Abstract:
Agriculture is one of the important occupations practiced in India. It is the broadest economic sector and plays a most important role in the overall development of the country. More than 60% of the land in the country is used for agriculture in order to suffice the needs of 1.3 billion people Thus adopting new agriculture technologies is very important. This will lead the farmers of our country towards profit.
Here we have proposed a system to guide the farmers to maximize the crop yield as well as suggest the most profitable crop for the specific region. The proposed model provides crop selection based on environmental conditions, and benefits to maximize the crop yield that will subsequently help to meet the increasing demand for the country's food supplies. The proposed model predicts the crop yield by studying factors such as humidity, Ph, soil type etc. The system also helps to determine the best time to use fertilizers. The user provides an area under cultivation, state, district, crop and season as inputs. According to the requirement, the model predicts the crop yield for a specific crop. The model also recommends the most suitable crop and suggests the right time to use the fertilizers. The timing of applying the fertilizer is very crucial. The farmer's effort and money will get wasted if the rain comes down too early. The proposed fertilizer usage service will guide the farmer on when to use the fertilizer. The model predicts the rain for the specific location with Open Weather API then it recommends the right time to use the fertilizers Also, the system provides an interaction facility with the expert for best assistance and doubt clearance.
Here we use Machine Learning approach for developing this system using K- Nearest Neighbor Algorithm to predict the crop yield and suitable crop for a specific region. K-nearest neighbors (KNN) is a type of supervised learning algorithm used for both regression and classification. KNN tries to predict the correct class for the test data by calculating the distance between the test data and all the training points.
