An Effective Soil Classification and Prediction of Crop Yield Using Spatial Big Data
Aakunuri Manjula1, G. Narsimha2

1Aakunuri Manjula, Research Scholar, Department of CSE, JNTUH Hyderabad (Telangana), India.
2Dr. G. Narsimha, Professor and Head, Department of CSE, JNTUH College of Engineering, Sulthanpur (Telangana), India.

Manuscript received on 01 May 2019 | Revised Manuscript received on 15 May 2019 | Manuscript published on 30 May 2019 | PP: 2263-2272 | Volume-8 Issue-7, May 2019 | Retrieval Number: G5835058719/19©BEIESP
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (

Abstract: (Please read carefully abstract of the template). The precise and prompt spatial categorization of the soil varieties and the forecast of crop yield rooted in the spatial big data have emerged as significant factors for the realistic purposes. In this regard, the spatially explicit crop-type information may be fruitfully utilized so as to evaluate the crop areas for a host of monitoring and decision-making applications like the crop insurance, land rental, supply-chain logistics, and the financial market forecasting. The underlying motive behind the current investigation is to effectively describe a modified support vector machine (MSVM) technique to effectively classify the soil type. The recommended crop and crop yield forecast is solely dependent on the soil type. In this regard, it is highly essential for the effective farm management to have appropriate output forecast in accordance with the amalgamation of several factors having a corresponding impact. In the document, three key functions like the big data decrease, soil categorization, and the crop recommendation including output forecast are performed. As a matter of fact, the crop changes from one farm to another on the basis of the planting dates, diversity, soil environment and the crop organization. With the result, it becomes indispensable to have an effective determination on the category of soil to be used. In the paper, the input is represented by the big data. The category of soil is ascertained by means of the procedure of the map reduce framework. The map reduction, in turn, is effectively attained with the help of the kernel principle component analysis (KPCA). Incidentally, the map reduction involves two key procedures such as the mapper and reducer. While the soil category is decided in the mapper side, the investigating procedure occurs in reducer side. Further, the innovative technique takes due consideration of the recommendation and output forecast of the crop, by elegantly employing an Optimal Artificial Neural Network classifier (OANN). In the document, the crop is recommended and the output forecast is carried out for the future years.
Keyword: Soil, Crop Yield Prediction, Spatial Big Data, MSVM, KPCA, OANN and Map Reduction.
Scope of the Article: Classification.