Investigating hydrologic alteration in the Pearl and Pascagoula River basins using rule-based model trees. (May 2023)

• Record Type: Journal Article
• Authors: Roland, Victor L.; Crowley-Ornelas, Elena; Rodgers, Kirk
• Is Part Of: Environmental modelling & software. Volume 163(2023)
• Publication Date: 2023-05
• Subjects: cubist -- Machine learning -- Model tree -- Hydrologic alteration; Environmental monitoring -- Computer programs -- Periodicals; Ecology -- Computer simulation -- Periodicals; Digital computer simulation -- Periodicals; Computer software -- Periodicals; Environmental Monitoring -- Periodicals; Computer Simulation -- Periodicals; Environnement -- Surveillance -- Logiciels -- Périodiques; Écologie -- Simulation, Méthodes de -- Périodiques; Simulation par ordinateur -- Périodiques; Logiciels -- Périodiques; Computer software; Digital computer simulation; Ecology -- Computer simulation; Environmental monitoring -- Computer programs; Periodicals; Electronic journals; 363.70015118
• DOI: 10.1016/j.envsoft.2023.105667
• Languages: English
• ISSNs: 1364-8152

Abstract

Abstract: Anthropogenic hydrologic alteration threatens the health of riverine ecosystems. Machine learning algorithms that employ the use of model trees to predict hydrologic alteration are underrepresented in related literature. This study assesses hydrologic alteration in the Pearl and Pascagoula River basins using modeled daily streamflow. Hydrologic alteration was determined by hypothesis testing and the computation of the net change across 60 years. Cubist models were developed for both basins to predict hydrologic alteration and to identify important basin characteristics. Results from net change and the hypothesis test indicated the basins were essentially identical with respect to the amount of hydrologic alteration. Cubist models for the basins successfully made accurate predictions of hydrologic alteration and demonstrated that the importance of basin geomorphology and land cover on alteration differed in both basins. The results of the study demonstrate the feasibility of model trees in assessing hydrologic alteration. Highlights: Hydrologic alteration in the Pearl and Pascagoula River basins was assessed using 60 years of modeled streamflow data. Analyses indicated similar amounts of hydrologic alteration in the Pearl (26%) and Pascagoula (22%) basins. Cubist models developed for each basin successfully predicted patterns of hydrologic alteration. Human alteration of stream channels influenced hydrologic alteration greatest in the Pearl River basin cubist model. Land cover change influenced alteration greatest in the Pascagoula River basin cubist model.