A neurosimulation tool for predicting performance in enhanced coalbed methane and CO₂ sequestration projects

One of the more important environmental issues is the increase in atmospheric carbon dioxide (CO₂) concentration resulting from anthropogenic sources. The CO₂ sequestration process includes capturing, separation and storage of carbon dioxide, and targets a potential solution mitigating the amount of CO₂ in the atmosphere. This work focuses on the last component of the aforementioned sequestration process, storage of CO₂. Coal seams are chosen as potential repositories because there are several advantages where the sequestration costs can be offset in various ways. The purpose of this study is to develop a tool for the practicing engineer to predict the important performance indicators that are critical in CO₂ storage projects in coal seams. The neuro-simulation methodology coupling the hard computing protocols with the soft computing protocols is used. PSU-COALCOMP, a compositional coalbed methane reservoir simulator (hard computing protocol), is used to generate the necessary training data sets utilized in the training of the artificial neural networks (soft computing protocol) that are developed in this study. The tested neural network predictions are found to be accurate and sufficiently precise to establish confidence in the tool. Accordingly, the developed neural network can be used to screen thousands of possible scenarios of operational conditions in the optimization of the coal sequestration project design parameters in few seconds without going through intensive numerical simulations.