Modeling temporal variation of soil acidity after the application of liming materials
Bibliographic record
Abstract
Soil acidification is a natural phenomenon that human activity can accelerate or manage. Acid soils limit plant growth by reducing nutrient availability and causing aluminum toxicity, significantly reducing crop production. Liming has proven efficient for increasing crop yield on acidic soils. Knowledge is required on the effect of liming on the soil pH dynamics to find the suitable material, application rate, timing, and method. The objective of this study was to develop a prediction model of soil pH temporal variations after lime application using data from the literature. A database was built from research results extracted from 16 scientific papers that provided data on soil acidity changes over time under different liming treatments. Machine learning (ML) was used to predict soil pH dynamics from eight predictive parameters: rate of application, time since application, neutralizing value (CCE), grind fineness (D50), pH measurement depth, soil acidity (pH prior to liming), the type of solution used for pH measurement (water or CaCl 2 ) and the soil:solution ratio used to measure pH. Since soil pH fluctuates with seasons, all pH values were expressed as difference between the actual pH value and that of an unlimed control (ΔpH). The Random Forest (RF) algorithm was tested to predict ΔpH over time. On testing, we obtained an R 2 between measured and predicted ΔpH values of 0.881 and an RMSE of 0.230. These results are excellent, considering the heterogeneity in soils, liming materials, and pedoclimatic conditions found in the 16 papers. The primary factors influencing ΔpH, ranked by their impact are application rate, time elapsed post-application, and lime characteristics including its grind fineness and neutralizing value. • Random Forest robustly predicts soil pH change over time following lime application. • The predictors are: rate, neutralizing value, particle size, depth, and initial pH. • The model predicts that, on average, lime increases soil pH for 82 weeks. • Machine learning models are promising tools in managing liming 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 | 0.001 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| 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".