Machine learning models predict organic fertilization effects on soil organic carbon stocks in global agroecosystems
Bibliographic record
Abstract
Organic fertilizers are more environmentally friendly than traditional fertilizers and affect the dynamics of soil organic carbon (SOC) stocks; however, the impact of organic fertilizers on SOC dynamics in global agroecosystems is poorly understood. Here, we use machine learning (ML) models to investigate the effect of organic fertilizer application on SOC stocks under different agronomic practices and environmental conditions on a global scale. Three tree-based ML algorithms—Random Forest (RF), Gradient Boosting Regressor (GBR), and Extreme Gradient Boosting (XGB)—were compared for their efficacy in predicting organic fertilizer effects on SOC stocks in global agroecosystems. Results indicate that GBR outperformed RF and XGB, with the GBR model producing higher training and testing R 2 values (0.96 and 0.73, respectively) and lower training and testing root mean square errors (2.1 and 2.23, respectively). Applied organic fertilizer dosage, cumulative organic fertilizer application amount, and soil bulk density were key factors affecting SOC stocks in global agroecosystems. Climate factors such as mean annual temperature and mean annual precipitation also significantly influenced the prediction of SOC stocks in global agroecosystems. This study underscores the potential of ML models in unravelling complex factors affecting SOC stocks in global agroecosystems. Future research should prioritize long-term monitoring to enhance our understanding of factors affecting SOC stocks in agroecosystems and inform sustainable soil management practices.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.000 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 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 teacher head, 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".