Intelligent System for Predicting Agricultural Drought for Maize Crop
View/ Open
Date
2014Author
Mwagha, Solomon Mwanjele
Waiganjo, Peter W.
Moturi, Christopher A
Masinde, E. Muthoni
Type
ArticleLanguage
enMetadata
Show full item recordAbstract
There has been little information in regard to agricultural drought prediction. This paper aimed at coming up with an efficient and intelligent agricultural drought prediction system.
By using a case study approach and knowledge discovery data mining process this study was preceded by drought literature review, followed by analysis of daily 1978-2008 meteorological and annual 1976-2006 maize produce data both from Voi, Taita-Taveta (Coast Province in Kenya).
The design and implementation of an agricultural drought prediction system, was made possible by computer science programming for meteorological data preprocessing, classification algorithms for training and testing as well as prediction and post processing of predictions to various agricultural drought aspects.
The study was evaluated by comparison of predicted with actual 2009 data as well as the Kenya Meteorological Department (KMD) 2009 records. The evaluation of this study results indicated consistency with the KMD 2009 outlook. The results showed that the application of classification algorithms on past meteorological data can lead to accurate predictions of future agricultural drought.
The recommendation is that future work can be based on designing a solution for multiple regions with multiple crops.
Citation
Vol 2, Issue 4Sponsorhip
Taita Taveta University College, Department of Mathematics & Informatics University of Nairobi, School of Computing & Informatics,Publisher
International journal of technology enhancements and emerging engineering research
Subject
Agricultural droughtintelligent system
Knowledge discovery
nearest neighbor classification
Drought prediction
Description
Full Text Article