Hydrologic soil groups play an important role in the determination of surface runoff, which, in turn, is crucial for soil and water conservation efforts. Traditionally, placement of soil into appropriate hydrologic groups is based on the judgement of soil scientists, primarily relying on their interpretation of guidelines published by regional or national agencies. As a result, large-scale mapping of hydrologic soil groups results in widespread inconsistencies and inaccuracies. This paper presents an application of machine learning for classification of soil into hydrologic groups. Based on features such as percentages of sand, silt and clay, and the value of saturated hydraulic conductivity, machine learning models were trained to classify soil into four hydrologic groups. The results of the classification obtained using algorithms such as k-Nearest Neighbors, Support Vector Machine with Gaussian Kernel, Decision Trees, Classification Bagged Ensembles and TreeBagger (Random Forest) were compared to those obtained using estimation based on soil texture. The performance of these models was compared and evaluated using per-class metrics and micro- and macro-averages. Overall, performance metrics related to kNN, Decision Tree and TreeBagger exceeded those for SVM-Gaussian Kernel and Classification Bagged Ensemble. Among the four hydrologic groups, it was noticed that group B had the highest rate of false positives.
She received the B.E. degree in Telecommunication Engineering from Visveswaraiah Technological University (VTU), India in 2007 and Ph.D. from Old Dominion University, Norfolk, VA in 2012. Her research interests span the areas of Wireless Communication, Internet of Things (IoT), Optimization using Game Theory, and Engineering Education Research. She is a member of the IEEE and ASEE, a technical program committee member for IEEE Globecom, ICC, ICCCN and VTC conferences, and a reviewer for several international journals and conferences.
Teaching at the college level since 1994 and in engineering since 2004, and previously an associate professor of EE at Oregon Tech, Vurkaç earned his Ph.D. in Electrical and Computer Engineering in December 2011 at Portland State University with research at the confluence of machine learning, information theory, and mathematical music theory. His current research areas are transfer learning and evolutionary computation in image processing, music perception in computational neuroscience, ensemble learning, engineering education, multivariate modeling in mathematical music theory, and music information retrieval.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.