ABSTRACT
This paper outlines a study that looked consider how machine learning regression techniques could be applied to forecast weather in agricultural fields for smart irrigation systems, crop selection, and agriculture. Farmers are increasingly relying on harvest time judgments in order to make sound crop management and financial decisions. Accurate crop output estimates can be immensely beneficial to decision-makers. In either case, using more weather-related features based on the harvest model will improve forecasting efficiency. In order to estimate crop production models, we developed an adaptable deep neural network architecture to analyse weather-related data in this article. The proposed model aims to forecast future harvest models using meteorological data from the previous year. By estimating future crop models based on weather-related data, farmers can take the necessary precautions or discontinue growing specific crops. The suggested model is designed to anticipate future crop models using weather-related data from the preceding year. As a result, farmers would be able to take appropriate adjustments or stop cultivating specific crops depending on future crop models projected using weather-related data.
