Instrumentation System for Monitoring of Soil Variables in Precision Agriculture Applications
The world faces a food crisis due to population growth, climate change, and social conflicts. Different solutions are being studied to increase food production and ensure food security. One approach is precision agriculture. This practice comprises a set of technologies that combine sensors, informa...
Saved in:
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2025-01-01
|
| Series: | IEEE Access |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10924202/ |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | The world faces a food crisis due to population growth, climate change, and social conflicts. Different solutions are being studied to increase food production and ensure food security. One approach is precision agriculture. This practice comprises a set of technologies that combine sensors, information systems, machinery, and information analysis to optimize agricultural production. Since each crop has different resource requirements, having a system to measure and visualize soil variables related to crop productivity is of great interest. The present work proposes a system to measure and visualize temperature, moisture, pH, Nitrate, and positive Potassium ions. The system design was divided into two stages. The first stage is an electronic instrumentation system to acquire, adapt, and transmit georeferenced soil variables. The second stage is a data processing system interpolating georeferenced information to generate estimated heatmaps for visualization. The built prototype characterization showed errors of less than 1% for temperature and moisture, 3% for pH, 17% for Nitrate, and 14% for positive Potassium ions. Despite presenting high levels of error in measuring nutrients, the sensors, manufactured using CMOS-MEMS technology, have high potential for integration and miniaturization. With data obtained from the prototype in a field trip to a rice crop, estimated heatmaps were generated using two interpolation techniques (IDW- Inverse Distance Weighting- and Kriging). Results showed that for the Kriging technique, MAE (mean absolute error) and RMSE (root-mean-square error) values were lower, confirming that this method is adequate for extrapolation and soil data visualization. |
|---|---|
| ISSN: | 2169-3536 |