Speakers
Victor Roland II
Victor Roland is a hydrologist with the U.S. Geological Survey Lower Mississippi-Gulf Water Science Center. Victor specializes in surface water modeling with a focus on watershed hydrology, water quality, and hydrologic alteration. He is the lead SPARROW modeler for the Southeast United States, and he leads hydrologic alteration and flow accounting studies for the LMG-RESTORE studies program.
Presentation Description
Modeling hydrologic alteration in Northern Gulf Coast river basinsIn recent history, interest in the conservation of Mississippi’s riverine ecosystems has grown as people have become more knowledgeable about the functions of these habitats. Anthropogenic hydrologic alteration is a direct threat to the health of these ecosystems because it often triggers a range of complex and negative effects on the biological, physical, chemical, and hydrologic characteristics of impacted waters. Understanding important factors and drivers of hydrologic alteration is essential to planning effective conservation action plans. Moreover, the use of machine learning to identify these drivers is underrepresented in hydrologic alteration literature. This study explores the application of machine learning to predicting hydrologic alteration and identifying important predictors of hydrologic alteration in the Pearl and Pascagoula River Basins in Mississippi. Modeled daily streamflow for 12-digit hydrologic unit code (HUC12) watershed pour points were used to compute the net change in streamflow volume and to conduct a confidence interval hypothesis test across pre- and post-alteration periods between 1950 and 2009. Cubist models were developed for each basin to predict the p value of the confidence interval test as a function of the net change and a range of other physical and meteorological watershed parameters. Analysis of the net change and confidence interval test results indicated the basins had similar amounts of altered watersheds. Moreover, patterns of alteration tended to coincide with the locations of densely populated areas, dams, and areas with substantial land cover change in both basins. The cubist models developed for the basins produced accurate predictions of the confidence interval test results in most HUC12 watersheds. The importance of model predictors demonstrated differences in the relationships between basin geomorphology, land cover, and hydrologic alteration between the basins. Results demonstrate the significant potential of the cubist algorithm in hydrologic alteration assessments. More broadly, this study outlines how machine learning and other data-driven approaches can help identify sources of hydrologic alteration and prioritize potential solutions.