Elena Crowley-Ornelas
Kirk D. Rodgers
Victor L. Roland II
2023
<div id="abstracts" class="Abstracts u-font-gulliver text-s"><div id="abs0010" class="abstract author" lang="en"><div id="abssec0010"><p id="abspara0010"><span>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 </span>streamflow<span>. 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.</span></p></div></div></div>
application/pdf
10.1016/j.envsoft.2023.105667
en
Elsevier
Investigating hydrologic alteration in the Pearl and Pascagoula River basins using rule-based model trees
article