A Data Mining System for Real Time Soil Moisture Prediction. (2017)

• Record Type: Journal Article
• Authors: Matei, Oliviu; Rusu, Teodor; Petrovan, Adrian; Mihuţ, Gabriel
• Is Part Of: Procedia engineering. Volume 181(2017)
• Page Start: 837
• Page End: 844
• Publication Date: 2017
• Subjects: meteo prediction -- data mining -- neural networks -- support vector machine.; Engineering -- Congresses; Engineering -- Periodicals; Engineering; Conference proceedings; Periodicals; 620.005
• DOI: 10.1016/j.proeng.2017.02.475
• Languages: English
• ISSNs: 1877-7058

Abstract

Abstract: In the context of the increased climate change, local weather monitoring is crucial from economic and agricultural point of view, as the classical meteo prediction schemes do not apply very precisely. Therefore, the current paper presents a data mining system capable of gathering weather data from several weather stations and predicting the moisture of the soil for the next day, all in real time. The system has been tested in real-life conditions, with ten stations working in Transylvanian Plain. We have proven that the prediction accuracy is very high and the system can be used in agriculture as a mature platform in any geo-climate conditions.