This paper is published in Volume-8, Issue-3, 2022
Area
Machine Learning
Author
Himanshu Ajay Borade, Amogh Chandrashekhar Kurlekar, Pranjal Shailendra Sawarbandhe, Randhir Arun Gitte, Dr. Rohini Chavan
Org/Univ
Vishwakarma Institute of Information Technology, Pune, Maharashtra, India
Pub. Date
21 June, 2022
Paper ID
V8I3-1271
Publisher
Keywords
Linear Regression, Agriculture, pH of the soil

Citationsacebook

IEEE
Himanshu Ajay Borade, Amogh Chandrashekhar Kurlekar, Pranjal Shailendra Sawarbandhe, Randhir Arun Gitte, Dr. Rohini Chavan. Best Crop Yield Prediction and Maintenance of Soil Fertility using pH Value of Soil: Predicting pH Value using Digital Image Processing and Linear Regression, International Journal of Advance Research, Ideas and Innovations in Technology, www.IJARIIT.com.

APA
Himanshu Ajay Borade, Amogh Chandrashekhar Kurlekar, Pranjal Shailendra Sawarbandhe, Randhir Arun Gitte, Dr. Rohini Chavan (2022). Best Crop Yield Prediction and Maintenance of Soil Fertility using pH Value of Soil: Predicting pH Value using Digital Image Processing and Linear Regression. International Journal of Advance Research, Ideas and Innovations in Technology, 8(3) www.IJARIIT.com.

MLA
Himanshu Ajay Borade, Amogh Chandrashekhar Kurlekar, Pranjal Shailendra Sawarbandhe, Randhir Arun Gitte, Dr. Rohini Chavan. "Best Crop Yield Prediction and Maintenance of Soil Fertility using pH Value of Soil: Predicting pH Value using Digital Image Processing and Linear Regression." International Journal of Advance Research, Ideas and Innovations in Technology 8.3 (2022). www.IJARIIT.com.

Abstract

the pH of the soil is a key factor that can impact nutrients in the soil and plays an important role in deciding what crops will we yield on the farm as well as fertilizer that farmers will use to make their crops better. The traditional methods are proven by many scientists and have their own disadvantages like sensor damage and maintenance of kits. The alternate solutions such as image processing-based prediction give more accurate and fast results than traditional methods. Here, we have used image processing and a Linear Regression algorithm to identify the pH level of the soil. Basically, to determine the pH level of soil, pH kits from labs are used. But they are not always accurate as they add extra maintenance for the results. To overcome this issue, we proposed a system that can obtain the pH value, recommend the crop for the same and also show the nearest fertilizer stores to the farmer. For crop recommendation system it uses attributes like soil pH, the texture of the soil, the color of soil, and nutrients available in the soil. In this paper, we proposed a method to get the result of soil pH instantly, so that it will be easier for farmers to analyze the crop prediction.