Conceptual modelling of forest fires flashes by datamining ontology-based. Part 1
Abstract
The heliocentric hypothesis of causes of forest fires outbreaks has been tested. We found evidence of correlation between the sudden arrival of charged particles from the Sun and the occurrence of forest fires with a delay of one to four days. In this research, the comparative analysis was made between ANFIS and Neuron Networks in the task of searching a functional dependence between the occurrence of forest fires and the factors which characterize the solar activity. For this purpose, we used several methods (R/S analysis, Hurst index, DataMining) for establishing potential links between the influx of some parameters from the Sun and the occurrence of forest fires with lag of several days. We found an evidence for a connection and developed a forecasting scenario based on the ANFIS and Neuron Network techniques. This scenario, in some cases, allows to predict occurrences of forest fires with up to 93% accuracy.References
Radovanovic M., Gomes J. Solar Activity and Forest Fires. — Nova Science Publishers Inc, 2009. — 109 p.
Nikolov N. Global Forest Resources Assessment 2005 – Report on fires in the Balkan Region. Forestry Department / N. Nikolov, Fire Management Working Papers FM/11/E, Rome, 2006. — 38 p.
Forest Fires in Europe, Middle East and North Africa 2011. [ G. Schmuck, J. San-Miguel-Ayanz, A. Camia, et al.], Publication office of the European union, 2012. — 108 p.
Incident Management Situation Report Archives. — http://www.predictiveservices.nifc.gov/intelligence/archive.htm.
Kourtz P.H., Todd J.B. Predicting the daily occurrence of lightning-caused forest fires / Forestry Canada, Petawawa National Forestry Institute, Chalk River, Ontario. — Information Report PI-X-112, 1991. — 26 p.
Hall L.B. Precipitation associated with lightning-ignited wildfires in Arizona and New Mexico // Int. J. Wildland Fire. — 2007. — 16 (2). — P. 242–254.
Cumming S.G. Forest type and wildfire in the Alberta boreal mixedwood: What do fires burn? // Ecol. Appl. — 2001. — 11 (1). — P. 97–110.
Wotton M.B., StockAn J.B., Martell L.D. An index for tracking sheltered forest floor moisture within the Canadian Forest Fire Weather Index Systemton // Int. J. Wildland Fire. — 2005. — 14(2). — P. 169–182.
Sannikov S.N., Zakharov A.I., Smol’nikova L.G., Sannikova N.S. Forest fires caused by lightning as an indicator of connections between atmosphere, lithosphere, and biosphere // Ekologiya. — 2010. — 41(1). — P. 1–6.
Viegas D.X. Forest fire propagation // Phil. Trans. R. Soc. London Ser. A. —1998. — P. 2907–2928.
Guyette P.R., Stambaugh C.M., Dey C.D., Muzika R.M. Predicting Fire Frequency with Chemistry and Climate Ecosystems // Ecosystems. — 2012. — 15(2). — P. 322–335.
Gomes J., Radovanovic M. Solar activity as a possible cause of large forest fires — а case study: Analysis of the Portuguese forest fires // Sci. Total Environ. — 2008. — 394 (1). — P. 197–205.
Incident Management Situation Report (IMSR) Archives. — http://www. predictiveservices.nifc.gov/intelligence/archive.htm.
SWPC Anonymous FTP Server Historical SWP Products from 1996 to 2008. — http://www.swpc.noaa.gov/ftpmenu/warehouse.html.
MTOF/PM Data by Carrington Rotation. — http://umtof.umd.edu/pm/crn/.
Ducic V., Milenkovic M., Radovanovic M. Contemporary Climate Variability and Forest Fires in Deliblatska pescara // Journal of the Geographical institute Jovan Cvijic. — 2008. — 58 (1). — P. 59−74.
Radovanović M. Forest fires in Europe from July 22nd to 25th 2009 // Arch. Biol. Sci. Belgrade. — 2010. — 62 (2). — P. 419−424.
Radovanovic M. Solar Activity – Climate Change and Natural Disasters in Mountain Regions // Sustainable Development in Mountain Regions. Belgrade. — 2011. — P. 9−17.
Boxall M. ESS Guidelines on Seasonal Adjustment. Eurostat. — Luxembourg: Office for Official Publications of the European Communities. — http://epp. eurostat.ec.europa.eu/portal/page/portal/national_accounts/documents/ESS_Guidelines_on_SA.pdf.
Bell W.R. Economic Time Series: Modeling and Seasonality. [W.R. Bell, S.H. Holan, T.S. McElroy] CRC. — 2012. — 554 p.
Hansen B.E. Econometrics. University of Wisconsin, Department of Economics // Debopam Bhattacharya, Oxford. — 2014. — P. 378.
Labitzke K. The global signal of the 11-year sunspot cycle in the atmosphere: When do we need the QBQ? // Meteorolog. Zeitschrift. Berlin. — 2003. — 12(4). — P. 209−216.
Lenskiy A. The analysis of R/S estimation algorithm with applications to WiMAX network traffic // International Journal of Multimedia and Ubiquitous Engineering. — 2012. — 7 (3). — P. 27−34.
Velsquez Valle M.A., Oleschko L., Klaudia Corral, Ruiz J.A., Korvin Gabor. Spatial Variability of the Hurst Exponent for the Daily Scale Rainfall Series in the State of Zacatecas, Mexico // Journal of Applied Meteorology and Climatology. — 2013. — 52(12). — P. 2771−2780.
Ozger M. Prediction of ocean wave energy from meteorological variables by fuzzy logic modeling // Expert Systems with Applications. — 2011. — 38 (5). — P. 6269−6274.
Peters E., Wiley J. Fractal Market Analysis: Applying Chaos Theory to Investment and Economics // John Wiley & Sons, 1994. — 315 p.
Radovanović M., Vyklyuk Y., Jovanović A., Vuković D., Milenković M., Stevančević M. Examination of the correlations between forest fires and solar activity using Hurst index // Journal of the Geographical institute Jovan Cvijic SASA. — 2013. — 63 (3). — P. 23−32.
Amini M., Abbaspour K.C., Johnson C.A. A comparison of different rule-based statistical models for modeling geogenic groundwater contamination // Environmental Modelling Software. — 2010. — 25(12) — P. 1650−1657.
Bektas Ekici B., Teoman Aksoy U. Prediction of building energy needs in early stage of design by using ANFIS // Expert Systems with Applications. — 2011. — 38(5). — P. 5352−5358.
Betul Bektas Ekici, Teoman Aksoy U. An approach based on ANFIS input selection and modeling for supplier selection problem // Expert Systems with Applications. — 2011. — 38(12). — P. 14907−14917.
Kurtulus B., Flipo N. Hydraulic head interpolation using anfis — model selection and sensitivity analysis // Computers & Geosciences. — 2012. — 38(1). — P. 43−51.
Shiri J., Kisi O., Yoon H., Lee K. Predicting groundwater level fluctuations with meteorological effect implications — A comparative study among soft computing techniques // Computers & Geosciences. — 2013. — 56. — P. 32−44.
Soltani F. Developing operating rules for reservoirs considering the water quality issues: Application of ANFIS-based surrogate models / F. Soltani, R. Kerachian, E. Shirangi // Expert Systems with Applications. — 2010. — 37(9). — P. 6639−6645.
Rowell A., Moore F., Peter F. Global Review of Forest Fires.; IUCN.Gland, Swetzerland, 2000. — 64 p.
Mitra S.K. Is Hurst Exponent Value Useful in Forecasting Financial Time Series? // Asian Social Science. — 2012. — 8 (8). — P. 111–120.
Jyh-Shing Roger Jang, Chuen-Tsai Sun, Eiji Mizutani. Neuro-Fuzzy and Soft Computing: A Computational Approach to Learning and Machine Inteligence // Prentice Hall, 1997. — 614 p.
Yilmaz I., Kaynar O. Multiple regression, ANN (RBF, MLP) and ANFIS models for prediction of swell potential of clayey soils // Expert Systems with Applications. — 2011. — 38 (5). — P. 5958−5966.
