THE IMPACT OF CLIMATE CHANGE ON PRECIPITATION IN ARKANSAS

Data collected from US EPA website, where trends in pollutant concentrations, atmospheric deposition, and ecological effects were monitored due to changes in air pollutant emissions 2000 – 2020 in Caddo Valley, AR. 

Partial Least Square (PLS) model and Principal Component Regression (PCR) were developed using 25 explanatory variables to predict precipitation. The goodness-of-fit of  predictive models were assessed using calibration coefficients of determination and Root Mean Square Error of Prediction (RMSEP). By using the four PLS components, the and RMSEP for the predictive PLS model were 0.85 and 22.77, respectively.  By using the four PCR components, the and RMSEP for the predictive PCR model were 0.87 and 25.82, respectively, indicating that both the PLS and the PCR models fit very well.