Efficient irrigation techniques are required for sustainable agriculture with the highest water management and crop productivity. Thus, a novel agricultural system is employed that integrates Artificial Intelligence (AI) methodologies with optimization techniques to automate irrigation in agricultural farms. Using AI, the system can make informed choices in water distribution based on real-time environmental parameters so crops receive enough water at the right time. Such an approach will be more resourceful, reduce the loss of water, and enhance the productivity of the farm, ultimately resulting in more sustainable agriculture systems and fewer water shortage problems in agriculture. To build a smart and adaptable the irrigation framework, the suggested system incorporates several elements, including soil moisture sensors, meteorological information, and AI-based decision-making algorithms. Further, to assess the agricultural data and make informed decisions regarding irrigation schedule, a novel multi-spectral weighted k-nearest neighbor (MSWKNN) based machine learning (ML) technique is used. To identify the most active hydration schedules, the AI model considers elements, including crop kind, development stage, environmental variables, and previous data. The monarch butterfly optimization algorithm (MBOA) is used to further enhance system efficiency. The irrigation schedules produced by the AI model are adjusted using the optimization algorithm. This makes it possible for the system to optimally distribute water resources and maximize irrigation plans to implement sustainable farming practices. Experimental findings show that the suggested strategy outperforms conventional techniques. Agriculture will experience a transformation because the results validate AI algorithms along with their optimization procedures for automated irrigation management. The technique enhances resource management and lowers environmental impact while enhancing farmer income to establish better sustainable agricultural practices and operational efficiency.
Harinaiha et al. (Fri,) studied this question.