ABSTRACT

Agriculture is a key employment in several countries throughout the globe. Artificial Intelligence (AI) is finding its way into the agricultural industry. Artificial Intelligence (AI) in the form of Machine Learning (ML) and Deep Learning (DL) can offer approaches that help produce nutritious grains. Artificial Intelligence (AI) and Machine Learning (ML) play a significant role in predicting the yield of major crops. This research employs advanced statistical and machine learning techniques to predict maize and wheat yields in the Dharwad district from 1980 to 2021, using weather data. The study objectives encompassed the development of yield prediction models, examining the impact of weather parameters on maize and wheat yield, and analysing shifts in cropping patterns.
Correlation analysis reveals significant and non-significant relationships between weather parameters and maize and wheat yield, with maximum and minimum temperature, rainfall, relative humidity, and windspeed showing varying degrees of influence. Regression analysis identifies significant factors affecting yield, with windspeed emerging as a crucial predictor in the Dharwad district for maize crop and maximum temperature as a crucial predictor for wheat crop in the Dharwad district. Machine learning models, including Support Vector Regression and K-nearest neighbor, were employed to predict yields based on weather parameters. K-nearest neighbor demonstrated superior predictive accuracy, offering insights for farmers' decision-making. Markov chain modelling unveiled shifts in cropping patterns.
Policy implications underscore the value of the predictive model's role in modern agriculture by leveraging data to improve decision-making, enhance productivity, and ensure sustainability. In conclusion, this thorough investigation offers insightful information about the production of maize and wheat in the Dharwad district of Karnataka empowering stakeholders to make well-informed decisions, maximize resource utilization, and improve overall sustainability and productivity.