IoT Based Real Time Crop Recommendation System Using Random Forest Classifier
Bibliographic record
Abstract
Agriculture continues to be a pillar of worldwide food security and economic stability but farmers often face challenges making an appropriate crop selection as environmental conditions constantly shift. This research presents an adaptive crop suggestion system that combines IoT-based field sensors with machine learning to support more informed decision-making in precision agriculture. As opposed to conventional methods based on stationary soil data, our system continuously evaluates real-time environmental factors—temperature, humidity, and precipitation (provided through OpenWeatherMap API)—in addition to IoT-measured soil factors like NPK content and pH. Using a trained Random Forest model with a large crop dataset, the system reaches a prediction accuracy of 98.9%, well above the performance of traditional methods. The hardware design integrates NPK and pH sensors with an Arduino microcontroller for unconstrained data capture, while the software infrastructure includes a Flask-driven backend and a user-friendly React-based interface for farmer usability. By integrating real-time sensor feeds with strong machine learning, our architecture provides actionable crop recommendations, minimizing resource wastages, optimizing yields, and promoting sustainable agriculture. This project fills key shortcomings in static crop models, presenting a scalable and adaptive tool for contemporary agronomy.
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 | 0.000 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.001 | 0.000 |
| Research integrity | 0.001 | 0.000 |
| Insufficient payload (model declined to judge) | 0.003 | 0.002 |
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".