A Deep Learning Optimization Framework for Geothermal Energy Production Based on Carbon Dioxide

Abstract

CO2 plume geothermal technology (CPG) has been developed in recent years by several companies. The technology aims to utilize CO2 stored in saline aquifers to produce geothermal energy. CPG is different from conventional geothermal concepts. Here, the feedstock utilizes CO2 as a carrier fluid through which heat is extracted from the subsurface reservoir. Furthermore, the system does not necessarily rely on shallow natural hydrothermal locations but can utilize a conventional sedimentary basis. At last, CPG can still harvest energy in low-temperature environments that are currently not suitable for conventional geothermal extraction. We present a new deep learning optimization framework for the maximization of power generation from a CPG system. The framework utilizes an adapted N-BEATS approach. The approach is based on a stack of ensembled feedforward networks that are also stacked by interconnecting backcast and forecast links. The advantages of the framework are its flexibility with respect to different input parameters and various forecastable time series. This is particularly important for CPG to easily capture variations in the temporal dynamics and temperature responses across the various CO2 injection and production wells. We evaluated the framework on a simulated CO2 storage reservoir based in the Taranaki basin in New Zealand. The Taranaki basin has been well studied for CO2 storage, given the presence of a large saline aquifer that may be well suitable for both CO2 storage and CPG energy production. We simulated 3.5 years of CO2 injection and production for geothermal energy production as input to the N-BEATS framework. The training performance of the network was strong, and the model's performance was then evaluated on subsequent two years of energy production. The deep learning framework is then integrated into a global optimization framework to optimize energy production while adapting CO2 injection. The new deep learning N-BEATS optimization framework for CPG power generation represents an innovative way to enhance energy generation from CO2 storage reservoirs providing a sustainable way to minimize carbon footprint while delivering energy.

Integrating Capacity and Efficiency for Optimal Hydrogen Storage Site Selection in Saline Aquifers

“…The XGBoost and random forest algorithms showed high prediction performance with R 2 > 0.95. However, the studies of Katterbauer et al 34 and Thanh et al 35 did not focus on H 2 storage capacity and efficiency. In contrast, extensive analyses 36−41 have investigated the uncertainty quantification and performance optimization of CO 2 sequestration using ROMs.…”

“…The optimal H 2 storage schedule was presented by optimizing the H 2 recovery and NPV. Katterbauer et al 34 presented a framework to determine the metabolism process of subsurface microorganisms in undergound H 2 storage. The random forest algorithm was applied to conduct multiclass classification.…”