Precision Home Agriculture and Refined Market Evaluation Resource PHARMER

Traditional farming practices have established themselves strongly over the course of time, however due to depleting natural resources growing crops has been getting difficult and less efficient, resulting in financial loss for an average farmer. The main reasons for decreasing efficiency are usage

Project Title

Precision Home Agriculture and Refined Market Evaluation Resource PHARMER

Project Area of Specialization

Internet of Things

Project Summary

Traditional farming practices have established themselves strongly over the course of time, however due to depleting natural resources growing crops has been getting difficult and less efficient, resulting in financial loss for an average farmer. The main reasons for decreasing efficiency are usage of flood irrigation, which wastes water, excessive use of fertilizers and pesticides, which decreases the quality of a crop overall, and depletion of soil nutrients over time, which leads to decreased crop quality and land degradation.

Project PHARMER hopes to introduce precision agriculture for the masses and provide them with a platform where they can find out which crops would be more profitable for them to plant. In addition to this, by introducing precision agriculture, we hope to solve the above-mentioned problems, and help the farmer population of Pakistan in general.

This problem is two-fold. Firstly, how to control the quality of the crop via an automated system, and secondly, how to make decisions on which crop to be planted in any farming environment. Traditional farming methods used in Pakistan today are wasteful of limited resources and do not account for which crop will be most successful in the market. Moreover, the farming process is tedious and requires a lot of manual work, therefore by automating the process the need for manual labor will be reduced.

The goal of this project is to devise a system which maximizes the yield while keeping the cost of resources as low as possible, by automating the farming process. Concurrently, the system also provides a tool that can assist a user in selecting a crop for maximum profit.

Project Objectives

The goal of the project is to introduce a precision agriculture technique which could help expert farmers, as well as the public to be able to grow and have access to simple crops. In addition to this, we also want to curb the problem of wasting resources and excessive use of pesticides and fertilizers. Furthermore, we also want to introduce a machine learning platform for farmers, where they could get suggestions about which crop, they should plant for better profits.

Project Implementation Method

The solution proposed will consist of a) an embedded system, and b) a web hosted machine learning platform. To interface with both of these systems, a mobile application(s) will be used. The user will be able to view and control the state of the embedded system using the app and will also be able to access the machine learning platform in order to make queries about which crop to plant.

The hardware portion will use micro controllers to sense the conditions and control the actuators. The sensors used will measure levels of moisture, temperature, and pH. These values will control the amount of water dispensed, heating and cooling, and fertilizer dispersion.

The embedded system code will talk with the app and database. The app will allow monitoring of the embedded system as well as access to the machine learning platform. The database will store all the required conditions for supported plants (ideal moisture, temperature, and pH).

The machine learning platform will utilize an ensemble classification technique to suggest best crop in terms of profit and or yield. This will be trained on a dataset consisting of crop types, conditions, yields, and profit.

Benefits of the Project

The main benefit of this project is to introduce precision agriculture and computer assisted decision making to both the general population as well as traditional farmers.

The vertical farm system will save on resource use and allow for crops to be grown in any conditions. It will also allow the user of the setup to not have to worry about catering the plant as it will be automated. The machine learning platform will allow its users to make informed decision about which crop to plant for maximum yield and profit.

Technical Details of Final Deliverable

The main deliverables are the vertical farm system, the machine learning platform, and the mobile application.

The design of the vertical farming system in this project is relatively simple. W use an AC to DC power supply of 12V to power the entire system, with regulators as required. 12V goes to the solenoid valves, 5V to power the LED strips, 3.3V to power the microcontrollers (both WROOM-ESP and Arduino Pro Mini). The heat lamps will be powered with 220VAC, and controlled via microcontroller through a triac. The main microcontroller and sub microcontrollers will all be connected via a data bus. Each of the sub microcontrollers is connected to various sensors (LM35, LM393, etc) and various actuators (LED strip, Heat lamp, water valve, etc) over its GPIO pins.

The code for both the main and sub microcontrollers are coded on the Arduino IDE, using their appropriate board manager software and libraries. The main microcontroller (WROOM-ESP ESP32) requires the ESP32 board manager software and utilizes libraries for communication on the common data bus. It also uses the firebase library to communicate with the Google Firebase database. The sub microcontrollers (Arduino Pro Mini) use the basic libraries included with the Arduino IDE, including the ones required for communication on the common data bus. Besides this, the sub microcontrollers will also include relevant libraries for sensors and actuators as required.

The machine learning platform will be written in python and will use classification algorithms available in the ‘sklearn’ and ‘tensorflow’ libraries. Besides this, the code will be written in such a way that it can be run from a server and communicate with the app over the internet.

The mobile application will be coded in the dart programming language, and built using the flutter app development platform, which is capable of building apps for both android and iOS. The app will also use the Google Firebase library in order to communicate with the main microcontroller.

Final Deliverable of the Project

HW/SW integrated system

Core Industry

Agriculture

Other Industries

Core Technology

Internet of Things (IoT)

Other Technologies

Artificial Intelligence(AI)

Sustainable Development Goals

Responsible Consumption and Production

Required Resources

If you need this project, please contact me on contact@adikhanofficial.com