Embed-to-Control-Based Deep-Learning Surrogate for Robust Nonlinearly Constrained Life-Cycle Production Optimization: A Realistic Deepwater Application

Summary This paper presents a realistic deepwater application of a deep-learning-based reservoir surrogate model in forecasting reservoir performance (via the prediction of state variables and well outputs) and nonlinearly constrained production optimization under geological uncertainty by utilizing an efficient gradient-based method. The reservoir surrogate model is based on the multi-model Embed-to-control Observe (E2CO) architecture, consisting of four blocks of neural networks: encoder, transition, transition output, and decoder. In this work, the surrogate model is coupled with the powerful stochastic-gradient-based line-search sequential quadratic programming (LS-SQP) workflow to handle robust production optimization in the presence of nonlinear state constraints. Five realizations of the synthetic realistic Reservoir X model with different channelized heterogeneous permeability distributions permeability under waterflooding are used for showcasing the prediction and optimization performances of the deep-learning-based framework. The results from this framework are directly and quantitatively compared with the ones simulated using a commercial high-fidelity reservoir simulator.