Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models
Abstract
Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts. We examined how forecast lead time affects the value of outage predictions for crew deployment, using operational forecasts from two AI weather models, GraphCast and FourCastNet, to predict outage occurrence for counties across the contiguous United States 24 to 120 hours ahead. Forecasts were evaluated by the share of outage burden captured by the counties where crews would be staged. Captured burden declined with lead time: the loss between three and five days was significant in all analyses, whereas the loss within three days was significant only for outages that had not yet started. Early deployment with all requested crews outperformed late deployment with fewer, and we report the availability ratio at which the two break even. Antecedent land surface predictors computed at forecast valid time include weather from the forecast period, which inflates their skill by 42 to 53% and reverses their apparent advantage over forecast meteorology at long lead times. Computed correctly, they improved occurrence skill by 17.5% at 24 hours but did not significantly change captured burden, a gap that attribution analysis linked to their static component. Prediction intervals covered only 0.476 of tropical cyclone events against a nominal 0.90. Calibration by hazard class corrected most of this shortfall at an 11% cost in interval width, as a diagnostic only, because hazard class is known only after the event.
Related
- AIFS Single 1.1.0: an update to ECMWF's machine-learned weather forecast model AIFS
- Forecast Skill Is Not Decision Skill: Evidence From Weather‐Dependent Decision Tasks
- Can AI Forecast the Extremes? Evaluating Probabilistic Weather Models on Tropical Cyclones
- Forecast‐Error Diagnostics in Neural Weather Models
- How well can we forecast local magnetic ground perturbations with existing space weather monitoring resources?
BibTeX
@misc{golkar2026forecast,
title = {{Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models}},
author = {Mohammad Kian Golkar and Luciano Alves de Oliveira and Mohamad Alipour},
howpublished = {arXiv},
year = {2026},
month = oct,
doi = {10.48550/arxiv.2610.20918},
eprint = {2610.20918},
archivePrefix = {arXiv},
url = {https://arxiv.org/abs/2610.20918},
note = {CC BY 4.0},
}
RIS
TY - UNPB
TI - Forecast lead time and the timing of crew deployment for weather-driven power outages using AI weather models
AU - Mohammad Kian Golkar
AU - Luciano Alves de Oliveira
AU - Mohamad Alipour
PY - 2026
DA - 2026/10/14
PB - arXiv
DO - 10.48550/arxiv.2610.20918
UR - https://arxiv.org/abs/2610.20918
AB - Utilities request mutual aid crews to restore power after severe storms, and requesting early secures more crews but relies on less accurate forecasts. We examined how forecast lead time affects the value of outage predictions for crew deployment, using operational forecasts from two AI weather models, GraphCast and FourCastNet, to predict outage occurrence for counties across the contiguous United States 24 to 120 hours ahead. Forecasts were evaluated by the share of outage burden captured by the counties where crews would be staged. Captured burden declined with lead time: the loss between three and five days was significant in all analyses, whereas the loss within three days was significant only for outages that had not yet started. Early deployment with all requested crews outperformed late deployment with fewer, and we report the availability ratio at which the two break even. Antecedent land surface predictors computed at forecast valid time include weather from the forecast period, which inflates their skill by 42 to 53% and reverses their apparent advantage over forecast meteorology at long lead times. Computed correctly, they improved occurrence skill by 17.5% at 24 hours but did not significantly change captured burden, a gap that attribution analysis linked to their static component. Prediction intervals covered only 0.476 of tropical cyclone events against a nominal 0.90. Calibration by hazard class corrected most of this shortfall at an 11% cost in interval width, as a diagnostic only, because hazard class is known only after the event.
ER -