PNNL

The Science

The hyporheic zone beneath and alongside a riverbed, where groundwater and surface water mix, is a key element of river corridors. This mixing provides and controls transport of dissolved nutrients, contaminants, and microbes. Modeling flow and transport in this region is challenging due to the natural variation and dynamic influences from water, sediment, and microbial processes. Researchers at the U.S. Department of Energy’s Pacific Northwest National Laboratory (PNNL) used machine learning to predict sediment grain size along the Hanford Reach of the Columbia River. Their resulting substrate size maps filled in gaps and improved spatial coverage and resolution by learning existing but unevenly sampled measurements.  

The Impact

Substrate size is a proxy for permeability. Spatial mapping of grain-size distribution along this river area enables a better understanding of the hydrological variation and complexity in the system. It also provides information useful for modeling transport properties, such as hydrologic exchange flows and residence times.   

Summary

Measurements of sediment grain size cover about 70% of the entire Hanford Reach, but the spatial resolution is too coarse to infer continuity or variation. Bathymetry measurements and hydrodynamic simulations of this area provide higher spatial resolution data. The research team wanted to use machine learning to link this higher-resolution information to predicted substrate size so they could develop a spatial map that captures the natural sediment variation along the 70-km reach.

The researchers trained the machine learning model with data from more than 13,000 samples of dominant substrate sizes previously collected along the reach. They also included measurements of bathymetry, slope, and aspect, as well as simulated hydrodynamic properties such as water depth, velocity, and river bottom shear stress. The researchers used a bagging-based machine learning technique, called Random Forest, to develop unbiased predictions with minimal over-fitting. The resulting model accurately predicted the measured substrate size and could be applied to a grid of 5-10m resolution across Hanford Reach. These algorithms enable gap filling and refining when mapping spatial grain-size distribution by learning predictive relationships between substrate size and multiple types of complementary information.

Contact

Huiying Ren
Pacific Northwest National Laboratory
huiying.ren@pnnl.gov

Funding

This research was supported by the U.S. Department of Energy, Office of Biological and Environmental Research (BER), as part of BER’s Subsurface Biogeochemical Research Program (SBR). This contribution originates from the SBR Scientific Focus Area at Pacific Northwest National Laboratory.