# Methane sorption modeling on Methane sorption dataset n=199 (test)

Source: [Methane sorption modeling on Methane sorption dataset n=199 (test)](<https://www.sota2.com/research/sota/methane-sorption-modeling-on-methane-sorption-dataset-n-199-test>)

Collection index: [llms.txt](<https://www.sota2.com/research/llms.txt>)

Data updated: 2026-04-16T08:28:49.736Z

Evaluation of models for Methane sorption modeling using the test split of the Methane sorption dataset (n=199). Metrics include R^2, Calibrated UQ assessment, Physics adherence, and Training Cost.

A research result applies to its stated dataset, split, metric and evaluation configuration. Compare like-for-like settings, preserve the metric's unit and direction, and distinguish paper-reported results from independent reproduction. The best result recorded here is not a claim of exhaustive, current global coverage.

| Scope | Recorded value |
| --- | --- |
| Task | Methane sorption modeling |
| Dataset (including any stated split) | Methane sorption dataset n=199 (test) |
| Metric | R^2 |
| Unit | SCALAR |
| Direction | Higher is better |
| Results loaded | 3 of 3 |
| Coverage | All results currently returned for this benchmark |

Evaluation settings may differ between results. The original papers and recorded configurations are needed to establish comparability. A shared metric name alone does not establish an identical protocol.

## Metrics

- [R^2](<https://www.sota2.com/research/sota/methane-sorption-modeling-on-methane-sorption-dataset-n-199-test.md?metric=R%5E2>): Higher is better; unit: SCALAR.

- [Calibrated Uncertainty Quantification](<https://www.sota2.com/research/sota/methane-sorption-modeling-on-methane-sorption-dataset-n-199-test.md?metric=Calibrated%20Uncertainty%20Quantification>): Lower is better; unit: SCALAR.

- [Physics Adherence](<https://www.sota2.com/research/sota/methane-sorption-modeling-on-methane-sorption-dataset-n-199-test.md?metric=Physics%20Adherence>): Higher is better; unit: SCALAR.

- [Training Cost](<https://www.sota2.com/research/sota/methane-sorption-modeling-on-methane-sorption-dataset-n-199-test.md?metric=Training%20Cost>): Lower is better; unit: TIME.

## Recorded results

| Method | R^2 | Result date | Report paper |
| --- | --- | --- | --- |
| Transfer-learned PINN | 0.932 | Not recorded | 69e06d307d0172140ec7cc0f |
| Random Forest | 0.87 | Not recorded | 69e06d307d0172140ec7cc0f |
| Classical isotherms | 0.29 | Not recorded | 69e06d307d0172140ec7cc0f |

### Transfer-learned PINN

R^2: 0.932. Result ID: 69e09dc047f34ce924c9d749.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d307d0172140ec7cc0f.md>)

[Method origin paper](<https://www.sota2.com/research/paper/69e06d307d0172140ec7cc0f.md>)

Recorded evaluation configuration: {"Model Class":"Transfer-learned PINN"}. This record does not assert independent reproduction.

### Random Forest

R^2: 0.87. Result ID: 69e09dc047f34ce924c9d748.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d307d0172140ec7cc0f.md>)

Recorded evaluation configuration: {"Model Class":"Random Forest"}. This record does not assert independent reproduction.

### Classical isotherms

R^2: 0.29. Result ID: 69e09dc047f34ce924c9d747.

[Reporting paper](<https://www.sota2.com/research/paper/69e06d307d0172140ec7cc0f.md>)

Recorded evaluation configuration: {"Model Class":"Classical isotherms"}. This record does not assert independent reproduction.

Page 1 of 1. This is an index page, not the full collection.
