Data mining and integration for predicting significant meteorological phenomena

Abstract

a MicroStep-MIS spol. s r.o., Čavojského 1, 84108 Bratislava, Slovenská republika b Ústav informatiky SAV, Dúbravská cesta 9, 84507 Bratislava, Slovenská republika c Fakulta elektrotechniky a informatiky TUKE, AbstractThis paper describes the planned contribution of the project Data Mining Meteo (DMM) to the research of parametrized models and methods for detection and prediction of significant meteorological phenomena, especially fog and low cloud cover. The project is expected to cover methods for integration of distributed meteorological data necessary for running the prediction models, training models and then mining the data in order to be able to efficiently and quickly predict even randomly occurring phenomena. We present the methods and technologies we will use for integration of the input data, distributed on different vendors' servers. The meteorological detection and prediction methods are based on statistical and climatological methods combined with knowledge discovery -data mining of meteorological data (SYNOP, METAR messages, weather radar imagery, "raw" meteorological data from stations, satellite imagery and results of common meteorological prediction models).

Big Data Approach and Using Data Mining Techniques in Weather Prediction

“…Juraj Bartoka, 2012; This work defines the prearranged involvement of the project based on DMM of the research on parameterized methods and models for detecting and predicting the significance of meteorological phenomena; particularly low covering of cloud and fogging. This venture was likely to cover the approaches for combining the scattered meteorological data that was essential for running models of prediction, training and then mining of the data in demand for predicting randomly occurring phenomena proficiently and speedily.…”

Federating queries in SPARQL 1.1: Syntax, semantics and evaluation

“…Some of these data workflow systems are presented in [18,12,19]. These systems have been successfully used in a variety of data intensive scenarios like analyzing data from the Southern California Earthquake Center [20], data from biological domains like post genomic research [21], analysis of proteins and peptides from tandem mass spectrometry data [22], cancer research [23], meteorological phenomena [24] or used in the German grid platform [25]. In these scenarios, the systems accessed and processed petabytes of data, and we are convinced that the approach they use is the most suitable for managing the large amounts of data present in the LOD cloud.…”

Data Mining Industrial Applications

“…The latest publications from 2010 concern a new approach based on particle swarm optimization algorithm for clustering problems description (Durán, O. et al, 2010) or knowledge induction from data to detect and isolate machine breakdowns in carpet manufacturing (Çiflikli, C. & Kahya-Özyirmidokuz, E., 2010) or modern manufacturing facilities for bioproducts to improve robustness of large scale bioprocesses (Charaniya, S., et al, 2010), where authors demonstrate in different stages of the process the power of mining process data in revealing hidden correlations between parameters and outcomes. Separate solution stands (Bartok, J. et al, 2010) where data mining tasks and integration is used for detection and prediction of significant meteorological phenomena due to DMM project (Data Mining Meteo). Widespread availability of new computational methods and tools both for data analysis and predictive modelling has its successful applications traditionally in business decision making (Seng, J., & Chen, T., 2010), but also in medicine (Bellazzi, R., & Zupan, B., 2008).…”