ABSTRACT:

This repository includes all the Python programming language scripts developed for long-term groundwater level projections in Finney County in southwest Kansas under 5 different well retirement plans and 2 climate scenarios (wet and dry). The Scikit-learn library is used to construct the RF model and the ArcPy package is utilized for all geospatial and geostatistical analyses.
The repository also includes all required data for running the scripts. All the scripts and data are uploaded as a single 7z file.
To project future GWLs for each retirement plan, initially change the home folder pathname in all 3 included python scripts, namely "all_calculations_in_arcpy.py", "projecting_water_level_variations_2017_2099_using_RF.py", and "removing_redundant_rasters.py". Then, run the "projecting_water_level_variations_2017_2099_using_RF.py" file.

ABSTRACT:

This repository includes all the Python programming language scripts developed for long-term groundwater level projections using the random forests (RF) method in combination with ordinary kriging in Finney County in southwest Kansas under various climate scenarios. The Scikit-learn library is used to construct the RF model and the ArcPy package is utilized for all geospatial and geostatistical analyses.
The climate scenarios are developed based on the downscaled climatic data of 20 GCMs for the RCPs of 4.5 and 8.5. The repository also includes the required data for running the scripts. All the scripts and data are uploaded as a single 7z file.
To project future GWLs, initially change the home folder pathname in all 3 included python scripts, namely "all_calculations_in_arcpy.py", "projecting_water_level_variations_2017_2099_using_RF.py", and "removing_redundant_rasters.py". Then, run the "projecting_water_level_variations_2017_2099_using_RF.py" file.

ABSTRACT:

This repository includes all the Python programming language scripts developed for long-term groundwater level (GWL) projections in Finney County in southwest Kansas, using the combination of the random forests (RF) and ordinary kriging techniques. The repository also includes all required data for running the scripts. GWL projections are done under various climate and management scenarios. The Scikit-learn library is used to construct the RF model and the ArcPy package is utilized for all geospatial and geostatistical analyses. All the scripts and data for GWL projections in different climate scenarios and under status quo management conditions are stored as a resource named "RF_GWL_projections_climate" and all the scripts and data pertinent to GWL forecasts in different well retirement plans and under the wet and dry climate conditions are stored as a resource named "RF_GWL_projections_management" (see Collection Contents). In each resource, all the files are uploaded as a single 7z file.