Open AccessA Decision Support System for Increasing Agricultural Production
Author(s) -
S. Revathi,
Michael Gabriel Paulraj,
P. Parameswari
Publication year - 2020
Publication title -
international journal of innovative technology and exploring engineering
Language(s) - English
Resource type - Journals
ISSN - 2278-3075
DOI - 10.35940/ijitee.d1133.029420
Subject(s) - agriculture , agricultural engineering , soil texture , environmental science , productivity , agricultural productivity , crop yield , soil type , water content , production (economics) , work (physics) , agricultural soil science , agroforestry , soil water , computer science , soil science , soil fertility , agronomy , soil biodiversity , engineering , geography , economics , mechanical engineering , geotechnical engineering , macroeconomics , archaeology , biology
Agriculture acts an important and primary role in all countries. Especially in Indian economy, agriculture acts an important factor. So, farmers are always in need to increase their crop productivity, which depends on variety of factors present in soil. If a crop is planted on unsuitable soil, it leads to poor yield. So much more attention is needed while selecting the crop for planting. The huge amount of agricultural data that is available in many resources and data mining performs major role in agriculture. By using this data mining techniques, the hidden required pattern from the huge data can be identified and make them useful to the farmers and decision makers to obtain better yield performance. In our work, data mining technique is applied in the dataset of soil and crops, which belongs to Tamilnadu region. We have analyzed various physical properties and also chemical properties of soil like Soil type, Soil Texture, Color, Structure, WHC (Water Holding Capacity), Soil Moisture, pH, Electrical Conductivity (EC) and Temperature. We have considered Soil Type, pH, EC and Temperature in this work to find the suitable crop for best productivity. This research mainly concentrates on finding the correlation between soil properties and crops by applying clustering algorithms such as Simple K Means (SKM), Filtered Clusterer (FC) and Hierarchical Clusterer (HC) for finding the suitable crop according to the soil properties.