ABSTRACT:

The resources contain grid averaged arsenic concentration (mean concentrations) and predictor variables in Jorhat and Golaghat districts of Assam. GPS location has included error terms for privacy. Basic workflow random forest model in python environment is also provided. Final model was determined through random 10-fold cross-validation. Final model was used in the prediction of arsenic probability in unknown locations. We have also checked spatial cross-validation. The results were found to be consistent and confirmed the overall distribution of high/moderate/low-risk zones for arsenic in groundwater.

Some of the original point data can be downloaded from: https://www.hydroshare.org/resource/bbe23dfacab647568a18dc338114d6d7/
reference: https://agupubs.onlinelibrary.wiley.com/doi/full/10.1029/2017WR022485

ABSTRACT:

This is the data we used for our article published in AGU GeoHealth.