Leah L. Rogers

OPTIMIZATION OF GROUNDWATER REMEDIATION USING ARTIFICIAL NEURAL NETWORKS WITH PARALLEL SOLUTE TRANSPORT MODELING

A new approach to nonlinear groundwater management methodology is presented which optimizes aquifer remediation with the aid of artificial neural networks (ANNs). The methodology allows solute transport simulations, usually the main computational component of management models, to be run in parallel. The ANN technology, inspired by neurobiological theories of massive interconnection and parallelism, has been successfully applied to a variety of optimization problems. In this new approach, optimal management solutions are found by (1) first training an ANN to predict the outcome of the flow and transport code, and (2) then using the trained ANN to search through many pumping realizations to find an optimal one for successful remediation. The behavior of complex groundwater scenarios with spatially variable transport parameters and multiple contaminant plumes is simulated with a two-dimensional hybrid finite-difference/finite-element flow and transport code. The flow and transport code develops the set of examples upon which the network is trained. The input of the ANN characterizes the different realizations of pumping, with each input indicating the pumping level of a well. The output is capable of characterizing the objectives and constraints of the optimization, such as attainment of regulatory goals, value of cost functions and cleanup time, and mass of contaminant removal. The supervised learning algorithm of back propagation was used to train the network. The conjugate gradient method and weight elimination procedures are used to speed convergence and improve performance, respectively. Once trained, the ANN begins a search through various realizations of pumping patterns to determine whether or not they will be successful. The search is directed by a simple genetic algorithm. The resulting management solutions are consistent with those resulting from a more conventional optimization technique, which combines solute transport modeling and nonlinear programming with a quasi-Newton search. The results suggest that the ANN approach has the following advantages over the conventional technique for the test remediations: more independence of the flow and transport code from the optimization, greater influence of hydrogeologic insight, and less computational burden due to the potential for parallel processing of the flow and transport simulations and the ability to “recycle” these simulations. The ANN performance was observed upon variation of the problem formulation, network architecture, and learning algorithm.

Optimal field-scale groundwater remediation using neural networks and the genetic algorithm.

We present a new approach for field-scale nonlinear management of groundwater remediation. First, an artificial neural network (ANN) is trained to predict the outcome of a groundwater transport simulation. Then a genetic algorithm (GA) searches through possible pumping realizations, evaluating the fitness of each with a prediction from the trained ANN. Traditional approaches rely on optimization algorithms requiring sequential calls of the groundwater transport simulation. Our approach processes the transport simulations in parallel and ``recycles`` the knowledge base of these simulations, greatly reducing the computational and real-time burden, often the primary impediment to developing field-scale management models. We present results from a Superfund site suggesting that such management techniques can reduce cleanup costs by over a hundred million dollars.

Applying soft computing methods to improve the computational tractability of a subsurface simulation–optimization problem

Abstract Formal optimization strategies normally evaluate hundreds or even thousands of scenarios in the course of searching for the optimal solution to a given management question. This process is extremely time-consuming when numeric simulators of the subsurface are used to predict the efficacy of a scenario. One solution is to train artificial neural networks (ANNs) to stand in for the simulator during the course of searches directed by some optimization technique such as the genetic algorithm (GA) or simulated annealing (SA). The networks are trained from a representative sample of simulations, which forms a re-useable knowledge base of information for addressing many different management questions. These concepts were applied to a water flood project at BPs Pompano Field. The management problem was to locate the combination of 1–4 injection locations that would maximize Pompanos simple net profit over the next 7 years. Using a standard industry reservoir simulator, a knowledge base of 550 simulations sampling different combinations of 25 potential injection locations was created. The knowledge base was first queried to answer questions concerning optimal scenarios for maximizing simple net profit over 3 and 7 years. The answers indicated that a considerable increase in profits might be achieved by expanding from an approach to injection depending solely on converting existing producers to one involving the drilling of three to four new injectors, despite the increased capital expenses. Improved answers were obtained when the knowledge base was used as a source of examples for training and testing ANNs. ANNs were trained to predict peak injection volumes and volumes of produced oil and gas at 3 and 7 years after the commencement of injection. The rapid estimates of these quantities provided by the ANNs were fed into net profit calculations, which in turn were used by a GA to evaluate the effectiveness of different well-field scenarios. The expanded space of solutions explored by the GA contained new scenarios that exceeded the net profits of the best scenarios found by simply querying the knowledge base. To evaluate the impact of prediction errors on the quality of solutions, the best scenarios obtained in searches where ANNs predicted oil and gas production were compared with the best scenarios found when the reservoir simulator itself generated those predictions during the course of search. Despite the several thousand CPU hours required to complete the simulator-based searches, the resulting best scenarios failed to match the best scenarios uncovered by the ANN-based searches. Lastly, results obtained from ANN-based searches directed by the GA were compared with ANN-based searches employing an SA algorithm. The best scenarios generated by both search techniques were virtually identical.

Chapter 18 Applying soft computing methods to improve the computational tractability of a subsurface simulation-optimization problem

Abstract Formal optimization strategies normally evaluate hundreds or even thousands of scenarios in the course of searching for the optimal solution to a given management question. This process is extremely time-consuming when numeric simulators of the subsurface are used to predict the efficacy of a scenario. One solution is to train artificial neural networks (ANNs) to stand in for the simulator during the course of searches directed by some optimization technique such as the genetic algorithm (GA) or simulated annealing (SA). The networks are trained from a representative sample of simulations, which forms a re-useable knowledge base of information for addressing many different management questions. These concepts were applied to a water flood project at BPs Pompano Field. The management problem was to locate the combination of 1-4 injection locations which would maximize Pompanos simple net profit over the next seven years. Using a standard industry reservoir simulator, a knowledge base of 550 simulations sampling different combinations of 25 potential injection locations was created. The knowledge base was first queried to answer questions concerning optimal scenarios for maximizing simple net profit over three and seven years. The answers indicated that a considerable increase in profits might be achieved by expanding from an approach to injection depending solely on converting existing producers to one involving the drilling of three to four new injectors, despite the increased capital expenses. Improved answers were obtained when the knowledge base was used as a source of examples for training and testing ANNs. ANNs were trained to predict peak injection volumes and volumes of produced oil and gas at three and seven years after the commencement of injection. The rapid estimates of these quantities provided by the ANNs were fed into net profit calculations, which in turn were used by a GA to evaluate the effectiveness of different well-field scenarios. The expanded space of solutions explored by the GA contained new scenarios which exceeded the net profits of the best scenarios found by simply querying the knowledge base. To evaluate the impact of prediction errors on the quality of solutions, the best scenarios obtained in searches where ANNs predicted oil and gas production were compared with the best scenarios found when the reservoir simulator itself generated those predictions during the course of search. Despite the several thousand CPU hours required to complete the simulator-based searches, the resulting best scenarios failed to match the best scenarios uncovered by the ANN-based searches. Lastly, results obtained from ANN-based searches directed by the GA were compared with ANN-based searches employing an SA algorithm. The best scenarios generated by both search techniques were virtually identical.

Optimal Groundwater Remediation Using Artificial Neural Networks

The significant cost and complexity of groundwater remediation and water resources management has encouraged integration of optimization techniques with groundwater flow and transport modeling to search for efficient groundwater management strategies. This integration of methodologies has often been referred to as simulationmanagement modeling or simulation-optimization groundwater management modeling. The values of the objective function and constraints of the optimization problem are calculated by the groundwater flow and transport models run as a submodel of the optimization driver. In the area of remediation, example objectives could be minimizing costs or maximizing contaminant mass removed; constraints might be avoiding dewatering or a total pumping volume limit. A general groundwater management model will use optimization techniques to search among almost infinite numbers of treatment or control strategies possibilities for ones that meet management goals while minimizing cost. The main advantage of applying these mathematical tools to decision-making problems is that they are less restricted by human imagination than case-by-case comparisons. As the number of competing engineering, economic, and environmental planning objectives and constraints increases, it becomes difficult for human planners to track complex interactions and select a manageable set of promising scenarios for examination. Using optimization techniques, the search can range over all possible combinations of variables, locating strategies whose effectiveness is not always obvious to planners.

Solute Transport Modelling of Organic Compounds in Groundwater West of the Lawrence Livermore National Laboratory, Livermore, California

The principal objective of this study is to determine optimal remedial action for the volatile organic plume contaminating groundwater in the complex heterogeneous alluvial sediments under the west boundary of the Lawrence Livermore National Laboratory (LLNL) site and vicinity. Simulation management modelling, a combination of solute transport simulation with linear optimization of well locations and pumpage rates, will be done to determine appropriate remedial action. The study will be unique in its application and verification of simulation management modelling of groundwater contaminant transport in an extremely complex geologic regime with poorly understood contaminant sources. Presented here are results from the initial phase of the study, the solute transport modelling of the organic compounds. The finite element groundwater flow and contaminant transport code SUTRA was used in areal steady-state simulations.