Crop prediction based on soil parameters using internet of things, machine learning, and implemented over WI-FI protocol | |
| Author | Sharma, Tanka Nath |
| Call Number | AIT RSPR no.TC-22-01 |
| Subject(s) | Internet of things Machine learning--Computer programs Soils--Quality Wireless communication systems |
| Note | A research study submitted in partial fulfillment of the requirements the degree of Master of Engineering in Telecommunications, School of Engineering and Technology |
| Publisher | Asian Institute of Technology |
| Abstract | With the increase in human pressure on natural resources to produce enough food for everyone, it has become necessary to find easier, economical, and sustainable agricultural practices. Using an Internet of Things (IoT) system along with machine learning algorithms could greatly enhance the ways we are doing farming in the present day. The most important factor for a good agricultural yield is to know the suitability of a crop for the land. We propose a low-cost, simple, and durable IoT-based system for the two following purposes: 1.) predicting crops suitable for a given piece of land based on the soil parameters, namely, soil potential of Hydrogen (pH) and soil temperature and 2.) monitoring and automating some of the recurrent processes, i.e., adding fertilizer such as Nitrogen, Phosphorous, and Potassium (NPK) and irrigation of the land. If the NPK levels for growing locations are good, then we can decide not to add additional fertilizers. We found that the proposed IoT based system can suggest a crop as well as monitor and control soil parameters throughout a crop life cycle. Thus, the system can help a farmer cultivate crops that are naturally suitable for his/her land, minimize human interaction, optimize the use of fertilizers and water resources, and reduce the necessity of chemicals such as pesticides and weedicides. Additionally, it can store these soil pa rameters which could be of use for further study and analysis. The proposed IoT-based system is built with open-source technologies, including communication protocols such as Modbus and MQTT, easily available hardware such as ESP32 microcontroller, solar panel, rechargeable batteries, relays etc, and software such as InfluxDB and Node-RED. Consequently, the system is cost-effective and adaptable to future changes. In future, this system can be improved by incorporating a machine learning technique making use of soil parameters to predict disease and crop yield. |
| Year | 2022 |
| Type | Research Study Project Report (RSPR) |
| School | School of Engineering and Technology (SET) |
| Department | Department of Information and Communications Technologies (DICT) |
| Academic Program/FoS | Telecommunications (TC) |
| Chairperson(s) | Attaphongse Taparugssanagorn |
| Examination Committee(s) | Teerapat Sanguankotchakorn;Poompat Saengudomlert, |
| Scholarship Donor(s) | Asian Development Bank-Japan Scholarship Program (ADB-JSP) |
| Degree | Research Studies Project Report (M. Eng.) - Asian Institute of Technology, 2022 |