Estimation of CO2 adsorption in high capacity metal−organic frameworks: Applications to greenhouse gas control

Abstract

In recent decades, adsorption of high amounts of carbon dioxide (CO2) in metal-organic frameworks (MOFs) has recived attention and is studied broadly. As a main principle, most scientists have accepted that CO2 can be capured by MOFs in order to prevent atmosphere from green-house gas emissions. In the present work, the potential of Particle Swarm Optimization Adaptive Neuro-Fuzzy Inference System (PSO-ANFIS), Differential Evolution-ANFIS (DE-ANFIS), Radial Basis Function Artificial Neural Network (RBF-ANN) and Least Square Support Vector Machine (LSSVM) to estimate CO2 uptake in 13 different MOFs, as a function of the operational pressure (P) supplemented with the property of MOFs was investigated. The inputs of the models are temperature, pressure, surface area and pore volume of MOFs. An extensive databank containing 506 data gathered from the literature was used for models development. The obtained %AARD values for the developed models are 10.05, 36.6, 35.51 and 8.17 for LSSVM, PSO-ANFIS, DE-ANFIS and RBF models, respectively.The sensitivity analysis demonstrated that operational pressure and pore volume of MOFs are the most effective parameters on CO2 adsorbtion by MOFs. It is found that LSSVM model is an outstanding tool for estimating adsorption of CO2 in comparison with other models. The LSSVM model presents a decent method for estimating CO2 adsorption in the studied MOFs, which is straightforward, capable and cost-efficient.