An Overview of Data Mining Techniques Applied to Agricultural Soil Data

Data Mining is emerging research field in agriculture soil data analysis. Different data mining approaches are in use, such as Nearest Neighbor, Regression, Neural Networks, Support Vector Machines, and Bayesian for areas like online advertising, health care, news publishing, brain science, bioinformatics, analysis of social network study of business, consumer and social insights, agriculture field etc. This review paper describes the discussion on the application of data mining predictive and descriptive techniques in the field of agriculture. Data mining tool will help appropriate amount of plant nutrients in the soil. This information will help to select type of fertilizer, time of application and overall selection of cropping pattern and cropping system. By analyzing the soil data one can come to know that there is use of fertilizers more than the requirement of soil. Excess use of fertilizers is a major agricultural problem that remains to be solved based on the available soil data. The problem can be solved by applying different data mining techniques. Application of nonrecommended rates or the wrong kinds of fertilizers can harm the crop and decrease crop production and productivity of the soil. The analysis of agriculture soil dataset with various data mining techniques may yield useful outcomes to farmers in order to make right decisions with respect to crop planning, cropping pattern, fertilizer management, and to maintain the fertility of soil. In this research review study, we describe an overview of data mining techniques applied to agricultural soil data for different purposes.