Precision farming practices with data-driven analysis and machine learning-based crop and fertiliser recommendation system
Bibliographic record
Abstract
Agriculture forms a major occupation in countries like India. More than 75% people rely on farming for their daily wages. Food security on a global scale is mostly dependent on agriculture. Hence, achieving good yield in the crops grown by farmers is the major concern. Various environmental factors have a significant impact on the crop yield. One such component that contributes majorly to the crop yield is soil. Due to urbanization and enhanced industrialization, the agricultural soil is getting contaminated, losing fertility, and hindering the crop yield. One exciting new way to maximise crop yields while decreasing input costs is precision farming, which makes use of machine learning (ML) and the IoT. Machine Learning (ML) is employed for agricultural data analysis. The goal of this research is to optimise agricultural practices by presenting an integrated crop and fertiliser recommendation system. The proposed ML based model “Precision Agriculture” aims at predicting the suitable crops that can be grown based on the class which the soil sample belongs to and suggests the fertilizers that can be used to further enhance the fertility of soil. Using proposed model, farmers can make decisions on which crop to grow based on the soil classification and decide upon the nitrogen–phosphorous– potassium (NPK) fertilizers ratio that can be used. Comparison of the SVM algorithm with Naive Bayes, and LSTM has shown that SVM performed with a higher accuracy. Decision support tools that integrate AI and domain knowledge are provided by the study, which is a substantial contribution to precision agriculture.
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 | 0.001 |
| 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".