Streamflow patterns are influenced by natural processes, anthropogenic activities, and climatic variability (Haddeland and others, 2014). Human activities, such as land-use changes, urbanization, deforestation, agricultural practices, and water resource development projects, can significantly impact hydrologic processes and streamflow (Foley and others, 2005). The data release presented here supports a study investigating the impacts of human activities and climate variability on hydrologic alterations in the Mobile River and Perdido River basins of Alabama using modeled daily streamflow data (Isik and others, 2025). The research employs a machine learning approach, specifically Cubist models (Quinlan, 1992), to quantify and predict changes in flow duration curves (FDCs) under both historical (1980–2009) and future climate scenarios. The future scenarios are based on Representative Concentration Pathways (RCP) 4.5 and 8.5 for two future periods: 1980–2069 and 1980–2099 (LaFontaine and Riley, 2023). Pre-alteration and post-alteration flow duration curves were used to calculate the net change across the proposed scenarios. Cubist models were developed for both basins to predict hydrologic alterations and to identify important basin characteristics. This data release includes one shapefile of the Hydrologic Unit Code level 12 (HUC12) pour points in the Mobile River and Perdido River basins (U.S. Geological Survey, 2019), a model input file containing computed net change percentages using flow duration curves, a model structure file detailing the number of input parameters, rules, and committees, and six model output files: observed net change percentages for the full, high, mean, and low flow regimes, variable importance data, observed net change (%) versus Cubist model-predicted net change (%) at HUC12 pour points, model performance metrics, Cubist model-predicted net change (%) for future scenarios, and p-values comparing baseline and future predictions. The input datasets used in this study include estimated daily streamflows (Robinson and others, 2020), climate variables (Crowley-Ornelas and others, 2019a; PDSI, 2023; LaFontaine and Riley, 2023), basin and stream characteristics (Crowley-Ornelas and others, 2019b; Robinson and others, 2019), land-use and land-cover data (USEPA, 2020), demographic data (Manson and others, 2021), and water use data (U.S. Geological Survey, 2022).
