A Comprehensive Review of IoT-Driven Soil Diagnostics and Crop Recommendation Techniques
Bibliographic record
Abstract
Modern agriculture faces the dual challenge of improving crop productivity while ensuring sustainable use of resources. Traditional farming methods often rely on guesswork, which can lead to overuse of water and fertilizers, harming both crops and the environment. This study presents AgroSense, a smart farming solution that combines Internet of Things (IoT) technology with machine learning to support better decision-making for farmers. The system uses a combination of sensors and NodeMCU (ESP8266) microcontrollers to gather real time data on soil temperature, moisture, pH levels, and essential nutrients like nitrogen, phosphorus, and potassium (NPK). The collected data is transmitted to Firebase, a cloud platform, where machine learning models process the information to recommend the most suitable crops based on current soil conditions. A user friendly interface, developed using Streamlit, allows farmers to view their soil data and receive crop suggestions through both web and mobile devices. Field tests were conducted in different farming environments to evaluate the system’s effectiveness. Results showed that AgroSense helped reduce unnecessary water usage and minimized fertilizer application while increasing overall crop yields. The system proved to be low-cost and accessible, making it ideal for small and medium-scale farmers. By merging traditional farming knowledge with data-driven insights, AgroSense promotes sustainable agriculture and supports long term food security. This survey highlights the potential of smart farming tools in transforming agriculture into a more efficient and environmentally friendly practice.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.002 | 0.004 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.001 | 0.002 |
| Open science | 0.001 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.004 | 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".