Evaluation of Some Supervised Machine Learning Techniques for the Prediction of Soil Macro-Nutrients for Cash Crop Production
Bibliographic record
Abstract
The prediction of soil macro-nutrients level is critical for optimizing cash crop production, ensuring both economic viability and sustainable agricultural practices.Researchers have used several machine learning models to predict the nutrients for the good yield of the crops; however, the supply and demand based on nutrients that provide the good yield cannot be met.Based on this shortfall, this study aims to evaluate some machine learning techniques for predicting soil nutrient for cash crop production.The dataset was sourced from "Nigeria Soils Data" on Africa Geoportal and includes soil samples collected from various locations across Nigeria.The data were preprocessed to handle missing values, feature engineering to transform spectral data using Principal Component Analysis (PCA), normalization of data features, and the splitting of the dataset.Each model was trained on the preprocessed data and assessed using Mean Absolute Error (MAE), Mean Squared Error (MSE), Root Mean Squared Error (RMSE), and R² score.The performance evaluation results for MAE, MSE, R² , RMSE under Nitrogen are: 0.029078, 0.002053, 0.710939, 0.045315 respectively.The result emphasizes the superior performance of Random Forest (RF) as it outperforms the remaining models within the metrics of MAE, MSE, R² , RMSE even after employing approaches to improve individual model performance through bagging methods.These insights can help agricultural stakeholders determine which approaches to employ, leading to enhance crop production and promote more eco-friendly agricultural methods.
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 | 0.004 | 0.006 |
| 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 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| 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".