Abstract:

Abstract In India, the majority of people make their living from the agricultural sector. Agriculture provides a livelihood for approximately 50 percent of India's total population. Agriculture has a significant bearing on both the state of business and the level of food safety in the country. This part of the economy is in terrible shape and has been showing signs of stagnation for some time. Changes in the environment make it harder for farmers to grow enough food for everyone. Floods and droughts are just two examples of bad weather events that can change the growing season, reduce the amount of water available, help plants, bugs, and fungi spread, and, in the end, make farming less productive. Greenhouse gas pollution from farms can be reduced if farmers adopt climate-smart practices. Farmers who employ AI find it easier to make sense of environmental and operational variables like temperature, humidity, wind speed, and sun radiation. Collecting and assessing statistics on climate, precipitation, soil, seed, crop yields, humidity, and wind speed in a few key locations will help producers increase crop yields. In addition, a custom recommender system was used to forecast crops and display them on a Flask-built graphical user interface. The system's flexible architecture means it could one day be used to find the recommended products of other regions. This article develops similar machine learning methods and compares and contrasts five methods using specific agricultural data.

Keywords: