Soil Analysis and Crop Fertility Prediction Using Machine Learning

Adrija Shree; Ekansh Singh; Ajay Chaudhary

Abstract: India's economy is built on agriculture. Agribusiness is responsible for 50% of the remaining task in India. Agriculture has a higher level of commitment in the Indian economy than any other division. In any event, farmers used traditional harvesting strategies, resulting in lower yield profitability. Furthermore, soil erosion and its integration is a major contributor to lower yield profitability. This will have an effect on the degree of productivity. Loss of soil nutrients due to various processes is also a motivator to reduce soil richness. Supplements such as potassium (K), nitrogen (N), and phosphorus (P) are essential for plant development. To address these challenges in the agribusiness sector, agricultural advancement is critical, and judicious cultivation is the ideal approach. Crop mutation is a strategy that farmers use after each subsequent crop production. The crop mutation allows the soil to reclaim minerals that were previously used by the crop and use the minerals that were left over to cultivate the new crop. Farmers must experience a decrease in production to determine if the soil has reached the point when it is unfit to yield the specific crop. Accepting a loss in one financial year is critical for a farmer. This research proposes a that would aid in the continuous maintenance of soil fertility. This strategy has been used in many places where a change in crop is made following a loss in yield from constantly cultivating the same crop. When it comes to predicting soil quality, three soil factors are taken into account. Using Machine Learning Techniques, this method provides a solution to the problem indicated above. This research proposes a software-based solution for predicting soil quality using key soil characteristics and variables.

Soil Analysis and Crop Fertility Prediction Using Machine Learning

Article Information

Abstract

Related Articles