Regression Model for Spatial Data in Precision Agriculture
Precision Agriculture (PA) is the modern farm managing technique that brings the farming challenges into an integrated environment and provides effective solution with the state of art technology. In this paper we address variable factors of land and resulting variability in yield to improve productivity and profitability. Our goal is to optimize returns on collected data to reduce environmental impacts and to gain high productivity with proper resources. Crop yield prediction is the primary factor in PA and its forecasting strongly depends on various data like meteorological, soil culture, water resource and agricultural statistics. Two main techniques are support vector regression and random forest are used in the Existing Methods. In our research we use Regression Analysis (RA) to analyze the impact factors that influences the crop yield. We have developed a regression setting which enables the spatial evaluation. We have accounted geo-referenced data and cross validate that in regression model to predict the crop yield. Regression Analysis is basically a statistical approach that estimates relationship among variables with valid relation. Here we will consider the factors like Rainfall level, Cultivation Area, Soil culture and agricultural statistics as explanatory variables to perform regression analysis that predicts the crop yield level
Keywords - Precision Agriculture; Site Specific Crop Management; Sscm; Regression Model.