Artificial neural networks (ANNs) were developed for accurately predicting potentiometric surface elevations (monitoring well water level elevations) in a semiconfined glacial sand and gravel aquifer under variable state, pumping extraction, and climate conditions. ANNs "learn" the system behavior of interest by processing representative data patterns through a mathematical structure analogous to the human brain. In this study, the ANNs used the initial water level measurements, production well extractions, and climate conditions to predict the final water level elevations 30 d into the future at two monitoring wells. A sensitivity analysis was conducted with the ANNs that quantified the importance of the various input predictor variables on final water level elevations. Unlike traditional physical-based models, ANNs do not require explicit characterization of the physical system and related physical data. Accordingly, ANN predictions were made on the basis of more easily quantifiable, measured variables, rather than physical model input parameters and conditions. This study demonstrates that ANNs can provide both excellent prediction capability and valuable sensitivity analyses, which can result in more appropriate ground water management strategies.

No abstract

The sophisticated algorithms we use to process, analyze, and interpret geophysical data automate tasks we used to do by hand, transform data into domains where patterns are more obvious, and allow us to calculate quantities where we used to rely on intuition or back‐of‐envelope estimates. But, the crux of the exploration problem is still interpretation—associating abstract patterns with geologic formations of economic value. Artificial neural networks are able to couple the speed and efficiency of the computer with the pattern recognition and association capabilities of the brain to aid the exploration process. The key concept to understand in the application of neural network technology is that they should not be used as an artificial intelligence tool to replace a human interpreter; rather, neural networks are an intelligence amplification toolkit that allows the interpreter to focus on the important information. More than 102 neural network papers have been published by SEG since 1988, and more than 550 neural network papers pertaining to any aspect of geophysics were published in that same time period. Neural network applications in exploration geophysics can generally be divided into two eras. The focus through 1994 was largely on learning what neural networks could do with different data sets, and how to prepare data for them and analyze the results. Networks were usually trained with synthetic data and then tested with field data. The second era, from 1995 to the present, has focused on some specific application areas such as reservoir characterization. The current emphasis is to integrate neural networks within a comprehensive interpretation scheme instead of as a stand‐alone application. Neural network technology has helped us turn data into information by allowing us to find nontrivial correlations between geophysical data and petrophysical properties; relate detailed changes in wavelet morphology to small‐scale changes in lithology; and find features in the wavelets that allow us to locate first breaks, track horizons, identify gas chimneys, or trace faults; and attenuate multiples. As the science and engineering of data acquisition progresses, neural networks will play an increasingly vital role in helping us find relevant information in the vast streams of data under the constraints of lower costs, less time, and fewer people.