balanced‑distribution model from natural data. Experiments over multiple Chinese regions show that Hurdle‑RMIL reduces systematic underestimation of rare high‑intensity rainfall, improves detection of extreme events, and achieves higher equitable threat scores without significantly harming lower‑threshold accuracy.

Related stories

arXiv Machine Learning
Aug 19

MAGPIE-Net: Predicting short-duration heavy-rainfall events in station neighborhoods from multitemporal FY-4A AGRI observations

MAGPIE‑Net is a deep‑learning framework that directly maps multitemporal FY‑4A AGRI infrared and water‑vapor observations to short‑duration heavy‑rainfall warnings for irregular station neighborhoods. By embedding a geographically adaptive, differentiable grid‑to‑station mapping and training with station‑neighborhood event losses, the model outperforms traditional gridded‑precipitation baselines, achieving higher detection rates and longer lead times in 2023 warm‑season tests over China.

By Xiang Lin, Yunying Li, Chengzhi Ye, Zitong Chen, Jing Sun
More like this →
arXiv AI
Sep 16

Composable multi-satellite precipitation estimation for evolving observing systems

The paper introduces PRISMA, a generative framework that separates precipitation prior training from sensor-specific constraints, allowing flexible composition of heterogeneous satellite observations without retraining the core model. By integrating FY‑4B/AGRI, GPM/GMI, F16‑F18 SSMIS, and GPM/DPR‑Ka data, PRISMA consistently improves precipitation‑estimation accuracy and outperforms IMERG Final in CRPS and RMSE while maintaining positive Brier skill across thresholds. The framework supports rapid, accurate ensemble precipitation estimates, enhancing satellite‑based monitoring for hydrometeorological hazards.

By Yunfan Yang, Haofei Sun, Xiuyu Sun, Wei Han, Xiaoze Xu, Xingtao Song, Jun Li, Zhiqiu Gao, Wei Huang
More like this →
arXiv Machine Learning
Aug 27

Tropospheric temperature and humidity profile retrieval from Meteosat Flexible Combined Imager based on deep learning

The study presents a spatially aware deep learning framework that retrieves all‑sky tropospheric temperature and humidity profiles from the Meteosat Third Generation Flexible Combined Imager (FCI) without relying on numerical weather prediction background fields. Using a Residual U‑Net trained on 14 months of collocated FCI observations and CERRA reanalysis data, the model achieves temperature biases below 0.4 K and relative humidity standard deviations between 12–20 %, with modest performance degradation under cloud cover. Ablation and feature‑sensitivity analyses confirm that incorporating spatial context across all 16 FCI channels, including visible and near‑infrared bands, improves retrieval accuracy, especially beneath cloud tops.

By Alejandro Salgueiro, Johannes Rausch, Julie Th\'er\`ese Villinger, Angela Meyer
agentsbenchmarks
More like this →
arXiv Machine Learning
Jul 7

Enhancing the Forecasting Capability of Multi-Model Blending Algorithms for Extreme Precipitation via Joint Use of Station and Gridded Observations

arXiv:2607. 04862v1 Announce Type: new Abstract: Accurate extreme precipitation forecasting is critical for disaster mitigation but remains challenging for numerical weather prediction (NWP) models due to systemic intensity underestimation and spatial displacement.

By Yu Wang, Yong Cao, Kan Dai, Yue Shen, Xiaoqing Zeng, Ruixia Zhao
safety
More like this →
arXiv AI
Sep 7

MZ-Rain: Moisture-Budget-Guided Zero-Inflated Model for Station-Level Precipitation Nowcasting

MZ‑Rain is a moisture‑budget‑guided zero‑inflated sLSTM framework designed for station‑level precipitation nowcasting. It decomposes precipitation formation into moisture storage, transport, surface evaporation, and persistence pathways, each modeled by dedicated sLSTM branches, and employs an adaptive Tweedie strategy to handle the dataset’s severe zero inflation. Experiments across varied climates show MZ‑Rain outperforms strong baselines on metrics such as CSI, FAR, MSE, and MAE, especially for heavy precipitation events.

By Yifang Zhang, Shengwu Xiong, Henan Wang, Wenjie Yin, Yuqiang Zhang, Chen Zhou, Hua Chen, Qile Zhao, Pengfei Duan
More like this →