Scientists Map America's Hidden Water Reserves Using AI Technology

Revolutionary Mapping Technique Reveals Vast Underground Resources

Deep beneath American soil lies a vast reservoir of fresh water that has remained largely unmapped until now. Scientists have determined that there are approximately 306,000 cubic kilometers of groundwater across the United States—more than 13 times the volume of all the Great Lakes combined . This groundbreaking discovery comes from researchers at Princeton University who used artificial intelligence to create the most detailed map of America's groundwater ever produced.

The team combined more than a million direct measurements of groundwater depth with regional climate and geological data , then used this information to train AI algorithms that estimated groundwater depth at sites where measurements were not available . The result is a comprehensive picture of America's hidden water wealth at unprecedented resolution.

"Given all the things we do know about the planet, we don't actually know how much water we have," said Reed Maxwell, the study's senior author and Princeton professor . "And since most of it's in groundwater, knowing how much surface water we have is only about 1% of the total. That's where this becomes a hard problem."

Breakthrough Technology Provides Unprecedented Detail

The researchers divided the continental United States into a grid of more than 8 billion squares, each about 30 meters on a side, producing a groundwater depth estimate for every one of them . This represents a dramatic improvement over previous methods. Previous models have been mainly physics-based, mapping water table depth at a resolution of about 1 kilometer , while the team's data-driven, AI-based model achieves a spatial resolution more than 1,000 times greater than physics-based models .

The machine learning approach, based on random forest algorithms, doesn't just provide estimates—it also quantifies uncertainty. "For each location, the method uses 300 decision trees" to generate reliable predictions, explained co-author Peter Melchior from Princeton's Center for Statistics and Machine Learning.

The research analyzed groundwater measurements from 1895 to 2023, with more than half of the locations measured only once. The team used all available data to build the best estimate possible , creating what Maxwell calls "a modern estimate" rather than an estimate at a specific point in time .

Practical Implications for Water Management

This detailed mapping has immediate practical value for agriculture, conservation, and water infrastructure planning. The new approach is built to detect shallow groundwater that can make or break agricultural planning, while older models often missed it . "It's this local decision [of how to irrigate] that is made millions of times," Maxwell noted .

While this data-driven method shows an amount of water that's in line with earlier studies, it does reveal supplies of shallow groundwater that were previously unknown. The work provides a foundation for further research as well as local and regional decision-making around irrigation, conservation and water infrastructure .

According to study lead author Yueling Ma, researchers focused on geochemistry and water quality have already shown interest in using the dataset to guide their own modeling. The model outputs are publicly available through the team's HydroFrame platform, which is part of a broader effort called HydroGEN. The goal is to make hydrology tools easier to access and apply, not just for specialists .

Looking Toward a Global Future

The Princeton team isn't stopping with the United States. In collaboration with local experts, the team is beginning to expand its method globally. Ma, now in Germany, and co-author Julian Koch of the Geological Survey of Denmark and Greenland are focusing on areas of Europe. Maxwell recently returned to Princeton from a sabbatical in Australia, where he is working with hydrologists to build both physics-based and machine-learning groundwater models for the continent. Others in his group are leading similar work in Brazil .

"The idea is to build this community globally, with the hope that as the model gets more generalized and more robust, it becomes a foundational machine-learning model for groundwater," Maxwell concluded . As water scarcity becomes an increasingly pressing global challenge, this AI-powered approach to mapping the world's hidden water reserves could prove invaluable for sustainable resource management worldwide.