Investigating the impacts of climate and hydrological disturbances on river water quality using a data-driven framework

About the project

Floods, droughts, and heat waves are projected to increase over the next few decades due to climate change. These disturbances can cause declining stream flows and worsen water quality by increasing salt, nutrient, and contaminant concentrations, which will have direct consequences for human and ecosystem health. There is a pressing need to understand how the  flows and water quality in rivers will respond and be resilient to new  disturbance regimes.  This project uses a novel, data synthesis and analysis framework to investigate the impacts to stream flows and water quality caused by climate-driven disturbances. The  goal is to determine how the intensity, duration, and frequency of disturbance events will affect rivers over time at impacted locations and further downstream, across watersheds with different characteristics of geomorphology, soil properties, climate, land use, and land cover. This will be achieved using a data-driven framework comprising  statistical analyses and machine learning methods to identify patterns and explanatory variables for changes following a disturbance event. This will result in better predictions of  river flows and water quality, characterize watershed resistance and resilience to disturbance, and lay the foundation for capability to generate and analyze integrated watershed data.

 Project Objectives

Disturbance Impacts and River Resilience

Impacts of heat waves, floods, and droughts on river water quality and river resilience to disturbance

Multi-scale Machine Learning Models for Water Quality Predictions

Machine learning models for predicting stream temperature, salinity and dissolved oxygen at multiple scales in space and time

iNAIADS Capability Development

iNtegration, Artificial Intelligence and Analytical Data Services (iNAIADS) framework for water quality predictions

Collaborative Activities and Open Science

Building and engaging collaborations across federal agencies, academia, and industry using an Open Science by Design philosophy

In the news

Recent paper featured in 200+ news outlets

Our Nature paper on amplfied rainfall extremes in a warming climate has received significant media attention.

Image credit: Jenny Nuss, LBNL

DOE AI4ESP report released 

Members of ths project contributed to the DOE AI4ESP report that laid the roadmap for using big data and AI/ML to accelerate Earth system predictability. To learn more, read the DOE blog post and news article.

Image credit: Diana Swantek, LBNL

Nagamoto wins AGU Award

Emily Nagamoto, a former student assistant won an outstanding student paper award for her presentation on drought impacts in the Upper Colorado River Basin at the 2022 American Geophysical Union Fall meeting


Contact [] to get more information on the project

This project is funded by a U.S. Department of Energy, Office of Science, Biological and Environmental Research Early Career Award.