Kenneth Belitz, 2023 Birdsall-Dreiss Lecturer
When
4/25/2023: EVENT CANCELED DUE TO SPEAKER'S TRAVEL ISSUES
(in-person & remote) The 2023 Birdsall-Dreiss Lecturer, Kenneth Belitz, USGS, will present Old problems, new approach: Applications of Ensemble-Tree Machine Learning to Hydrogeology.
STUDENTS: Contact the weekly colloquium coordinator, Bo Guo, if you would like to meet the speaker after his presentation.
Abstract
Ensemble tree modeling is a machine learning method well suited for representing complex non-linear phenomena. As such, ensemble tree modeling can be applied to a wide range of questions in hydrogeology, including questions related to hydrogeologic mapping. Some questions are problems of regression in which one seeks an estimate of a continuous variable. For example, what is the depth to the water table across a region of interest? Other questions are problems of classification. For example, across a region of interest and over a range of depths, is groundwater oxic or reduced?
The U.S. Geological Survey National Water Quality Assessment project (NAWQA) has used ensemble tree methods to address questions related to groundwater quality at regional and national scales. Some of our models evaluate the three-dimensional distribution of factors that can affect groundwater quality, such as pH, redox, and groundwater age. In turn, the modeled factors were used in subsequent models to map the three-dimensional distribution of contaminant concentrations. In our experience, ensemble tree models are a powerful tool for answering difficult questions. They can be used as a complement to process-based modeling and to make predictions at scales that preclude the use of process-based approaches.
Bio
Dr. Kenneth Belitz is a Research Hydrologist in the Water Resources Mission Area of the United States Geological Survey (USGS). He received his B.A. in Geology from Binghamton University, and Ph.D. in hydrogeology from Stanford University in 1985. His dissertation examined the evolution of large-scale groundwater flow in the Denver Basin under the direction of Dr. John Bredehoeft. Throughout his career, Ken has simultaneously pursued two fronts: improving the fundamental hydrogeologic framework of the conterminous U.S., and employing numerical models – and, most recently, machine learning – in novel ways to better understand regional-scale groundwater quality and to project our current understanding into unsampled space.
Upon completing his Ph.D., Ken joined the USGS California Water Science Center, where he constructed a model of the western San Joaquin Valley; this model and its underlying framework became the gold standard and basis for subsequent models of this critically important aquifer system. From 1990-1997 Ken taught at Dartmouth University and Queens College of New York, before returning to the USGS in 1998 to lead an interdisciplinary team studying the water quality of the intensely urbanized Santa Ana River Basin as part of the USGS National Water Quality Assessment (NAWQA) Program. In this capacity, Ken began to develop a systematic approach to large-scale groundwater-quality assessment founded on a deep understanding of groundwater flow. From 2003-2012, Ken up-scaled this approach to obtain representative, unbiased water-quality data for the groundwater resources of the entire state of California. This work yielded new insights into the processes behind the spatial distribution of critical contaminants including perchlorate, pharmaceuticals, and hexavalent chrome. Ken then led the design and implementation of the groundwater component for the USGS NAWQA Program’s third decade. The design characterizes water quality in the most productive principal aquifers, cumulatively representing 85 percent of the Nation’s GW-derived drinking-water supplies. Ken’s work has given us an unbiased and surprising perspective on the relative risks of geogenic and anthropogenic contaminants, while evaluating constituents not previously sampled for at the national scale. Ken is a GSA Fellow and has received numerous USGS awards for his publications and service.