Behaviour and Analysis of Soil Fertility Based on ML Models

Sarvesh Shingane, Vaidehi Lehekar, Yash Patil, Chinmayee Kharwade

Abstract: Agriculture is a critical aspect of human life and a significant source of employment in India. A large portion of the Indian population relies on agriculture, which is the backbone of the country's economy. One of the most important factors in agriculture is soil fertility. Understanding and predicting soil fertility can aid farmers and other relevant parties in making informed decisions regarding crop selection and agronomy. Machine learning offers a unique opportunity to analyse vast amounts of data and make data - driven decisions. By utilizing this technology, soil fertility prediction can be improved. This prediction includes estimating the nitrogen, phosphorus, and potassium content of soil based on historical data, such as temperature, humidity, pH, and rainfall. These predictions provide insights into soil fertility based on current field weather conditions. In this proposed research, a comparative analysis of soil properties for fertility prediction will be performed using machine learning algorithms. The study will include a comparison of different algorithms to assess soil fertility.

Keywords: fertility, Agriculture, Soil properties, Crop prediction, NPK content, machine learning algorithms, Crop production

How to Cite?: Sarvesh Shingane, Vaidehi Lehekar, Yash Patil, Chinmayee Kharwade, "Behaviour and Analysis of Soil Fertility Based on ML Models", Volume 12 Issue 3, March 2023, International Journal of Science and Research (IJSR), Pages: 1576-1578, https://www.ijsr.net/getabstract.php?paperid=SR23325224753, DOI: https://dx.doi.org/10.21275/SR23325224753