Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences
This white paper focuses on water for energy.
High frequency, reliable, and spatially explicit flood forecasts are necessary to forecast impacts to the energy system from hydrological hazards. While these tools are nearing operation at scale, they have not yet been systematically connected to information on critical energy infrastructure, creating a gap in how efficiently we use the knowledge generated by this significant program in support of energy resilience.
Over the next three to five years, significant opportunities exist to advance the resilience of the United States' energy-water systems by integrating emerging flood forecasting capabilities with models of the nation?s energy infrastructure. It is now feasible to couple flood inundation forecasts with models of the electricity transmission system and natural gas pipeline system with very high reliability. This integration would enable daily, automated energy system impact assessments based on continuously updated hydrologic forecasts. It would provide energy system operators with reliable, near-real-time insights into how forecasted water system hazards may disrupt critical energy infrastructure. Such a capability would improve situational awareness and extend the decision-making window for mitigation actions from hours to days. We aim to accomplish this goal by developing and demonstrating a connection between NOAAs Flood Inundation Model (FIM) capability, and existing Energy Resilience Models produced by the Department of Energy.
The success of this approach could be demonstrated by the ability to provide reliable, actionable, and probabilistic week-ahead forecasts of flood impacts to critical energy infrastructure. The primary quantitative measure of success will be the accuracy and reliability of the energy system forecasts, evaluated through (a) comparisons between predicted and observed flood impacts on specific energy infrastructure such as substations or compressor stations and (b) through comparisons between predicted and observed flood impacts on the electricity transmission system or natural gas pipeline system's ability to deliver energy to users. Indicators of enhanced energy system resilience could include reductions in outage duration and extent, and improvements in system recovery times following extreme events.
Citation Formats
TY - DATA
AB - This white paper focuses on water for energy.
High frequency, reliable, and spatially explicit flood forecasts are necessary to forecast impacts to the energy system from hydrological hazards. While these tools are nearing operation at scale, they have not yet been systematically connected to information on critical energy infrastructure, creating a gap in how efficiently we use the knowledge generated by this significant program in support of energy resilience.
Over the next three to five years, significant opportunities exist to advance the resilience of the United States' energy-water systems by integrating emerging flood forecasting capabilities with models of the nation?s energy infrastructure. It is now feasible to couple flood inundation forecasts with models of the electricity transmission system and natural gas pipeline system with very high reliability. This integration would enable daily, automated energy system impact assessments based on continuously updated hydrologic forecasts. It would provide energy system operators with reliable, near-real-time insights into how forecasted water system hazards may disrupt critical energy infrastructure. Such a capability would improve situational awareness and extend the decision-making window for mitigation actions from hours to days. We aim to accomplish this goal by developing and demonstrating a connection between NOAAs Flood Inundation Model (FIM) capability, and existing Energy Resilience Models produced by the Department of Energy.
The success of this approach could be demonstrated by the ability to provide reliable, actionable, and probabilistic week-ahead forecasts of flood impacts to critical energy infrastructure. The primary quantitative measure of success will be the accuracy and reliability of the energy system forecasts, evaluated through (a) comparisons between predicted and observed flood impacts on specific energy infrastructure such as substations or compressor stations and (b) through comparisons between predicted and observed flood impacts on the electricity transmission system or natural gas pipeline system's ability to deliver energy to users. Indicators of enhanced energy system resilience could include reductions in outage duration and extent, and improvements in system recovery times following extreme events.
AU - Brelsford, Christa
A2 - Garcia, Manuel
A3 - Robbins, Zachary
A4 - Schwenk, Jon
A5 - Chinthavali, Supriya
A6 - Liu, Yan
DB - Energy-Water Resilience
DP - Open EI | National Laboratory of the Rockies
DO -
KW - energy infrastructure
KW - flooding
KW - forecasts
KW - energy resilience
KW - flood mapping
KW - machine learning
KW - AI predictions
KW - energy resilience models
KW - societal impacts
KW - stakeholder collaboration
KW - operational confidence
KW - energy robustness
KW - energy flexibility
KW - forecast
KW - flood exposure
KW - AI
KW - artificial intelligence
KW - consequences
KW - flood forecast
LA - English
DA - 2026/01/15
PY - 2026
PB - LANL
T1 - Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences
UR - https://ewr.openei.org/submissions/14
ER -
Brelsford, Christa, et al. Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences. LANL, 15 January, 2026, Energy-Water Resilience. https://ewr.openei.org/submissions/14.
Brelsford, C., Garcia, M., Robbins, Z., Schwenk, J., Chinthavali, S., & Liu, Y. (2026). Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences. [Data set]. Energy-Water Resilience. LANL. https://ewr.openei.org/submissions/14
Brelsford, Christa, Manuel Garcia, Zachary Robbins, Jon Schwenk, Supriya Chinthavali, and Yan Liu. Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences. LANL, January, 15, 2026. Distributed by Energy-Water Resilience. https://ewr.openei.org/submissions/14
@misc{EWR_Dataset_14,
title = {Maximizing American Energy Dominance with Forecasts of Energy Infrastructure Flood Exposure and AI Predictions of Consequences},
author = {Brelsford, Christa and Garcia, Manuel and Robbins, Zachary and Schwenk, Jon and Chinthavali, Supriya and Liu, Yan},
abstractNote = {This white paper focuses on water for energy.
High frequency, reliable, and spatially explicit flood forecasts are necessary to forecast impacts to the energy system from hydrological hazards. While these tools are nearing operation at scale, they have not yet been systematically connected to information on critical energy infrastructure, creating a gap in how efficiently we use the knowledge generated by this significant program in support of energy resilience.
Over the next three to five years, significant opportunities exist to advance the resilience of the United States' energy-water systems by integrating emerging flood forecasting capabilities with models of the nation?s energy infrastructure. It is now feasible to couple flood inundation forecasts with models of the electricity transmission system and natural gas pipeline system with very high reliability. This integration would enable daily, automated energy system impact assessments based on continuously updated hydrologic forecasts. It would provide energy system operators with reliable, near-real-time insights into how forecasted water system hazards may disrupt critical energy infrastructure. Such a capability would improve situational awareness and extend the decision-making window for mitigation actions from hours to days. We aim to accomplish this goal by developing and demonstrating a connection between NOAAs Flood Inundation Model (FIM) capability, and existing Energy Resilience Models produced by the Department of Energy.
The success of this approach could be demonstrated by the ability to provide reliable, actionable, and probabilistic week-ahead forecasts of flood impacts to critical energy infrastructure. The primary quantitative measure of success will be the accuracy and reliability of the energy system forecasts, evaluated through (a) comparisons between predicted and observed flood impacts on specific energy infrastructure such as substations or compressor stations and (b) through comparisons between predicted and observed flood impacts on the electricity transmission system or natural gas pipeline system's ability to deliver energy to users. Indicators of enhanced energy system resilience could include reductions in outage duration and extent, and improvements in system recovery times following extreme events.},
url = {https://ewr.openei.org/submissions/14},
year = {2026},
howpublished = {Energy-Water Resilience, LANL, https://ewr.openei.org/submissions/14},
note = {Accessed: 2026-06-17}
}
Details
Data from Jan 15, 2026
Last updated Jan 16, 2026
Submitted Jan 15, 2026
Contact
Christa Brelsford
Authors
Keywords
energy infrastructure, flooding, forecasts, energy resilience, flood mapping, machine learning, AI predictions, energy resilience models, societal impacts, stakeholder collaboration, operational confidence, energy robustness, energy flexibility, forecast, flood exposure, AI, artificial intelligence, consequences, flood forecastDOE Project Details
Project Name White Papers on Ideas to Advance Energy-Water Resilience
Project Lead
Project Number WP-014
