Abstract: More than half of India's population depends on agriculture as their primary means of sustenance, making it the cornerstone of the nation's economy. However, the future prospects of agriculture are under significant jeopardy due to the impact of shifting weather patterns, climate variations, and other environmental elements .The success of agriculture or crop management was entirely determined by the final yield and the prevailing market prices .Artificial intelligence (AI) enables automated monitoring of crops and offers predictive capabilities for yield estimation. Machine learning (ML) is instrumental in serving as a decision support tool for Crop Yield Prediction (CYP). It aids in making informed decisions regarding crop selection and providing guidance throughout the crop's growth cycle. Farmers often engage in the repeated cultivation of the same crops without exploring new crop varieties, and they apply fertilizers without proper knowledge of nutrient deficiencies and appropriate quantities. This research work aims to assist novice farmers by utilising advanced technologies such as machine learning to provide guidance on selecting suitable crops for cultivation based on accurate crop predictions. In this context, the seed data of the crops is gathered, encompassing crucial parameters such as temperature, humidity, and moisture content. This data plays a vital role in facilitating optimal crop growth and ensuring successful cultivation. The primary objective of this project is to assist farmers in predicting the yield of their crops prior to cultivation, empowering them to make informed decisions. To address this challenge, a prototype of an interactive prediction system is being developed, aiming to provide an effective solution.
Methodology:
A. Dataset Crop Recommendation Dataset collects data on weather parameters such as rainfall, temperature, humidity, and soil content, which are sourced from various reliable sources such as government websites, and weather departments. The system can receive input from farmers or sensors, including temperature, humidity, and pH levels.
B. Use of Machine Learning Algorithm • For Recommendation System (a) Random Forest Regression (b) Decision Tree (c) KNN Classifier
C. Crop Recommendation System Since the environmental conditions differ from region to region, a machine learning model is used to predict the best crop type for the selected land. To train the crop recommending model with the data collected, machine learning algorithms are used to identify the best crop to cultivate with the highest probability of growing. KNN Classifier machine algorithms is used for recommendation of crop for different season.
Results:
Using Different Machine Learning Algorithm for recommendation of Crops on the provided datasets.
KNN algorithm shows the highest accuracy among other machine learning algorithm.
