A wavelet-SARIMA-ANN hybrid model for precipitation forecasting

• Autorzy: Shafaei M. , Adamowski J. , Fakheri-Fard M. , Dinpashoh Y. , Adamowski K.

Identyfikatory

DOI

10.1515/jwld-2016-0003

Warianty tytułu

PL

Hybrydowy model wavelet-SARIMA-ANN do prognozowania opadów

• Języki publikacji: EN

Abstrakty

EN

Given its importance in water resources management, particularly in terms of minimizing flood or drought hazards, precipitation forecasting has seen a wide variety of approaches tested. As monthly precipitation time series have nonlinear features and multiple time scales, wavelet, seasonal auto regressive integrated moving average (SARIMA) and hybrid artificial neural network (ANN) methods were tested for their ability to accurately predict monthly precipitation. A 40-year (1970–2009) precipitation time series from Iran’s Nahavand meteorological station (34°12’N lat., 48°22’E long.) was decomposed into one low frequency subseries and several high frequency sub-series by wavelet transform. The low frequency sub-series were predicted with a SARIMA model, while high frequency subseries were predicted with an ANN. Finally, the predicted subseries were reconstructed to predict the precipitation of future single months. Comparing model-generated values with observed data, the wavelet-SARIMA-ANN model was seen to outperform wavelet-ANN and wavelet-SARIMA models in terms of precipitation forecasting accuracy.

PL

Prognozowanie opadów, ze względu na ich znaczenie w gospodarce zasobami wodnymi, szczególnie w zmniejszaniu ryzyka powodzi czy susz, było już przedmiotem wielu badań. Serie miesięcznych opadów mają właściwości nieliniowe i różne skale czasowe, w związku z czym przetestowano różne metody: wavelet, metodę zintegrowanej sezonowej autoregresji z ruchomą średnią (SARIMA) i hybrydową metodę sztucznych sieci neuronowych (ANN) pod kątem ich zdolności do dokładnego przewidywania miesięcznych opadów. Czterdziestoletnią (1970–2009) serię opadów z irańskiej stacji meteorologicznej w Nahavand (34°12’N, 48°22’E) rozłożono na jedną podserię o niskiej częstotliwości i kilka podserii o wysokiej częstotliwości występowania opadów przez transformację falkową. Podserie o niskiej częstotliwości prognozowano za pomocą modelu SARIMA, podczas gdy podserie o wysokiej częstotliwości prognozowano, stosując ANN. Na koniec prognozowane podserie zrekonstruowano celem przewidywania opadów w poszczególnych miesiącach w przyszłości. Porównanie wartości generowanych przez model z danymi z obserwacji wykazało lepszą dokładność prognozowania opadów za pomocą modelu wavelet-SARIMA-ANN niż za pomocą modeli wavelet-ANN i wavelet-SARIMA.

Słowa kluczowe

EN

artificial neural network (ANN); precipitation forecasting; seasonal auto regressive integrated moving average (SARIMA); water resources management; wavelet

PL

gospodarka zasobami wodnymi; metoda wavelet; prognozowanie opadów; sezonowa zintegrowana autoregresja z ruchomą średnią; sztuczne sieci neuronowe

• Wydawca: Wydawnictwo ITP
• Czasopismo: Journal of Water and Land Development
• Rocznik: 2016
• Tom: no. 28
• Strony: 27--36
• Opis fizyczny: Bibliogr. 41 poz., rys., tab.

Twórcy

autor

Shafaei M.

• University of Tabriz, Department of Water Engineering, Iran

autor

Adamowski J.

• McGill University, Faculty of Agricultural and Environmental Sciences, Department of Bioresource Engineering, Quebec, Canada, H9X 3V9

autor

Fakheri-Fard M.

• University of Tabriz, Department of Water Engineering, Iran

autor

Dinpashoh Y.

• University of Tabriz, Department of Water Engineering, Iran

autor

Adamowski K.

• University of Ottawa, Department of Civil Engineering, Canada

Bibliografia

• ADAMOWSKI J., ADAMOWSKI K., BOUGADIS J. 2010. Influence of trend on short duration design storms. Water Resources Management. Vol. 24 p. 401–413.
• ADAMOWSKI J., CHAN H.F.A. 2011. Wavelet neural network conjunction model for groundwater level forecasting. Journal of Hydrology. Vol. 407. Iss. 1–4 p. 28–40. DOI: 10.1016/j.jhydrol.2011.06.013
• ADAMOWSKI J., CHAN H., PRASHER S., SHARDA V.N. 2012a. Comparison of multivariate adaptive regression splines with coupled wavelet transform artificial neural networks for runoff forecasting in Himalayan microwatersheds with limited data. Journal of Hydroinformatics. Vol. 3 p. 731–744.
• ADAMOWSKI J., PROKOPH A., ADAMOWSKI K. 2012b. Influence of the 11 year solar cycle on annual streamflow maxima in Southern Canada. Journal of Hydrology. Vol. 442 p. 55–62.
• ADAMOWSKI J., PROKOPH A., ADAMOWSKI K. 2013. A spectral analysis based methodology to detect climatological influences on daily urban water demand. Mathematical Geosciences. Vol. 45 p. 49–68.
• ADAMOWSKI J., SUN K. 2010. Development of a coupled wavelet transform and neural network method for flow forecasting of non-perennial rivers in semi-arid watersheds. Journal of Hydrology. Vol. 390. Iss. 1–2 p. 85–91. DOI: 10.1016/j.jhydrol.2010.06.033
• ADAMOWSKI K., PROKOPH A., ADAMOWSKI J. 2009. Development of a new method of wavelet aided trend detection and estimation. Hydrological Processes. Vol. 23 p. 2686–2696.
• AKANSU A.N., SERDIJN W.A., SELESNICK I.W. 2010. Emerging applications of wavelets: A review. Physical Communications. Vol. 3. Iss. 1 p. 1–18. DOI: 10.1016/j.phycom.2009.07.001.
• ARAGHI A., ADAMOWSKI J., NALLEY D., MALARD J. 2015. Using wavelet transforms to estimate surface temperature trends and dominant periodicities in Iran based on gridded reanalysis data. Atmospheric Research. Vol. 155 p. 52–72.
• BELAYNEH A., ADAMOWSKI J., KHALIL B., OZGA-ZIELINSKI B. 2014. Long-term SPI drought forecasting in the Awash River Basin in Ethiopia using wavelet-support vector regression models. Journal of Hydrology. Vol. 508 p. 418–429.
• BOX G.E.P., JENKINS G.M. 1976. Time series analysis: Forecasting and control. 4th ed. San Francisco, CA. Holden Day.
• BUTLER C., ADAMOWSKI J. 2015. Empowering marginalized communities in water resources management: Addressing inequitable practices in Participatory Model Building. Journal of Environmental Management. Vol. 153 p. 153–162.
• CAMPISI S., ADAMOWSKI J., ORON G. 2012. Forecasting urban water demand via wavelet- denoising and neural network models. Case study: City of Syracuse, Italy. Water Resources Management. Vol. 26 p. 3539–3558.
• CANNAS B., FANNI A., SEE L., SIAS G. 2006. Data preprocessing for river flow forecasting using neural networks: wavelet transforms and data partitioning. Physics and Chemistry of the Earth. Parts A/B/C. Vol. 31. Iss. 18 p. 1164–1171. DOI:10.1016/j.pce.2006.03.020.
• GOYAL M., BHARTI B., QUILTY J., ADAMOWSKI J., PANDEY A. 2014 Modeling of daily pan evaporation in sub tropical climates using ANN, LS-SVR, fuzzy logic, and ANFIS. Expert Systems with Applications, 41, 11 p. 5267–5276.
• HAIDARY A., AMIRI B.J., ADAMOWSKI J., FOHRER N., NAKANE K. 2013. Assessing the impacts of four land use types on the water quality of wetlands in Japan. Water Resources Management. Vol. 27 p. 2217–2229.
• HALBE J., ADAMOWSKI J., BENNETT E., PAHL-WOSTL C., FARAHBAKHSH K. 2014. Functional organization analysis for the design of sustainable engineering systems. Ecological Engineering. Vol. 73 p. 80–91.
• HALBE J., PAHL-WOSTL C., SENDZIMIR J., ADAMOWSKI J. 2013. Towards adaptive and integrated management paradigms to meet the challenges of water governance. Water Science and Technology: Water Supply. Vol. 67. Iss. 11 p. 2651–2660.
• INAM A., ADAMOWSKI J., HALBE J., PRASHER S. 2015. Using causal loop diagrams for the initialization of stakeholder engagement in soil salinity management in agricultural watersheds in developing countries: A case study in the Rechna Doab watershed, Pakistan. Journal of Environmental Management. Vol. 152 p. 251–267.
• KARRAN D., MORIN E., ADAMOWSKI J. 2014. Multi-step streamflow forecasting using data-driven non-linear methods in contrasting climate regimes. Journal of Hydroinformatics. Vol. 16. Iss. 3 p. 671–689.
• KIM T.W., VALDES J.B. 2003. Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering. Vol. 8. Iss. 6 p. 319–328. DOI: 10.1061/(ASCE)1084-0699(2003)8:6(319).
• KISI O., CIMEN M. 2012. Precipitation forecasting by using wavelet-support vector machine conjunction model. Engineering Applications of Artificial Intelligence. Vol. 25. Iss. 4 p. 783–792. DOI: 10.1016/j.engappai.2011.11.003.
• KISI O., SHIRI J. 2011. Precipitation forecasting using wavelet-genetic programming and wavelet-neuro-fuzzy conjunction models. Water Resource Management. Vol. 25. Iss. 13 p. 3135–3152. DOI: 10.1007/s11269-011-9849-3.
• KOLINJIVADI V., ADAMOWSKI J., KOSOY N. 2014. Recasting payments for ecosystem services (PES) in water resource management: A novel institutional approach. Ecosystem Services. Vol. 10 p. 144–154.
• LU R.Y. 2002. Decomposition of interdecadal and interannual components for North China rain fall in rainy season. Chinese Journal of Atmosphere. Vol. 26 p. 611– 624 (in Chinese).
• NALLEY D., ADAMOWSKI J., KHALIL B. 2012. Using discrete wavelet transforms to analyze trends in streamflow and precipitation in Quebec and Ontario (1954–2008). Journal of Hydrology. Vol. 475 p. 204–228.
• NALLEY D., ADAMOWSKI J., KHALIL B., OZGA-ZIELINSKI B. 2013. Trend detection in surface air temperature in Ontario and Quebec, Canada during 1967–2006 using the discrete wavelet transform. Atmospheric Research. Vol. 132/133 p. 375–398.
• NASON G.P., VON SACHS R. 1999. Wavelets in time series analysis. Philosophical Transactions of the Royal Society A. Vol. 357. Iss. 1760 p. 2511–2526. DOI: 10.1098/rsta.1999.0445
• NOURANI V., BAGHANAM A., ADAMOWSKI J., KISI O. 2014. Applications of hybrid wavelet-artificial intelligence models in hydrology: A review. Journal of Hydrology. Vol. 514 p. 358–377.
• PINGALE S., KHARE D., JAT M., ADAMOWSKI J. 2014. Spatial and temporal trends of mean and extreme rainfall and temperature for the 33 urban centres of the arid and semi-arid state of Rajasthan, India. Atmospheric Research. Vol. 138 p. 73–90.
• RATHINASAMY M., ADAMOWSKI J., KHOSA R. 2014. Multiscale streamflow forecasting using a new Bayesian model average based ensemble multi-wavelet Volterra nonlinear method. Journal of Hydrology. Vol. 507 p. 186–200.
• RATHINASAMY M., KHOSA R., ADAMOWSKI J., CH S., PARTHEEPAN G., ANAND J., NARSIMLU B. 2015. Wavelet-based multiscale performance analysis: An approach to assess and improve hydrological models. Water Resources Research. Vol. 50. Iss. 12 p. 9721–9737. DOI: 10.1002/2013WR014650.
• SAADAT H., ADAMOWSKI J., BONNELL R., SHARIFI F., NAMDAR M., ALE-EBRAHIM S. 2011. Land use and land cover classification over a large area in Iran based on single date analysis of satellite imagery. Journal of Photogrammetry and Remote Sensing. Vol. 66 p. 608–619.
• SALAS J.D., DELLEUR J.W., YEVJEVICH V., LANE W.L. 1980. Applied modeling of hydrological time series. Littleton, CO. Water Resources Publications. ISBN 978-09-18334-37-4 pp. 484.
• SANTOS C.A.G., MORAIS B.S., SILVA G.B.L. 2009. Drought forecast using an artificial neural network for three hydrological zones in San Francisco River basin, Brazil. IAHS Publication. Vol. 333 p. 302–312.
• SANTOS C.A.G., SRINIVASAN V.S., SUZUKI K., WATANABE M. 2003. Application of an optimization technique to a physically based erosion model. Hydrological Processes. Vol. 17. Iss. 5 p. 989–1003. DOI: 10.1002/hyp.1176.
• SELESNICK I.W., BARANIUK R.G., KINGSBURY N.C. 2005. The dual-tree complex wavelet transform. Signal Processing Magazine, IEEE. Vol. 22. Iss. 6 p. 123–151. DOI: 10.1109/MSP.2005.1550194
• STRAITH D., ADAMOWSKI J., REILLY K. 2014. Exploring the attributes, strategies and contextual knowledge of champions of change in the Canadian water sector. Canadian Water Resources Journal. Vol. 39. Iss. 3 p. 255–269.
• TANTANEE S., PATAMATAMMAKUL S., OKI T., SRIBOONLUE V., PREMPREE T. 2005. Coupled wavelet-autoregressive model for annual rainfall prediction. Journal of Environmental Hydrology. Vol. 13. Paper 18 p. 1–8.
• TIWARI M., ADAMOWSKI J. 2014. Urban water demand forecasting and uncertainty assessment using ensemble wavelet-bootstrap-neural network models. Water Resources Research. Vol. 49. Iss. 10 p. 6486–6507.
• TIWARI M., ADAMOWSKI J. 2015. Medium-term urban water demand forecasting with limited data using an ensemble wavelet-bootstrap machine-learning approach. Journal of Water Resources Planning and Management. Vol. 141. No. 2.

Uwagi

PL

Opracowanie ze środków MNiSW w ramach umowy 812/P-DUN/2016 na działalność upowszechniającą naukę.