Predictive Modeling of CO<sub>2</sub> Adsorption in Metal–Organic Frameworks Using Hybrid Machine Learning Approaches
Bibliographic record
Abstract
Carbon dioxide (CO 2 ) emissions from industrial and energy sources lead to global warming and drive climate change. To address the critical challenge of rising atmospheric CO 2 levels, strategies such as CO 2 capture are essential for limiting emissions and mitigating environmental impact. Among various materials, metal–organic frameworks (MOFs) have emerged as highly promising and effective adsorbents for CO 2 capture, offering high selectivity and capacity. This study evaluates the performance of various machine learning (ML) models, including artificial neural network-particle swarm optimization (ANN-PSO), coupled simulated annealing-least squares support vector machine (CSA-LSSVM), and adaptive neuro-fuzzy inference system (ANFIS), in predicting the CO 2 capture capacity of MOFs. Additionally, gene expression programming (GEP) is utilized to find a mathematical correlation between CO 2 capture capacity and key operating variables such as pressure and surface area. The model development considered the input variables: temperature, pressure, surface area, pore volume, and enthalpy. Performance metrics such as mean square error (MSE) and coefficient of determination ( R 2 ) are calculated for the training and testing phases to assess the model accuracy and reliability. Among the evaluated models, CSA-LSSVM exhibits the best performance, achieving R 2 values of 0.971 and 0.915 and MSE values of 0.0025 and 0.0034 for the training and testing phases, respectively. Sensitivity analysis conducted on the CSA-LSSVM model reveals that pressure significantly influences CO 2 capture capacity, followed by surface area. The results demonstrate the potential of ML models, particularly CSA-LSSVM, as powerful tools for predicting and optimizing the performance of MOFs in CO 2 capture, considering cost, energy efficiency, and environmental sustainability.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.001 | 0.000 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".