Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis
This white paper outlines a strategy for enhancing energy-efficient water management in agriculture through the application of Geospatial Artificial Intelligence (GeoAI). The focus is on developing a Dynamic Irrigation Window Scheduling (DIWS) system that optimizes irrigation based on real-time data regarding evapotranspiration (ET), crop health, and energy pricing signals. By integrating energy use with field-scale water demand, this model aims to improve the resilience and coordination of energy and water resources in agriculture.
Agriculture is the largest consumer of water in the U.S., with irrigation accounting for 47% of freshwater withdrawals. Despite irrigated farms producing over 50% of crop value, most irrigation systems rely on fixed schedules that do not account for variability in ET, crop stress, or energy tariffs. This rigidity leads to significant water waste, yield losses, and increased energy consumption, particularly during peak grid hours. Current satellite data on ET, although available, are not integrated into adaptive irrigation frameworks, limiting their effectiveness. Additionally, governance inconsistencies and rigid irrigation schedules hinder flexibility and responsiveness.
The DIWS system would utilize satellite-based ET forecasting, AI-driven crop diagnostics, and grid-responsive energy optimization to provide a flexible irrigation framework. By analyzing data from various sources, including satellite imagery and IoT sensors, the system would generate 72-hour adaptive irrigation windows that align with real-time crop needs and energy costs. This approach aims to reduce water use, energy consumption, and crop disease risk while maintaining yield and profitability.
If successfully implemented, the DIWS system could reduce water use by 15-25%, energy consumption by 20-30%, and crop losses by approximately 10%. Additionally, it would provide utilities with better visibility into agricultural demand, allowing for more coordinated water-energy management and support for renewable energy integration.
Citation Formats
TY - DATA
AB - This white paper outlines a strategy for enhancing energy-efficient water management in agriculture through the application of Geospatial Artificial Intelligence (GeoAI). The focus is on developing a Dynamic Irrigation Window Scheduling (DIWS) system that optimizes irrigation based on real-time data regarding evapotranspiration (ET), crop health, and energy pricing signals. By integrating energy use with field-scale water demand, this model aims to improve the resilience and coordination of energy and water resources in agriculture.
Agriculture is the largest consumer of water in the U.S., with irrigation accounting for 47% of freshwater withdrawals. Despite irrigated farms producing over 50% of crop value, most irrigation systems rely on fixed schedules that do not account for variability in ET, crop stress, or energy tariffs. This rigidity leads to significant water waste, yield losses, and increased energy consumption, particularly during peak grid hours. Current satellite data on ET, although available, are not integrated into adaptive irrigation frameworks, limiting their effectiveness. Additionally, governance inconsistencies and rigid irrigation schedules hinder flexibility and responsiveness.
The DIWS system would utilize satellite-based ET forecasting, AI-driven crop diagnostics, and grid-responsive energy optimization to provide a flexible irrigation framework. By analyzing data from various sources, including satellite imagery and IoT sensors, the system would generate 72-hour adaptive irrigation windows that align with real-time crop needs and energy costs. This approach aims to reduce water use, energy consumption, and crop disease risk while maintaining yield and profitability.
If successfully implemented, the DIWS system could reduce water use by 15-25%, energy consumption by 20-30%, and crop losses by approximately 10%. Additionally, it would provide utilities with better visibility into agricultural demand, allowing for more coordinated water-energy management and support for renewable energy integration.
AU - Cafferty, Kara
A2 - Zaman, Bushra
A3 - Pacheco, Camilo J. Bastidas
DB - Energy-Water Resilience
DP - Open EI | National Laboratory of the Rockies
DO -
KW - Energy-efficient water management
KW - Artificial Intelligence AI
KW - Agriculture
KW - Evapotranspiration ET
KW - Irrigation
KW - GeoAI
KW - Geospatial
KW - AI
KW - DIWS
KW - Dynamic Irrigation Window Scheduling
KW - evapotranspiration
KW - crop health
KW - energy pricing
KW - water demand
LA - English
DA - 2026/01/16
PY - 2026
PB - INL
T1 - Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis
UR - https://ewr.openei.org/submissions/43
ER -
Cafferty, Kara, et al. Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis. INL, 16 January, 2026, Energy-Water Resilience. https://ewr.openei.org/submissions/43.
Cafferty, K., Zaman, B., & Pacheco, C. (2026). Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis. [Data set]. Energy-Water Resilience. INL. https://ewr.openei.org/submissions/43
Cafferty, Kara, Bushra Zaman, and Camilo J. Bastidas Pacheco. Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis. INL, January, 16, 2026. Distributed by Energy-Water Resilience. https://ewr.openei.org/submissions/43
@misc{EWR_Dataset_43,
title = {Energy-Efficient Water Management Using Geo-AI for Evapotranspiration and Crop Risk Analysis},
author = {Cafferty, Kara and Zaman, Bushra and Pacheco, Camilo J. Bastidas},
abstractNote = {This white paper outlines a strategy for enhancing energy-efficient water management in agriculture through the application of Geospatial Artificial Intelligence (GeoAI). The focus is on developing a Dynamic Irrigation Window Scheduling (DIWS) system that optimizes irrigation based on real-time data regarding evapotranspiration (ET), crop health, and energy pricing signals. By integrating energy use with field-scale water demand, this model aims to improve the resilience and coordination of energy and water resources in agriculture.
Agriculture is the largest consumer of water in the U.S., with irrigation accounting for 47\% of freshwater withdrawals. Despite irrigated farms producing over 50\% of crop value, most irrigation systems rely on fixed schedules that do not account for variability in ET, crop stress, or energy tariffs. This rigidity leads to significant water waste, yield losses, and increased energy consumption, particularly during peak grid hours. Current satellite data on ET, although available, are not integrated into adaptive irrigation frameworks, limiting their effectiveness. Additionally, governance inconsistencies and rigid irrigation schedules hinder flexibility and responsiveness.
The DIWS system would utilize satellite-based ET forecasting, AI-driven crop diagnostics, and grid-responsive energy optimization to provide a flexible irrigation framework. By analyzing data from various sources, including satellite imagery and IoT sensors, the system would generate 72-hour adaptive irrigation windows that align with real-time crop needs and energy costs. This approach aims to reduce water use, energy consumption, and crop disease risk while maintaining yield and profitability.
If successfully implemented, the DIWS system could reduce water use by 15-25\%, energy consumption by 20-30\%, and crop losses by approximately 10\%. Additionally, it would provide utilities with better visibility into agricultural demand, allowing for more coordinated water-energy management and support for renewable energy integration.
},
url = {https://ewr.openei.org/submissions/43},
year = {2026},
howpublished = {Energy-Water Resilience, INL, https://ewr.openei.org/submissions/43},
note = {Accessed: 2026-11-16}
}
Details
Data from Jan 16, 2026
Last updated Jan 16, 2026
Submitted Jan 16, 2026
Contact
Kara Cafferty
Authors
Keywords
Energy-efficient water management, Artificial Intelligence AI, Agriculture, Evapotranspiration ET, Irrigation, GeoAI, Geospatial, AI, DIWS, Dynamic Irrigation Window Scheduling, evapotranspiration, crop health, energy pricing, water demandDOE Project Details
Project Name White Papers on Ideas to Advance Energy-Water Resilience
Project Lead
Project Number WP-043
