Effective Energy Estimation Technique to Classify the Nitrogen and Temperature for Crop Yield Based Green House Application

Abstract

Precision Agriculture (PA) refers to the usage of information technology to help farmers enhance and maintain crops, soil and energy efficiency and effectiveness for green house effect. PA's objectives are to preserve the climate, profitability, and energy productivity. The rise of machine learning has proven to be especially valuable for applications that need massive amounts of data. In certain ways, it is like other areas of research; it has tremendous potential and they can even use it in agriculture. An integrated approach to modelling and decision-making in PA, including geographical, spectral, and temporal domains, as well as expert knowledge. Multi-ML and signal processing approaches combined into hybrid systems to use their strengths and overcome their weaknesses. The most important issue in farming is getting an accurate yield temperature and applying an optimized nitrogen strategy One benefit of PA is considering as being the elimination of starvation Although technical, economic, and social factors typically linked to one another, the key drivers of agriculture systems growth, there is a lack of realistic agricultural realization because of the mutual complexity Through productivity and all across the state, this project hopes to lead PA to explore more deeply into the disciplines of agriculture and agricultural technology In this paper, we proposed a decision tree and a support vector machine technique, accounts for environmental conditions including temperature and the Nitrogen level of the soil to have more yield efficient and resource-conscious crop growth and cultivation plans with energy estimation.