• >Home
  • >News
  • >2022
  • >February
  • >Dr. Gonzalez-Pinzon and collaborators receive NSF award to develop global database and machine-learning-informed solute transport model

Dr. Gonzalez-Pinzon and collaborators receive NSF award to develop global database and machine-learning-informed solute transport model

February 7, 2022

In 2013, Dr. Gonzalez-Pinzon and collaborators published a manuscript titled “Scaling and predicting solute transport processes in streams”, where they investigated scaling of conservative solute transport using temporal moment analysis of 98 tracer experiments (384 breakthrough curves) conducted in 44 streams located on five continents. Those experiments spanned 7 orders of magnitude in discharge, 5 orders of magnitude in longitudinal scale, and sampled different environments—forested headwater streams, hyporheic zones, desert streams, major rivers, and urban manmade channels. The meta-analysis of those data revealed that the current solute transport theory was inconsistent with experimental data and suggested that a revised theory of solute transport was needed.

In 2019, Dr. Gonzalez-Pinzon started collaborating with colleagues from Washington State University, the University of Illinois at Urbana Champaign, and New Mexico State University to tackle the challenges noted in the 2013 publication. Late in 2021, the team received an NSF award from the Hydrologic Sciences program to fund this collaborative research over the next three years ($ 821,567 to team, $254,245 to González-Pinzón). The goals of this project are to develop a comprehensive, global database of river tracer testing data for open sharing with the scientific community, and to develop and test a novel generalized model of solute transport in river corridors. The activities proposed center around the construction of a community-available, large database of tracer tests performed in streams and rivers worldwide and its use as curricula for machine learning of model properties. The team will perform congruent data analytics to identify correlations among key variables of both river and tracer test properties, treating breakthrough curves not individually but in the tracer test sets in which they are measured. The uncertainty in experimentally measured solute concentrations will be formally addressed and used to describe model predictive power. The models selected for evaluation range from the classical transient storage model to a new model designed to address the hypothesis that residence time in the river and in the hyporheic zone both matter to exchange fluxes. Both conventional inverse modeling and machine learning tools will be applied in dual model calibration tasks, bringing uniquely powerful physics-informed neural networks to bear on this challenging problem.

From a practical standpoint, improving our capacity to scale and predict solute transport processes in streams and rivers is essential to informing stakeholders and water users how anthropogenic disturbances to fluvial networks (e.g., discharges from cities and farms, spills, and post-wildfire runoff) combine with natural physical and biochemical processes to control the fate and transport of solutes, including key nutrients for life (e.g., carbon and nitrogen) and hazardous pollutants (e.g., heavy metals and emerging contaminants).