International Journal of Human Computations & Intelligence

Hybrid Mode of Crop Yield Prediction Using Various Machine Learning Algorithms

Sangeetha Muthu — 2024-06-03

Over 50% of India's population depends on agriculture for existence, making it the foundation of the country's economy.Variations in weather, climate, and other environmental factors are now a significant threat to the continued success ofagriculture. The decision support tool for Crop Yield Prediction (CYP), which includes assisting decisions on which crops to plant and what to do during the growth season of the crops, is where machine learning (ML) plays a vital role. The current study focuses on a systematic review that extracts and synthesizes the CYP traits. In addition, a number of approaches have been created to analyse agricultural production prediction utilizing Artificial Intelligence techniques. In this paper, the predictions provided by the Random Forest and Naive Bayes algorithms will assist the farmers in choosingwhich crop to cultivate to produce the greatest yield by taking into account variables such as water, wind, sunlight,temperature, rainfall, and photosynthetic activity. Pollinating agents, which analyses several ML strategies used in the fieldof agricultural yield estimation and offered a complete study in terms of accuracy employing the techniques, boost the fertility of the soil.

An efficient crop recommendation system using machine learning mechanisms

Kiran Kumar P N — 2024-06-03

In India, the job situation and economy are significantly influenced by agriculture. However, a common problem for Indian farmers is choosing the wrong crops for their land, which lowers yield. In addition to having an impact on individual farmers' earnings, this problem has larger ramifications for the country's food security and is a factor in the surge in farmer suicides. Proactive steps are needed to address these issues, such as recommending appropriate crops based on soil tests before sowing. A crop recommendation system that incorporates machine learning algorithms is one suggested way to address this. The objective is to reduce farmer losses and increase total productivity by evaluating the profitability of individual crops. Various soil factors are used to identify the most suited crops through the use of machine learning algorithms for classification. To verify dependable results, the efficacy of this method is tested by calculating accuracy and confusion matrix metrics. The objective is to equip farmers with the knowledge necessary to make wise decisions by strategically applying cutting-edge algorithms and data analysis. This will ultimately promote sustainable agricultural practices and solve the sector's problems.