Data-driven surrogate modelling and multi-variable optimization of trickle bed and packed bubble column reactors for CO2 capture via enhanced weathering

Abstract

Enhanced weathering (EW) of minerals could potentially absorb atmospheric CO2 at gigaton scale per year and store it as bicarbonate and carbonate in the ocean. However, this process must be accelerated by engineered reactors, in which optimal reaction conditions maximise the CO2 capture rate and minimise the energy and water consumption. In this work, trickle beds (TBs) and packed bubble columns (PBCs), operated with fresh water and CO2 -rich flue gas, are chosen as typical chemical reactors to perform the EW-based CO2 capture. We firstly develop experimentally validated physics-based mechanistic models then generate data to train data-driven surrogate models to achieve rapid prediction of performance and multi-variable optimization. Two surrogate models, namely, response surface methodology (RSM) and extended adaptive hybrid functions (E-AHF), are developed and compared, in which the effect of five design variables on three objective functions are investigated. Results show that the R2 for the prediction of CO2 capture rate (CR) and water consumption (WC) through RSM and E-AHF is higher than 0.84. For TB reactors, in particular, the calculated R2 is higher than 0.96. The prediction accuracy of energy consumption (EC) through the RSM approach is, however, relatively poor (R2 ∼ 0.79), but is improved by using the E-AHF surrogate model, increasing to R2 ∼ 0.89. The developed data-driven surrogate model can rapidly predict the performance indicators of TB and PBC reactors without solving complex mechanistic models consisting of many partial differential equations. After optimization using the surrogate models, improvements were achieved in the objectives for TB and PBC reactors as follows: CR increased by 37.8 % and 13.1 %, EC reduced by 37.4 % and 23.8 %, and WC reduced by 12.5 % and 40.7 %, respectively.