Monitor the energy and carbon emissions of process-based models: ProcessC
Bibliographic record
Abstract
• ProcessC , a multi-platform energy usage and carbon emission tracking program for process-based models was developed. • Machine-learning models consumed and released less energy (115-fold) and less carbon emissions (29397-fold) compared to the RZ-SHAW in simulating winter drainage. • Different modelling approaches result in drastically varying energy usage and carbon emissions; future studies should consider energy efficiency. • Reducing model training or calibration time and optimizing computation locations are crucial for sustainable modelling. Sustainable modelling to reduce carbon emissions from heavy computations is being adopted in machine learning communities. However, this concept has not been considered in process-based model communities, with carbon emissions rarely monitored and reported. This study developed ProcessC, a multi-platform program to monitor energy usage and carbon emissions in process-based models’ simulations. ProcessC was tested through a case study involving a process-based model, RZ-SHAW, for winter artificial drainage simulation. Results indicated that the RZ-SHAW model consumed 115 times more energy and released 29,397 times more carbon emissions compared to machine learning (ML) models for the winter artificial drainage simulation. The study suggests deploying computing systems in regions with low grid carbon intensity, choosing energy-efficient systems, and reducing simulation time as potential solutions for a more carbon-sustainable modelling. The findings from the current study urge the process-based community to commence considering and reporting carbon emissions in future modelling studies.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".