Article Preview
TopBefore diving into the actual implementation of the Agricultural decision support system, there are some noteworthy related works that have already made an impact around the globe in the field of agriculture. Some of them are pictured below that uses different data analytic techniques to solve the existing problems.
The rudimentary task of an agriculture decision support system would be the crop type and yield prediction. Sujatha and Isakki in their work make use of different classification algorithms such as Naïve Bayes and Decision tree for forecasting the crop yield (Sujatha and Isakki, 2016). The system proposed by them contains an input module (comprising of crop name, land area, soil type, soil pH, pest details, weather, water level, seed type) and feature selection unit (minimizes the selection set of an attribute based on crop details). Eventually, after feature selection the data is grouped with similar contents on the basis of defined classification rules, which are then implemented to categorize the crop depending on the name, yield and pesticide.
Similarly, Vijayabaskara et al. (2017) in their work use predictive analytics (numerous statistical techniques to interpret historic and present data and forecast based on it) to predict the crop. An application to test the soil fertility, suggest or predict the crop and its yields, and recommendations related to fertilizers is provided and as the prediction depends on the atmosphere which is not constant, the results may vary accordingly.