Predicting high resolution total phosphorus concentrations for soils of the Upper Mississippi River Basin using machine learning

Authors: DOLPH, CHRISTINE - University Of Minnesota; CHO, SE JONG - Us Geological Survey (USGS); FINLAY, JACQUES - University Of Minnesota; HANSEN, AMY - University Of Kansas; Dalzell, Brent

Submitted to: Biogeochemistry
Publication Type: Peer Reviewed Journal
Publication Acceptance Date: 2/8/2023
Publication Date: 3/28/2023
Citation: Dolph, C., Cho, S., Finlay, J., Hansen, A., Dalzell, B.J. 2023. Predicting high resolution total phosphorus concentrations for soils of the Upper Mississippi River Basin using machine learning. Biogeochemistry. 163:289–310. https://doi.org/10.1007/s10533-023-01029-8.
DOI: https://doi.org/10.1007/s10533-023-01029-8

Interpretive Summary: Soil phosphorus is important for crop production, but it can cause water quality problems in streams and rivers. In order to manage agricultural lands in a way that can benefit both crop production and protect water quality, it is important to have a good understanding of where soil phosphorus can be found in the landscape. We used large existing datasets of soil phosphorus to develop a model that predicts soil phosphorus at a 100 m grid scale for the Upper Mississippi River Basin, USA. This research will benefit soil and water conservation professionals by providing a more accurate estimate of the distribution of soil phosphorus across the Upper Mississippi River Basin.

Technical Abstract: The spatial distribution of soil phosphorus (P) is important to both biogeochemical processes and the management of agricultural landscapes, where it is critical for both crop production and conservation planning. Recent advances in the availability of large environmental datasets together with big data analytical tools like machine learning have created opportunities for evaluating and predicting spatial patterns in complex environmental variables like soil P. Here, we apply a random forest machine learning model to publicly available soil P datasets together with nearly 300 geospatial attributes summarizing aspects of soil type, land cover, land use, topography, nutrient inputs, and climate to predict total soil P at a 100m grid scale for the Upper Mississippi River Basin (UMRB), USA. The UMRB is one of the most intensively farmed regions in the world and is characterized by widespread water quality degradation arising from P-associated eutrophication. At the regional scale represented by our model, the variables with the greatest comparative importance for predicting soil P included a combination of soil sample depth, land use/land cover, underlying soil physical and geochemical properties, landscape features (such as slope, elevation and proximity to the stream network), nutrient inputs, and climate-related factors. An important product of this research is a fine-scale (100 m) raster data layer of predicted total soil P values for the UMRB for public use. This dataset can be used to improve conservation planning and modeling efforts to improve water quality in the region.