Machine learning-based modelling for geologic CO2 storage in deep saline aquifers. Case study of bunter sandstone in Southern North Sea

Abstract

This paper presents a machine learning (ML) model designed to speed up the appraisal of geologic CO2 storage sites by predicting the effectiveness in trapping and accommodating CO2 in saline aquifers. Considering the urgency of de-risking as much geologic CO2 storage resources as possible to help with CO2 emission reduction Paris’ goal, ML-based reservoir modelling has been documented as proper tool when a faster, good approximate, and less expensive approach is needed to surrogate multiple assessments of storage sites traditionally performed by long-timeframe and multi-stage geologic CO2 storage numerical modelling approach. In this paper, a case study is presented. It consisted of a dataset comprised of six geologic aquifer parameters (CO2 residual saturation, horizontal permeability, vertical to horizontal permeability ratio, porosity, brine salinity, and CO2 flow rate) and elapsed time as input data, and as output data the CO2 trapping mechanism indices (Solubility Trapping Index, Residual Trapping Index, and Structural Trapping Index) along with the dynamic storage capacity (CO2 injected volume). Such dataset was used to train and test the artificial neural network (ANN) model. The dataset was generated from thousands of post-processed numerical realizations at several injection periods by applying design of experiment using a synthetic aquifer model derived from the Bunter Sandstone Closure 36 aquifer numerical model, from the Southern North Sea. The ANN architecture designed in Python consisted of 3 hidden layers and 40 nodes and its performance was assessed using the coefficient of determination (R2) and root mean squared error (RMSE). The ANN performance showed accuracies (R2) for training and testing with 96% and 95% of precision respectively. Practical application of the ANN model was successfully implemented to CO2 storage aquifer sites selected from CO2Stored® database which lacking numerical models (Bunter Closure 3, 9, 35, and 40), obtaining at the end of 100-years injection case a Structural, Residual, and Solubility Trapping Index averaging 83%, 11%, and 6% respectively, with low variation coefficient indicating that trapping indices were predicted properly because aquifers selected for ANN model application have similar structures (dome-like shape) and reservoir properties. In addition, CO2 injected volume predictions for 100-years injection case were ranging from 397 to 456 million ton (Mt) totalling 2.1 giga ton (Gt) of potential storage capacity which represents 70% of total theoretical volumetric capacity. These results show the significant impact to accelerate geologic CO2 storage sites assessment by implementing ML-based modelling to preliminary de-risking groups of saline aquifers and reasonably consider them technically feasible CO2 storage sites in UK.