Skip to main content
U.S. flag

An official website of the United States government

Paul Stackelberg

Paul Stackelberg is a Hydrologist with the Water Resources Mission Area.

Paul Stackelberg has worked as a hydrologist with the U.S. Geological Survey (USGS) since 1988. His research interests have included (1) evaluating natural and anthropogenic factors that affect groundwater quality, (2) developing statistical models for predicting the occurrence of contaminants in groundwater resources, and (3) determining the persistence and fate of pharmaceuticals and other wastewater-related compounds in conventional and advanced drinking-water-treatment facilities. Currently Paul is leading a team of USGS scientist who are using machine learning methods to predict groundwater quality conditions in three dimensions throughout select principal aquifers of the United States as well as at the depths commonly used for domestic and public supplies at the National scale.

Education:

M.S., Geology, University of Missouri - Columbia.

B.S., Geology and Mineralology, The Ohio State University, Minor: Computer and Information Science.

Science and Products

link
A rainbow arc over a large-volume public-supply well

Groundwater Quality Research

Every day, millions of gallons of groundwater are pumped to supply drinking water for about 140 million people, almost one-half of the Nation’s population. Learn about the quality and availability of groundwater for drinking, where and why groundwater quality is degraded, and where groundwater quality is changing.
By
Water Resources Mission Area, National Water Quality Program, Colorado Water Science Center, Dakota Water Science Center, Wyoming-Montana Water Science Center
link

Groundwater Quality Research

Every day, millions of gallons of groundwater are pumped to supply drinking water for about 140 million people, almost one-half of the Nation’s population. Learn about the quality and availability of groundwater for drinking, where and why groundwater quality is degraded, and where groundwater quality is changing.
Learn More
link
Map of the Southwestern U.S. showing predicted concentrations of arsenic in shades of green (low) to orange (high)

Predicting Groundwater Quality in Unmonitored Areas

Groundwater provides nearly one-half of the Nation’s drinking water, and sustains the steady flow of streams and rivers and the ecological systems that depend on that flow. Unless we drill a well, how can we know the quality of the groundwater below? Learn about how the USGS is using sophisticated techniques to predict groundwater quality and view national maps of groundwater quality.
By
Water Resources Mission Area, National Water Quality Program
link

Predicting Groundwater Quality in Unmonitored Areas

Groundwater provides nearly one-half of the Nation’s drinking water, and sustains the steady flow of streams and rivers and the ecological systems that depend on that flow. Unless we drill a well, how can we know the quality of the groundwater below? Learn about how the USGS is using sophisticated techniques to predict groundwater quality and view national maps of groundwater quality.
Learn More
link
multicolored map of aquifers in the United States

National Water Quality Assessment Program -- Water-Quality Assessments of Principal Aquifers

A major focus of the NAWQA Program in its second decade (2002-2013) is on regional- and national-scale assessments of groundwater-quality status and trends in principal aquifers. The U.S. Geological Survey Office of Groundwater has identified 62 principal aquifers in the U.S. (U.S. Geological Survey, 2003). About 1/3 of the Nation's principal aquifers are the focus of water-quality assessments at
By
New York Water Science Center
link

National Water Quality Assessment Program -- Water-Quality Assessments of Principal Aquifers

A major focus of the NAWQA Program in its second decade (2002-2013) is on regional- and national-scale assessments of groundwater-quality status and trends in principal aquifers. The U.S. Geological Survey Office of Groundwater has identified 62 principal aquifers in the U.S. (U.S. Geological Survey, 2003). About 1/3 of the Nation's principal aquifers are the focus of water-quality assessments at
Learn More

Data for depth of groundwater used for drinking-water supplies in the United States

This data release includes grids representing the depth and thickness of drinking-water withdrawal zones, polygons of hydrogeologic settings, an inventory of sources of well construction data, and summaries of data comparisons used to assess the depth of groundwater used for drinking-water supplies in the United States. Well construction data sources are documented in Table1_DataSources.xlsx. Data
By
Water Resources Mission Area

Data for Machine Learning Predictions of Nitrate in Groundwater Used for Drinking Supply in the Conterminous United States

A three-dimensional extreme gradient boosting (XGB) machine learning model was developed to predict the distribution of nitrate in groundwater across the conterminous United States (CONUS). Nitrate was predicted at a 1-square-kilometer (km) resolution for two drinking water zones, each of variable depth, one for domestic supply and one for public supply. The model used measured nitrate concentrati
By
California Water Science Center

Data Release for Evaluation of Six Methods for Correcting Bias in Estimates from Ensemble Tree Machine Learning Regression Models

Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias: (1) empirical distribution matching (EDM); (2) regression of
By
Water Resources Mission Area

Data for machine learning predictions of pH in the glacial aquifer system, northern USA

A boosted regression tree (BRT) model was developed to predict pH conditions in three-dimensions throughout the glacial aquifer system (GLAC) of the contiguous United States using pH measurements in samples from 18,258 wells and predictor variables that represent aspects of the hydrogeologic setting. Model results indicate that the carbonate content of soils and aquifer materials strongly controls
By
Water Resources Mission Area

Data for Radium Mobility and the Age of Groundwater in Public-drinking-water Supplies from the Cambrian-Ordovician Aquifer System, North-Central USA

High radium (Ra) concentrations in potable portions of the Cambrian-Ordovician (C-O) aquifer system were investigated using water-quality data and environmental tracers ( 3H, 3Hetrit, SF6 , 14C and 4Herad) of groundwater age from 80 public-supply wells (PSWs). Groundwater ages were estimated by calibration of tracers to lumped parameter models and ranged from modern (1 Myr) in the most downgradien
By
Water Resources Mission Area, National Water Quality Program

Datasets from Groundwater-Quality Data from the National Water-Quality Assessment Project, January through December 2014 and Select Quality-Control Data from May 2012 through December 2014

Groundwater-quality data were collected from 559 wells as part of the National Water-Quality Assessment Project of the U.S. Geological Survey National Water-Quality Program from January through December 2014. The data were collected from four types of well networks: principal aquifer study networks, which assess the quality of groundwater used for public water supply; land-use study networks, whic
By
Water Resources Mission Area, National Water Quality Program
No results found.
Filter Total Items: 38

A spatial machine learning model developed from noisy data requires multiscale performance evaluation: Predicting depth to bedrock in the Delaware River Basin, USA

Spatial machine learning models can be developed from observations with substantial unexplainable variability, sometimes called ‘noise’. Traditional point-scale metrics (e.g., R2) alone can be misleading when evaluating these models. We present a multi-scale performance evaluation (MPE) using two additional scales (distributional and geostatistical). We apply the MPE framework to predictions of de
Authors
Phillip J. Goodling, Kenneth Belitz, Paul Stackelberg, Brandon J. Fleming
By
Water Resources Mission Area, National Water Quality Program, Maryland-Delaware-D.C. Water Science Center, Pennsylvania Water Science Center

Salinity and total dissolved solids measurements for natural waters: An overview and a new salinity method based on specific conductance and water type

The total concentration of dissolved constituents in water is routinely quantified by measurements of salinity or total dissolved solids (TDS). However, salinity and TDS are operationally defined by their analytical methods and are not equivalent for most waters. Furthermore, multiple methods are available to determine salinity and TDS, and these methods have inherent differences. TDS is defined a
Authors
R. Blaine McCleskey, Charles A. Cravotta, Matthew P. Miller, Fred D. Tillman, Paul Stackelberg, Katherine J. Knierim, Daniel Wise
By
Water Resources Mission Area, National Water Quality Program, Arizona Water Science Center, Lower Mississippi-Gulf Water Science Center, Oregon Water Science Center, Pennsylvania Water Science Center

Gross alpha-particle activity and high 226Ra concentrations do not correspond with high 210Po in the Atlantic and Gulf Coastal Plain aquifers of the United States

210Po, which is of human-health concern based on lifetime ingestion cancer risk, is indirectly regulated in drinking water through the U.S. Environmental Protection Agency’s gross alpha-particle activity (GAPA) maximum contaminant level of 15 pCi/L (picocuries per liter). This regulation requires independent measurement of 226Ra for samples exceeding the GAPA screening level of 5 pCi/L. There is n

Authors
Zoltan Szabo, Charles A. Cravotta, Paul Stackelberg, Kenneth Belitz
By
Water Resources Mission Area, New England Water Science Center, New Jersey Water Science Center, Pennsylvania Water Science Center

Quality of groundwater used for public supply in the continental United States: A comprehensive assessment

The presence of contaminants in a source water can constrain its suitability for drinking. The quality of groundwater used for public supply was assessed in 25 principal aquifers (PAs) that account for 84% of groundwater pumped for public supply in the U.S. (89.6 million people on a proportional basis). Each PA was sampled across its lateral extent using an equal-area grid, typically with 60 wells

Authors
Kenneth Belitz, Miranda S. Fram, Bruce D. Lindsey, Paul Stackelberg, Laura M. Bexfield, Tyler D. Johnson, Bryant Jurgens, James A. Kingsbury, Peter B. McMahon, Neil M. Dubrovsky
By
Water Resources Mission Area, California Water Science Center, Colorado Water Science Center, New Mexico Water Science Center

Mapped predictions of manganese and arsenic in an alluvial aquifer using boosted regression trees

Manganese (Mn) concentrations and the probability of arsenic (As) exceeding the drinking-water standard of 10 μg/L were predicted in the Mississippi River Valley alluvial aquifer (MRVA) using boosted regression trees (BRT). BRT, a type of ensemble-tree machine-learning model, were created using predictor variables that affect Mn and As distribution in groundwater. These variables included iron (Fe
Authors
Katherine J. Knierim, James A. Kingsbury, Kenneth Belitz, Paul Stackelberg, Burke J. Minsley, James R. Rigby
By
Water Resources Mission Area, New England Water Science Center, Lower Mississippi-Gulf Water Science Center, Geology, Geophysics, and Geochemistry Science Center

Relation between road-salt application and increasing radium concentrations in a low-pH aquifer, southern New Jersey

The Kirkwood–Cohansey aquifer in southern New Jersey is an important source of drinking-water supplies, but the availability of the resource is limited in some areas by high concentrations of radium, a potential carcinogen at elevated concentrations. Radium (226Ra plus 228Ra) concentrations from a network of 25 drinking-water wells showed a statistically significant increase over a decadal time sc

Authors
Bruce D. Lindsey, Charles A. Cravotta, Zoltan Szabo, Kenneth Belitz, Paul Stackelberg
By
Water Resources Mission Area, New Jersey Water Science Center, Pennsylvania Water Science Center

Depth of groundwater used for drinking-water supplies in the United States

Groundwater supplies 35 percent of drinking water in the United States. Mapping the quantity and quality of groundwater at the depths used for potable supplies requires an understanding of locational variation in the characteristics of drinking-water wells (depth and open interval). Typical depths of domestic- and public-drinking-water supply wells vary by and within aquifer across the United Stat
Authors
James R. Degnan, Leon J. Kauffman, Melinda L. Erickson, Kenneth Belitz, Paul E. Stackelberg
By
Water Resources Mission Area, New England Water Science Center

Machine learning predictions of nitrate in groundwater used for drinking supply in the conterminous United States

Groundwater is an important source of drinking water supplies in the conterminous United State (CONUS), and presence of high nitrate concentrations may limit usability of groundwater in some areas because of the potential negative health effects. Prediction of locations of high nitrate groundwater is needed to focus mitigation and relief efforts. A three-dimensional extreme gradient boosting (XGB)
Authors
Katherine Marie Ransom, Bernard T. Nolan, Paul Stackelberg, Kenneth Belitz, Miranda S. Fram
By
Water Resources Mission Area, California Water Science Center

Predicting regional fluoride concentrations at public and domestic supply depths in basin-fill aquifers of the western United States using a random forest model

A random forest regression (RFR) model was applied to over 12,000 wells with measured fluoride (F) concentrations in untreated groundwater to predict F concentrations at depths used for domestic and public supply in basin-fill aquifers of the western United States. The model relied on twenty-two regional-scale environmental and surficial predictor variables selected to represent factors known to c
Authors
Celia Z Rosecrans, Kenneth Belitz, Katherine Marie Ransom, Paul E. Stackelberg, Peter B. McMahon
By
Water Resources Mission Area, California Water Science Center, Colorado Water Science Center, New England Water Science Center, New York Water Science Center

Machine-learning predictions of high arsenic and high manganese at drinking water depths of the glacial aquifer system, northern continental United States

Globally, over 200 million people are chronically exposed to arsenic (As) and/or manganese (Mn) from drinking water. We used machine-learning (ML) boosted regression tree (BRT) models to predict high As (>10 μg/L) and Mn (>300 μg/L) in groundwater from the glacial aquifer system (GLAC), which spans 25 states in the northern United States and provides drinking water to 30 million people. Our BRT mo
Authors
Melinda L. Erickson, Sarah M. Elliott, Craig J. Brown, Paul Stackelberg, Katherine Marie Ransom, James E. Reddy, Charles A. Cravotta
By
Water Resources Mission Area, California Water Science Center, New England Water Science Center, New York Water Science Center, Pennsylvania Water Science Center, Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center

Evaluation of six methods for correcting bias in estimates from ensemble tree machine learning regression model

Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias. Method performance was evaluated using four case studies of
Authors
Kenneth Belitz, Paul Stackelberg
By
Water Resources Mission Area

Machine learning predicted redox conditions in the glacial aquifer system, northern continental United States

Groundwater supplies 50% of drinking water worldwide and 30% in the United States. Geogenic and anthropogenic contaminants can, however, compromise water quality, thus limiting groundwater availability. Reduction/oxidation (redox) processes and redox conditions affect groundwater quality by influencing the mobility and transport of common geogenic and anthropogenic contaminants. In the glacial aqu
Authors
Melinda L. Erickson, Sarah M. Elliott, Craig J. Brown, Paul Stackelberg, Katherine Marie Ransom, James E. Reddy
By
Water Resources Mission Area, California Water Science Center, Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center, New York Water Science Center
New 3-D models predict pH conditions throughout the glacial aquifer system

New 3-D models predict pH conditions throughout the glacial aquifer system

A new 3-D model predicts pH in groundwater at all depths across the 25-state span of the glacial aquifer system, reports an article by the USGS. The...

Read Article
Scientists Home in on Causes of High Radium Levels in Key Midwestern Aquifer

Scientists Home in on Causes of High Radium Levels in Key Midwestern Aquifer

Oxygen levels, dissolved minerals among factors responsible for high concentrations of radium in untreated water from aquifer that underlies six...

Read Article

Science and Products

link
A rainbow arc over a large-volume public-supply well

Groundwater Quality Research

Every day, millions of gallons of groundwater are pumped to supply drinking water for about 140 million people, almost one-half of the Nation’s population. Learn about the quality and availability of groundwater for drinking, where and why groundwater quality is degraded, and where groundwater quality is changing.
By
Water Resources Mission Area, National Water Quality Program, Colorado Water Science Center, Dakota Water Science Center, Wyoming-Montana Water Science Center
link

Groundwater Quality Research

Every day, millions of gallons of groundwater are pumped to supply drinking water for about 140 million people, almost one-half of the Nation’s population. Learn about the quality and availability of groundwater for drinking, where and why groundwater quality is degraded, and where groundwater quality is changing.
Learn More
link
Map of the Southwestern U.S. showing predicted concentrations of arsenic in shades of green (low) to orange (high)

Predicting Groundwater Quality in Unmonitored Areas

Groundwater provides nearly one-half of the Nation’s drinking water, and sustains the steady flow of streams and rivers and the ecological systems that depend on that flow. Unless we drill a well, how can we know the quality of the groundwater below? Learn about how the USGS is using sophisticated techniques to predict groundwater quality and view national maps of groundwater quality.
By
Water Resources Mission Area, National Water Quality Program
link

Predicting Groundwater Quality in Unmonitored Areas

Groundwater provides nearly one-half of the Nation’s drinking water, and sustains the steady flow of streams and rivers and the ecological systems that depend on that flow. Unless we drill a well, how can we know the quality of the groundwater below? Learn about how the USGS is using sophisticated techniques to predict groundwater quality and view national maps of groundwater quality.
Learn More
link
multicolored map of aquifers in the United States

National Water Quality Assessment Program -- Water-Quality Assessments of Principal Aquifers

A major focus of the NAWQA Program in its second decade (2002-2013) is on regional- and national-scale assessments of groundwater-quality status and trends in principal aquifers. The U.S. Geological Survey Office of Groundwater has identified 62 principal aquifers in the U.S. (U.S. Geological Survey, 2003). About 1/3 of the Nation's principal aquifers are the focus of water-quality assessments at
By
New York Water Science Center
link

National Water Quality Assessment Program -- Water-Quality Assessments of Principal Aquifers

A major focus of the NAWQA Program in its second decade (2002-2013) is on regional- and national-scale assessments of groundwater-quality status and trends in principal aquifers. The U.S. Geological Survey Office of Groundwater has identified 62 principal aquifers in the U.S. (U.S. Geological Survey, 2003). About 1/3 of the Nation's principal aquifers are the focus of water-quality assessments at
Learn More

Data for depth of groundwater used for drinking-water supplies in the United States

This data release includes grids representing the depth and thickness of drinking-water withdrawal zones, polygons of hydrogeologic settings, an inventory of sources of well construction data, and summaries of data comparisons used to assess the depth of groundwater used for drinking-water supplies in the United States. Well construction data sources are documented in Table1_DataSources.xlsx. Data
By
Water Resources Mission Area

Data for Machine Learning Predictions of Nitrate in Groundwater Used for Drinking Supply in the Conterminous United States

A three-dimensional extreme gradient boosting (XGB) machine learning model was developed to predict the distribution of nitrate in groundwater across the conterminous United States (CONUS). Nitrate was predicted at a 1-square-kilometer (km) resolution for two drinking water zones, each of variable depth, one for domestic supply and one for public supply. The model used measured nitrate concentrati
By
California Water Science Center

Data Release for Evaluation of Six Methods for Correcting Bias in Estimates from Ensemble Tree Machine Learning Regression Models

Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias: (1) empirical distribution matching (EDM); (2) regression of
By
Water Resources Mission Area

Data for machine learning predictions of pH in the glacial aquifer system, northern USA

A boosted regression tree (BRT) model was developed to predict pH conditions in three-dimensions throughout the glacial aquifer system (GLAC) of the contiguous United States using pH measurements in samples from 18,258 wells and predictor variables that represent aspects of the hydrogeologic setting. Model results indicate that the carbonate content of soils and aquifer materials strongly controls
By
Water Resources Mission Area

Data for Radium Mobility and the Age of Groundwater in Public-drinking-water Supplies from the Cambrian-Ordovician Aquifer System, North-Central USA

High radium (Ra) concentrations in potable portions of the Cambrian-Ordovician (C-O) aquifer system were investigated using water-quality data and environmental tracers ( 3H, 3Hetrit, SF6 , 14C and 4Herad) of groundwater age from 80 public-supply wells (PSWs). Groundwater ages were estimated by calibration of tracers to lumped parameter models and ranged from modern (1 Myr) in the most downgradien
By
Water Resources Mission Area, National Water Quality Program

Datasets from Groundwater-Quality Data from the National Water-Quality Assessment Project, January through December 2014 and Select Quality-Control Data from May 2012 through December 2014

Groundwater-quality data were collected from 559 wells as part of the National Water-Quality Assessment Project of the U.S. Geological Survey National Water-Quality Program from January through December 2014. The data were collected from four types of well networks: principal aquifer study networks, which assess the quality of groundwater used for public water supply; land-use study networks, whic
By
Water Resources Mission Area, National Water Quality Program
No results found.
Filter Total Items: 38

A spatial machine learning model developed from noisy data requires multiscale performance evaluation: Predicting depth to bedrock in the Delaware River Basin, USA

Spatial machine learning models can be developed from observations with substantial unexplainable variability, sometimes called ‘noise’. Traditional point-scale metrics (e.g., R2) alone can be misleading when evaluating these models. We present a multi-scale performance evaluation (MPE) using two additional scales (distributional and geostatistical). We apply the MPE framework to predictions of de
Authors
Phillip J. Goodling, Kenneth Belitz, Paul Stackelberg, Brandon J. Fleming
By
Water Resources Mission Area, National Water Quality Program, Maryland-Delaware-D.C. Water Science Center, Pennsylvania Water Science Center

Salinity and total dissolved solids measurements for natural waters: An overview and a new salinity method based on specific conductance and water type

The total concentration of dissolved constituents in water is routinely quantified by measurements of salinity or total dissolved solids (TDS). However, salinity and TDS are operationally defined by their analytical methods and are not equivalent for most waters. Furthermore, multiple methods are available to determine salinity and TDS, and these methods have inherent differences. TDS is defined a
Authors
R. Blaine McCleskey, Charles A. Cravotta, Matthew P. Miller, Fred D. Tillman, Paul Stackelberg, Katherine J. Knierim, Daniel Wise
By
Water Resources Mission Area, National Water Quality Program, Arizona Water Science Center, Lower Mississippi-Gulf Water Science Center, Oregon Water Science Center, Pennsylvania Water Science Center

Gross alpha-particle activity and high 226Ra concentrations do not correspond with high 210Po in the Atlantic and Gulf Coastal Plain aquifers of the United States

210Po, which is of human-health concern based on lifetime ingestion cancer risk, is indirectly regulated in drinking water through the U.S. Environmental Protection Agency’s gross alpha-particle activity (GAPA) maximum contaminant level of 15 pCi/L (picocuries per liter). This regulation requires independent measurement of 226Ra for samples exceeding the GAPA screening level of 5 pCi/L. There is n

Authors
Zoltan Szabo, Charles A. Cravotta, Paul Stackelberg, Kenneth Belitz
By
Water Resources Mission Area, New England Water Science Center, New Jersey Water Science Center, Pennsylvania Water Science Center

Quality of groundwater used for public supply in the continental United States: A comprehensive assessment

The presence of contaminants in a source water can constrain its suitability for drinking. The quality of groundwater used for public supply was assessed in 25 principal aquifers (PAs) that account for 84% of groundwater pumped for public supply in the U.S. (89.6 million people on a proportional basis). Each PA was sampled across its lateral extent using an equal-area grid, typically with 60 wells

Authors
Kenneth Belitz, Miranda S. Fram, Bruce D. Lindsey, Paul Stackelberg, Laura M. Bexfield, Tyler D. Johnson, Bryant Jurgens, James A. Kingsbury, Peter B. McMahon, Neil M. Dubrovsky
By
Water Resources Mission Area, California Water Science Center, Colorado Water Science Center, New Mexico Water Science Center

Mapped predictions of manganese and arsenic in an alluvial aquifer using boosted regression trees

Manganese (Mn) concentrations and the probability of arsenic (As) exceeding the drinking-water standard of 10 μg/L were predicted in the Mississippi River Valley alluvial aquifer (MRVA) using boosted regression trees (BRT). BRT, a type of ensemble-tree machine-learning model, were created using predictor variables that affect Mn and As distribution in groundwater. These variables included iron (Fe
Authors
Katherine J. Knierim, James A. Kingsbury, Kenneth Belitz, Paul Stackelberg, Burke J. Minsley, James R. Rigby
By
Water Resources Mission Area, New England Water Science Center, Lower Mississippi-Gulf Water Science Center, Geology, Geophysics, and Geochemistry Science Center

Relation between road-salt application and increasing radium concentrations in a low-pH aquifer, southern New Jersey

The Kirkwood–Cohansey aquifer in southern New Jersey is an important source of drinking-water supplies, but the availability of the resource is limited in some areas by high concentrations of radium, a potential carcinogen at elevated concentrations. Radium (226Ra plus 228Ra) concentrations from a network of 25 drinking-water wells showed a statistically significant increase over a decadal time sc

Authors
Bruce D. Lindsey, Charles A. Cravotta, Zoltan Szabo, Kenneth Belitz, Paul Stackelberg
By
Water Resources Mission Area, New Jersey Water Science Center, Pennsylvania Water Science Center

Depth of groundwater used for drinking-water supplies in the United States

Groundwater supplies 35 percent of drinking water in the United States. Mapping the quantity and quality of groundwater at the depths used for potable supplies requires an understanding of locational variation in the characteristics of drinking-water wells (depth and open interval). Typical depths of domestic- and public-drinking-water supply wells vary by and within aquifer across the United Stat
Authors
James R. Degnan, Leon J. Kauffman, Melinda L. Erickson, Kenneth Belitz, Paul E. Stackelberg
By
Water Resources Mission Area, New England Water Science Center

Machine learning predictions of nitrate in groundwater used for drinking supply in the conterminous United States

Groundwater is an important source of drinking water supplies in the conterminous United State (CONUS), and presence of high nitrate concentrations may limit usability of groundwater in some areas because of the potential negative health effects. Prediction of locations of high nitrate groundwater is needed to focus mitigation and relief efforts. A three-dimensional extreme gradient boosting (XGB)
Authors
Katherine Marie Ransom, Bernard T. Nolan, Paul Stackelberg, Kenneth Belitz, Miranda S. Fram
By
Water Resources Mission Area, California Water Science Center

Predicting regional fluoride concentrations at public and domestic supply depths in basin-fill aquifers of the western United States using a random forest model

A random forest regression (RFR) model was applied to over 12,000 wells with measured fluoride (F) concentrations in untreated groundwater to predict F concentrations at depths used for domestic and public supply in basin-fill aquifers of the western United States. The model relied on twenty-two regional-scale environmental and surficial predictor variables selected to represent factors known to c
Authors
Celia Z Rosecrans, Kenneth Belitz, Katherine Marie Ransom, Paul E. Stackelberg, Peter B. McMahon
By
Water Resources Mission Area, California Water Science Center, Colorado Water Science Center, New England Water Science Center, New York Water Science Center

Machine-learning predictions of high arsenic and high manganese at drinking water depths of the glacial aquifer system, northern continental United States

Globally, over 200 million people are chronically exposed to arsenic (As) and/or manganese (Mn) from drinking water. We used machine-learning (ML) boosted regression tree (BRT) models to predict high As (>10 μg/L) and Mn (>300 μg/L) in groundwater from the glacial aquifer system (GLAC), which spans 25 states in the northern United States and provides drinking water to 30 million people. Our BRT mo
Authors
Melinda L. Erickson, Sarah M. Elliott, Craig J. Brown, Paul Stackelberg, Katherine Marie Ransom, James E. Reddy, Charles A. Cravotta
By
Water Resources Mission Area, California Water Science Center, New England Water Science Center, New York Water Science Center, Pennsylvania Water Science Center, Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center

Evaluation of six methods for correcting bias in estimates from ensemble tree machine learning regression model

Ensemble-tree machine learning (ML) regression models can be prone to systematic bias: small values are overestimated and large values are underestimated. Additional bias can be introduced if the dependent variable is a transform of the original data. Six methods were evaluated for their ability to correct systematic and introduced bias. Method performance was evaluated using four case studies of
Authors
Kenneth Belitz, Paul Stackelberg
By
Water Resources Mission Area

Machine learning predicted redox conditions in the glacial aquifer system, northern continental United States

Groundwater supplies 50% of drinking water worldwide and 30% in the United States. Geogenic and anthropogenic contaminants can, however, compromise water quality, thus limiting groundwater availability. Reduction/oxidation (redox) processes and redox conditions affect groundwater quality by influencing the mobility and transport of common geogenic and anthropogenic contaminants. In the glacial aqu
Authors
Melinda L. Erickson, Sarah M. Elliott, Craig J. Brown, Paul Stackelberg, Katherine Marie Ransom, James E. Reddy
By
Water Resources Mission Area, California Water Science Center, Upper Midwest Environmental Sciences Center, Upper Midwest Water Science Center, New York Water Science Center
New 3-D models predict pH conditions throughout the glacial aquifer system

New 3-D models predict pH conditions throughout the glacial aquifer system

A new 3-D model predicts pH in groundwater at all depths across the 25-state span of the glacial aquifer system, reports an article by the USGS. The...

Read Article
Scientists Home in on Causes of High Radium Levels in Key Midwestern Aquifer

Scientists Home in on Causes of High Radium Levels in Key Midwestern Aquifer

Oxygen levels, dissolved minerals among factors responsible for high concentrations of radium in untreated water from aquifer that underlies six...

Read Article
Was this page helpful?