Performance comparison of physical process-based and data-driven models: a case study on the Edwards Aquifer, USA
- PDF / 2,095,660 Bytes
- 13 Pages / 595.276 x 790.866 pts Page_size
- 102 Downloads / 221 Views
PAPER
Performance comparison of physical process-based and data-driven models: a case study on the Edwards Aquifer, USA Andi Zhang 1 & James Winterle 1 & Changbing Yang 1 Received: 4 December 2019 / Accepted: 20 April 2020 # Springer-Verlag GmbH Germany, part of Springer Nature 2020
Abstract Physical process-based groundwater flow models are the major tools for studying fluid-flow behavior and for simulating the hydrological responses of water levels and spring discharge to human- and/or nature-induced triggers such as pumping and recharge. Such models are built with deep understanding of the physical processes and are based on geological models, developed by integrating data from geology, geophysics, and geochemistry. However, data-driven models can be built with limited data, eliminating the need for a detailed understanding of the physics. In this research, a data-driven model is built for simulating hydraulic responses (both groundwater levels and spring discharges) in a complex groundwater flow system of the Edwards Aquifer in Central Texas, USA, with the recurrent neural network (RNN) technique. The model is first trained and validated with the observation data of four targets—water levels from two index wells, and spring flow rates from San Marcos and Comal springs—from 2001 through 2015. The model is then used to predict the hydrological responses for the drought of record (1947–1958). The performance of the RNN model for the training, validation and prediction period is then quantitatively compared to that of the physical process-based MODFLOW model in terms of four statistical measures. The statistical measures suggest that the RNN model performs almost as well as the MODFLOW model. With further improvements, a data-driven model may be a surrogate to (or integrate with) a physical process-based model for simulating hydrological responses in the Edwards Aquifer. Keywords Numerical modeling . Groundwater management . Physical process-based model . Recurrent neural network . USA
Introduction The Edwards Aquifer is one of the largest and most important aquifers in North America, providing water resources for agricultural, industrial, municipal, ecological, and recreational uses in the region (Hunt et al. 2016; Scanlon et al. 2003; Sharp and Banner 1997). It is of particular importance to understand the hydrogeologic processes that control the distribution and availability of groundwater in the Edwards Aquifer for optimal resource management to ensure that present and future needs are satisfied (Todd Engineers 1999). Various studies have been conducted for understanding hydrogeological conditions of the Edwards Aquifer in the past (Barker and Ardis 1992; Campana and Mahin 1985; Collins * Changbing Yang [email protected] 1
Edwards Aquifer Authority, 900 E Quincy, San Antonio, TX 78215, USA
and Hovorka 1997; Hunt et al. 2016; Kuniansky and Spangler 2017; Land and Prezbindowski 1981; Lindgren et al. 2004; McCarl et al. 1999; Pearson Jr. and Rettman 1976; Puente 1975). One of the methods that has been extensiv
Data Loading...