Skip to main content
Dryad logo

Random forest climatic modeling of agricultural insurance loss across the inland Pacific Northwest region of the United States

Citation

Seamon, Erich et al. (2022), Random forest climatic modeling of agricultural insurance loss across the inland Pacific Northwest region of the United States, Dryad, Dataset, https://doi.org/10.5061/dryad.h9w0vt4kh

Abstract

We compared climatic relationships to insurance loss across the inland Pacific Northwest region of the United States, using a design matrix methodology, to identify optimum temporal windows for climate variables by county in relationship to wheat insurance loss due to drought. The results of our temporal window construction for water availability variables (precipitation, temperature, evapotranspiration, and the Palmer drought severity index [PDSI]) identified spatial patterns across the study area that aligned with regional climate patterns, particularly with regards to drought-prone counties of eastern Washington. Using these optimum time-lagged correlational relationships between insurance loss and individual climate variables, along with commodity pricing, we constructed a regression-based random forest model for insurance loss prediction and evaluation of climatic feature importance. Our cross-validated model results indicated that PDSI was the most important factor in predicting total seasonal wheat/drought insurance loss, with wheat pricing and potential evapotranspiration having noted contributions. Our overall regional model had a R2 of 0.49 and a RMSE of $30.8 million. Model performance typically underestimated annual losses, with moderate spatial variability in terms of performance between counties.

Methods

The attached zip file contains the full GitHub repository, which includes data, the supplemental code, and an output HTML. The GitHub repository can be additionally viewed at: http://github.com/erichseamon/RFclimatePaper

Data provided include climate correlations, climate matrices, climatological data taken from Abatzoglou's (2013) GRIDMET daily downscaled climate data, as well as wheat commodity pricing data at a county level.

The user should only need to download the attached zip file, decompress it, and then run the Rmd from the location of the data download. The Rmd contains code to expand any zip files, and load data needed to re-generate the Rmd output (which is included as an HTML file).

Usage Notes

The user should only need to download the attached zip file, decompress it, and then run the Rmd from the location of the data download. The Rmd contains code to expand any zip files, and load data needed to re-generate the Rmd output (which is included as an HTML file). The user may choose to simply look at the generated HTML file without re-running the .Rmd, if preferred.

Funding

National Oceanic and Atmospheric Administration, Award: NA15OAR4310145

National Institute of General Medical Sciences, Award: P20GM104420