EvoBench is a diagnostic benchmark framework designed to reveal where and when machine‑learning models for environmental variables fail, rather than relying on a single average accuracy score. It tracks model performance over time and across spatial extrapolation, highlighting issues such as non‑stationarity, poor performance at unmonitored sites, and under‑prediction of rare events like floods. In a case study on daily streamflow prediction across 9,000 U.S. basins, EvoBench shows that no model dominates all scenarios and that targeted fixes can mitigate identified weaknesses.
By Yiming Sun, Yuan Zhang, Qi Cheng, Yingda Fan, Runlong Yu, Yiqun Xie, Xiaowei Jia
OutageDiT is a foundation model designed to generate seven‑day power‑outage trajectories at 15‑minute resolution. It uses a condition encoder to process historical context and future covariates, and a shallow flow‑matching decoder to sample complete outage trajectories, enabling point forecasting, uncertainty quantification, and conditional scenario generation. The model improves forecast accuracy and scenario quality over strong baselines and can transfer zero‑shot to held‑out regions, linking outage forecasting to operational planning under uncertainty.
By Yunqin Zhu, Feng Qiu, Yao Xie
The study evaluates how forecast lead time influences the effectiveness of outage predictions for crew deployment using AI weather models GraphCast and FourCastNet. It finds that the ability to capture outage burden decreases with longer lead times, with a notable drop between three and five days. Early deployment with all requested crews outperforms late deployment with fewer crews, and the study also examines the impact of antecedent land surface predictors and calibration of prediction intervals for tropical cyclone events.
By Mohammad Kian Golkar, Luciano Alves de Oliveira, Mohamad Alipour
OutageDiT is a generative foundation model that produces seven‑day power‑outage trajectories at quarter‑hour resolution, trained on nationwide outage and weather data. It uses a condition encoder to process historical context and future covariates, and a shallow flow decoder to generate full trajectories, enabling point forecasting, uncertainty quantification, and conditional event simulation. The model outperforms strong baselines on forecasting benchmarks and can transfer zero‑shot to unseen regions, linking outage simulation to operational planning under uncertainty.
By Yunqin Zhu, Feng Qiu, Yao Xie
arXiv:2607. 16050v1 Announce Type: new Abstract: Pluvial (rainfall-driven) flooding accounts for 45% of National Flood Insurance Program (NFIP) claims in the United States and is harder to predict than its riverine and coastal counterparts, with existing approaches limited to coarse resolution, regional domains, or computationally intensive process-based models unsuitable for daily continental-scale use.
By Yuya Kawakami, Daniel Cayan, Dongyu Liu, Kwan-Liu Ma, Tom Corringham
The paper presents a modular, scalable framework for estimating the probability of failure (PoF) of power‑line assets using geospatial machine learning. It integrates diverse environmental predictors—topography, vegetation indices, lightning climatology, proximity features, and operational records—to model vegetation‑ and lightning‑related failure modes. The architecture is designed to be computationally efficient, easily extensible to new data sources, and suitable for large‑scale utility deployment, enabling asset‑level risk stratification for inspection and resilience planning.
By Artur Sokolovsky, Bhavik Merai, Moe Jafari, Muen Chen
arXiv:2606. 08630v1 Announce Type: cross Abstract: Global wind power capacity, especially in China, is booming, with new farms spanning diverse terrains and climates.
By Jiahui Huang, Ao Luo, Lei Liu, Hongwei Zhao, Tengyuan Liu, Ruibo Guo, Bo Wang, Zhao Wang, Bin Li
This study evaluates large language models (LLMs) for predicting weather‑related forced outage risk in a distribution grid using a zero‑shot approach without labeled training data. The task is framed as binary severity classification over 3h, 6h, and 12h horizons, leveraging six years of outage records and high‑resolution weather data from central Texas. Four zero‑shot LLMs are compared to two supervised classifiers under two input settings—current weather observations and forecast data—showing that supervised models lead on macro‑F1 and precision, while newer LLMs achieve competitive scores and offer complementary strengths in reasoning and geographic scalability.
By Christos Petridis, Zoran Obradovic, Mladen Kezunovic
arXiv:2609.14821v1 Announce Type: new
Abstract: Earth system modeling is shifting from task-specific predictors toward foundation models with general spatiotemporal representation capabilities. Altho...
By Ji Lu, Huiran Duan, Bo Zhao, Xianglong Wang, Yiru Fang, Kuo Yang, Xiaoqin Feng, Jianping Gou
arXiv:2608. 12663v1 Announce Type: cross Abstract: Wildfire susceptibility mapping typically relies on physical variables assembled from multiple remote-sensing, climate, and geospatial products.
By Yuan Zhuang, Sanaa Hobeichi, Peng Shi, Fei Huang
arXiv:2606. 27277v1 Announce Type: new Abstract: Earth Observation (EO) forecasting aims to predict future Earth surface dynamics from satellite observations under changing meteorological conditions.
By Junwei Luo, Shuai Yuan, Zhenya Yang, Yansheng Li, Zhe Liu, Hengshuang Zhao
arXiv:2608. 00012v1 Announce Type: cross Abstract: Multimodal Large Language Models (MLLMs) are increasingly used to interpret Earth observation data, yet their capability to support real-world disaster emergency response remains insufficiently evaluated.
By Fengxiang Wang, Qiuyang Yu, Yueying Li, Mingshuo Chen, Chengchi Fei, Kaiyi Xu, Lixin Gu, Wangxu Wei, Junchao Gong, Lipeng Ma, Jiong Wang, Fenghua Ling, Wenlong Zhang, Xue Yang, Wenjing Yang, Ben Fei, Long Lan