ARTIFICIAL INTELLIGENCE AND BIG DATA ANALYTICS-BASED OPTIMIZATION OF CROP YIELDS IN SUSTAINABLE AGRICULTURE

Abstract

Rural residents are gradually beginning to agree with their urban counterparts. Site-specific tweaking of administration requires precision farming since it accounts for soil nutrients that are specific to the needs of each crop. Careful planning is necessary to optimize yields, but a precise evaluation of the soil's capabilities and constraints is also crucial, as it will form the basis for choosing the right manure, application quantity, and timing. Farmers’ Preparation times are notoriously hard to estimate, so you'll need to depend on gut feelings, trial and error, a healthy dose of mystery, and critical thinking. Inefficient outcomes, wasted resources, and exacerbated environmental harm are only some of the numerous negative consequences of these issues. Because of a lack of information, farmers often have no idea how their decisions will influence their crop yields or the state of the environment. Based on the results of this research, it seems that adapting manure management strategies to the specific needs of certain crops and regions might help mitigate the negative effects of excess fertilizer and manure on the environment. By using artificial intelligence and big data analytics, the agri-food industry has the potential to make significant contributions toward meeting the growing food demand throughout the world and attaining sustainability in spite of the many challenges it faces. Soil samples might be sent to universities for analysis; however, this method is ill-considered, time-consuming, and unreliable. Recommendations such as predicted compost, NPK supplementation, and application time may be generated using weather prediction and an ANN's development.