Deep Learning-based Regional Plant Type Recommendation System for Enhancing Agricultural Productivity
Bibliographic record
Abstract
Recommendation systems serve as pivotal components in the agricultural domain, significantly contributing to global economic growth.One particular application, the recommendation of region-specific plant types, can mitigate losses in unfavorable conditions and optimize yields when growth conditions are ideal.However, accurately identifying the specific parameters of a field location and the diverse characteristics of plant types can pose a challenge.Deep learning has demonstrated efficacy as a predictive model within recommender systems, including those for plant type matching.However, building such models necessitates the identification of optimal solutions, taking into account the complexities of the problem scope and the unique characteristics of the domain.This paper introduces the development of a deep learning model architecture designed to recommend plant types best suited to specific regions.The model was constructed based on an extension of the Convolutional Neural Network (CNN), a deep learning model recognized for its robust pattern recognition capabilities, making it suitable for classification tasks.It has the ability to discern patterns from datasets with a limited number of input features, thus making it an ideal choice for a plant type recommendation system.The Adagrad optimizer was employed for its advantage of partitioning the learning rate into smaller units, which significantly impacts the speed of the training process.Evaluation of this model was undertaken in a two-step process.First, the learning model's performance was assessed using a confusion matrix.Subsequently, the model's functionality was evaluated using real data from a city in Indonesia, investigating its ability to provide relevant recommendations based on the city's unique contextual characteristics.The results demonstrated a substantial accuracy level of 90%, underscoring the model's potential to effectively recommend suitable plant types for specific regional contexts.
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 | 0.000 | 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 | 0.000 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
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".