An Efficient Crop Yield Prediction Framework Using Hybrid Machine Learning Model
Bibliographic record
Abstract
Given India's vast expanse and dense population, the prediction of agricultural yields is crucial for ensuring food security. The task, however, is complex due to the influence of a multitude of factors, such as agricultural practices, environmental conditions, and technological advancements. Existing machine learning (ML) models face difficulties due to the quality and variability of data, model overfitting, intricate model structures, insufficient feature engineering, and temporal dependencies. Therefore, a robust and efficient model that addresses these challenges is imperative. In this study, an investigation was conducted using five prevalent ML algorithms -Random Forest (RF), XGBoost, Decision Tree (DT), Support Vector Machine (SVM), and Linear Regression (LR)on a crop prediction dataset sourced from Kaggle. Algorithms that exhibited the highest coefficient of determination (R ) were selected to construct a hybrid model for aggregate prediction. Results demonstrated that the proposed hybrid model, encompassing DT, XGBoost, and RF, surpassed individual classifiers in terms of R score and outperformed the existing models, achieving an accuracy of 98.6%. This provides a robust and efficient framework for crop yield predictions. Consequently, a user-friendly tool, 'Crop Yield Predictor', was developed, rendering the model accessible and practical for on-ground applications in agriculture. This tool effectively translates complex data and algorithms into actionable insights, bridging the gap between advanced machine learning techniques and practical agricultural applications.
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 | 0.001 |
| 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) | 0.001 | 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".