Basin characteristics, climate data, and R-scripts to determine hydrologic alteration in the Mississippi Alluvial Plain

To identify the degree of hydrologic alteration of streams in the Mississippi Alluvial Plain (MAP), we used random forest (RF) regression methods (Breiman, 2001) to model the relation between six selected streamflow characteristics and explanatory variables (such as drainage area, precipitation, soils, and other watershed characteristics). RFs were chosen for this study because they have been proven to be more robust and accurate than traditional linear regression methods (Carlisle and others, 2010; Lawler and others, 2006; Prasad and others, 2006; Cutler and others, 2007). Estimated expected monthly mean streamflow from the RF models were compared to observed monthly mean streamflow at 68 sites located within the MAP and two adjacent Level III Ecoregions. We also used an additional eight sites to compare estimated expected streamflow, generated by the RF models, and observed streamflow for characteristics of flood frequency, high streamflow duration, number of zero streamflow days, frequency of low-pulse spells, and high streamflow discharge. This data release includes the explanatory variables (input data) used in the random-forest models (Breiman, 2001) to determine expected flows (output data) at 76 sites in the MAP. The geospatial dataset contains the point and watershed features for the sites used in the analyses. These data were used to support the findings in the journal article titled "Quantifying Hydrologic Alteration in an Area Lacking Current Reference Conditions--The Mississippi Alluvial Plain of the South-Central U.S." by Hart and Breaker (2018). References: Breiman, L. 2001, Random forests: Machine Learning, v. 45, p.5-32. Carlisle, D.M., Falcone, J., Wolock, D.M., Meador, M.R., and Norris, R.H., 2010, Predicting the natural streamflow regime: models for assessing hydrological alteration in streams: River Research and Applications, v. 26, p.118-136. Cutler, D.R., Edwards, T.C. Jr, Beard, K.H., Cutler, A., Hess, K.T., Gibson, J., Lawler, J.J., 2007, Random forests for classification in ecology: Ecology v. 88, p.2783-2792. Hart, R.M., and Breaker, B.K., 2019, Quantifying hydrologic alteration in an area lacking current reference conditions--The Mississippi Alluvial plain of the south?central United States. River Res Applic. 35 (6):553-565. Lawler, J.J., White, D., Neilson, R.P., and Blaustein, A.R., 2006, Predicting climate-induced range shifts: model differences and model reliability: Global Climate Change Biology v. 12, p.1568-1584. Prasad, A.M., Iverson, L.R., Liaw, A., 2006, Newer classification and regression tree techniques: bagging and random forests for ecological prediction: Ecosystems v. 9, p.181-199.