Machine learning improves groundwater quality monitoring
S. Himmelstein | November 22, 2024
Machine learning tools offer an opportunity to eliminate the time and cost intensity of groundwater monitoring networks while zeroing in on the supplies that should be prioritized for testing. The machine learning framework devised by researchers from Arizona State University and North Carolina State University uses limited water quality samples to predict which inorganic pollutants are likely to be present in a groundwater supply.
Two advanced multiple data imputation techniques, AMELIA and MICE algorithms, were applied to fill gaps in sparse groundwater quality data sets. The analysis spanned 140 years of water quality monitoring data for groundwater in North Carolina and Arizona and included more than 20 million data points covering more than 50 water quality parameters.
“We used this data set to ‘train’ a machine learning model to predict which elements would be present based on the available water quality data,” explained the researchers. “In other words, if we only have data on a handful of parameters, the program could still predict which inorganic pollutants were likely to be in the water, as well as how abundant those pollutants are likely to be.”
The models indicate pollutants are exceeding drinking water standards in more groundwater sources than previously documented. Field data suggest that 75% to 80% of sampled locations were within safe limits while the machine learning framework predicts that only 15% to 55% of the sites may truly be risk-free.
The research published in Environmental Science & Technology can be applied to fill critical gaps in groundwater quality in any region.