eXplainable expert systems for potato tuber yield prediction in the Maritime provinces of Canada
Bibliographic record
Abstract
The potato crop is vital to the economy of Canada’s Maritime provinces. Prince Edward Island (PEI) and New Brunswick (NB) contribute significantly to Canadian potato production and gross domestic product (GDP). Estimating potato tuber yields helps farmers to make informed decisions for sustainable and profitable farming. This study investigated fluctuations in tuber yield based on 30 soil properties gathered over four seasons through experimental trials. An emerging eXplainable high-dimensional feature vote-based ensemble framework explained with SHAP (SHapley Additive exPlanations) tool was employed to estimate potato tuber yield accurately. In order to develop the model, the most influential feature was first filtered using the Boruta-SHAP feature selection. Afterwards, the most deserved combinations (four scenarios) were ascertained using the best subset regression (BSR) integrated with two Multi-Criteria Decision-Making (MCDM), namely Weighted Aggregated Sum Product Assessment (WASPAS) and Multi-Objective Optimization methods were adopted based on the Ratio Analysis (MOORA). To estimate potato tuber yield, we adopted a novel explainable ensemble machine learning model, called VOTE-LGCB, that combines voted Categorical Boosting and the Light Gradient-Boosting Machine framework. We evaluated our approach against Least Absolute Shrinkage and Selection Operator (LASSO) regression, elastic net regression, Extra Tree, classical LightGBM, and classical CatBoost baselines. Six metric performances such as correlation coefficient (R), root mean square error (RMSE), and reliability were implemented to validate the multi-process ML models. All the metrics were singularized using WASPAS and MOORA to determine the best input combination related to each model separately. We found that the VOTE-LGCB-Combo 3 outperformed baseline methods (R = 0.8958, RMSE = 5088.5087, Reliability = 93.7500, WASPAS = 0.00023, and MOORA = 0.3788). Moisture content was identified as the most significant feature, followed by the Normalized Difference Vegetation Index (NDVI). The modeling framework we advance can be used as a reliable simulation system for various aspects of agricultural production systems that involve high-dimensional features.
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 | 0.006 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.000 |
| Scholarly communication | 0.001 | 0.000 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.002 | 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".