Skip to main content

A comparison of data-driven methods in prediction of weather patterns in central Croatia

Abstract

The prediction of future weather patterns has recently become a very important research area due to the ongoing climate change process which causes extreme weather events and rapidly changing weather patterns. In this paper we compare the prediction accuracy of eight data-driven methods, which had been developed for time series prediction, on future weather patterns in central Croatia. The evaluated methods are Seasonal naïve, AutoRegressive Integrated Moving Average (ARIMA), Error-Trend-Seasonality (ETS), Exponential smoothing state space model with Box-Cox transformation (TBATS), Dynamic Harmonic Regression (DHR), Neural Network AutoRegression (NNAR), Support Vector Regression (SVR) and Long Short-Term Memory (LSTM). In our experimental evaluation, we use a historical data from 1961 to 2017 that contains temperature, air pressure and precipitation values for eight weather stations in central Croatia, and indices from two atmospheric oscillations, namely North Atlantic Oscillation (NAO) and Arctic Oscillation (AO). The results of our evaluation show that SVR is the best method, and that DHR and NNAR methods are also better than the other evaluated methods, as far as the accuracy of prediction is concerned. Among DHR and NNAR methods, DHR method is better for the prediction of temperature and air pressure, while NNAR method is better for the prediction of precipitation. Additionally, our evaluation shows that SVR, DHR and NNAR methods achieve a better prediction accuracy when oscillation indices are included as additional predictors.

This is a preview of subscription content, access via your institution.

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6

Availability of data

Publicly available datasets of daily AO and NAO indices were used in this study. This data can be found in a public repository of the National Weather Service – Climate Prediction Center. The data from eight analyzed weather stations in Croatia that we used in this study are available upon request from the Croatian Meteorological and Hydrological Service. The data are not publicly available due to business policy, but is available free of charge for scientific and research purposes.

Notes

  1. https://meteo.hr/proizvodi_e.php?param=services

  2. ftp://ftp.cpc.ncep.noaa.gov/cwlinks

  3. https://www.r-project.org/about.html

  4. https://www.rstudio.com/

  5. https://keras.rstudio.com/

  6. https://www.tensorflow.org/

  7. A stationary time series is one whose statistical properties do not depend on the time at which the series is observed.

References

  • Akaike H (1974) A new look at the statistical model identification. IEEE Trans Autom Control 19(6):716–723

    Article  Google Scholar 

  • Akaikei H (1973) Information theory and an extension of maximum likelihood principle. In: Proc. 2nd Int. Symp. on Information Theory, pp 267–281

  • Ambaum MHP, Hoskins BJ, Stephenson DB (2001) Arctic oscillation or north atlantic oscillation?. J Clim 14(16):3495–3507

    Article  Google Scholar 

  • Arampongsanuwat S, Meesad P (2011) Prediction of pm10 using support vector regression. In: International Conference on Information and Electronics Engineering, IACSIT Press. Singapore, vol 6

  • Athanasiadis PJ, Bellucci A, Scaife AA, Hermanson L, Materia S, Sanna A, Borrelli A, MacLachlan C, Gualdi S (2017) A multisystem view of wintertime nao seasonal predictions. J Clim 30(4):1461–1475

    Article  Google Scholar 

  • Barnston AG, Livezey RE (1987) Classification, seasonality and persistence of low-frequency atmospheric circulation patterns. Monthly Weather Rev 115(6):1083–1126

    Article  Google Scholar 

  • Barry RG, Chorley RJ (2009) Atmosphere, weather and climate. Routledge

  • Bauer P, Thorpe A, Brunet G (2015) The quiet revolution of numerical weather prediction. Nature 525(7567):47–55

    Article  Google Scholar 

  • Bice D, Montanari A, Vučetić V, Vučetić M (2012) The influence of regional and global climatic oscillations on croatian climate. Int J Climatol 32(10):1537–1557

    Article  Google Scholar 

  • Boser BE, Guyon IM, Vapnik VN (1992) A training algorithm for optimal margin classifiers. In: Proceedings of the fifth annual workshop on Computational learning theory, pp 144–152

  • Box GEP, Jenkins GM (1970) Time series analysis; forecasting and control. Holden-Day, San Francisco

    Google Scholar 

  • Brown RG (1959) Statistical forecasting for inventory control. McGraw/Hill

  • Castro A, Vidal MI, Calvo AI, Fernández-Raga M, Fraile R (2011) May the nao index be used to forecast rain in spain?. Atmósfera 24(3):251–265

    Google Scholar 

  • Cattiaux J, Vautard R, Cassou C, Yiou P, Masson-Delmotte V, Codron F (2010) Winter 2010 in europe: A cold extreme in a warming climate. Geophys Res Lett 37(20)

  • Chandra R, Goyal S, Gupta R (2021) Evaluation of deep learning models for multi-step ahead time series prediction. IEEE Access 9:83105–83123

    Article  Google Scholar 

  • Chen WY, Van den Dool H (2003) Sensitivity of teleconnection patterns to the sign of their primary action center. Monthly Weather Rev 131(11):2885–2899

    Article  Google Scholar 

  • Chevalier RF, Hoogenboom G, McClendon RW, Paz JA (2011) Support vector regression with reduced training sets for air temperature prediction: a comparison with artificial neural networks. Neural Comput Appl 20(1):151–159

    Article  Google Scholar 

  • Cleveland RB, Cleveland WS, McRae JE, Terpenning I (1990) Stl: A seasonal-trend decomposition. J Offic Stat 6(1):3–73

    Google Scholar 

  • Cohen J, Coumou D, Hwang J, Mackey L, Orenstein P, Totz S, Tziperman E (2019) S2s reboot: An argument for greater inclusion of machine learning in subseasonal to seasonal forecasts. Wiley Interdiscip Rev Clim Chang 10(2):e00567

    Article  Google Scholar 

  • De Livera AM, Hyndman RJ, Snyder RD (2011) Forecasting time series with complex seasonal patterns using exponential smoothing. J Amer Stat Assoc 106(496):1513–1527

    Article  Google Scholar 

  • deCastro M, Lorenzo N, Taboada JJ, Sarmiento M, Alvarez I, Gomez-Gesteira M (2006) Influence of teleconnection patterns on precipitation variability and on river flow regimes in the miño river basin (nw iberian peninsula). Clim Res 32(1):63–73

    Article  Google Scholar 

  • Deo RC, Salcedo-Sanz S, Carro-Calvo L, Saavedra-Moreno B (2018) Drought prediction with standardized precipitation and evapotranspiration index and support vector regression models. In: Integrating disaster science and management. Elsevier, pp 151–174

  • Diez-Sierra J, del Jesus M (2020) Long-term rainfall prediction using atmospheric synoptic patterns in semi-arid climates with statistical and machine learning methods. J Hydrol 586:124789

    Article  Google Scholar 

  • Drucker H, Burges CJ, Kaufman L, Smola A, Vapnik V (1996) Support vector regression machines. Adv Neural Inf Process Syst 9

  • Dutta R, Maity R (2020) Temporal networks-based approach for nonstationary hydroclimatic modeling and its demonstration with streamflow prediction. Water Resour Res 56(8):e2020WR027086

    Article  Google Scholar 

  • Efthymiadis D, Goodess CM, Jones PD (2011) Trends in mediterranean gridded temperature extremes and large-scale circulation influences. Nat Hazards Earth Syst Sci 11(8):2199– 2214

    Article  Google Scholar 

  • Field AP (2014) K endall’s coefficient of concordance. Wiley StatsRef: Statistics Reference Online

  • García NO, Gimeno L, De La Torre L, Nieto R, Añel JA (2005) North atlantic oscillation (nao) and precipitation in galicia (spain). Atmósfera 18(1):25–32

    Google Scholar 

  • Ham Y-G, Kim J-H, Luo J-J (2019) Deep learning for multi-year enso forecasts. Nature 573(7775):568–572

    Article  Google Scholar 

  • Hewage P, Behera A, Trovati M, Pereira E, Ghahremani M, Palmieri F, Liu Y (2020) Temporal convolutional neural (tcn) network for an effective weather forecasting using time-series data from the local weather station. Soft Comput 24(21):16453–16482

    Article  Google Scholar 

  • Hochreiter S, Schmidhuber J (1997) Long short-term memory. Neural Comput 9(8):1735–1780

    Article  Google Scholar 

  • Holland MM (2003) The north atlantic oscillation–arctic oscillation in the ccsm2 and its influence on arctic climate variability. J Clim 16(16):2767–2781

    Article  Google Scholar 

  • Holmstrom M, Liu D, Vo C (2016) Machine learning applied to weather forecasting. Meteorol Appl

  • Holt CC (2004) Forecasting seasonals and trends by exponentially weighted moving averages. Int J Forecast 20(1):5–10

    Article  Google Scholar 

  • Hornik K (1993) Some new results on neural network approximation. Neural Netw 6(8):1069–1072

    Article  Google Scholar 

  • Hurrell JW (1995) Decadal trends in the north atlantic oscillation: Regional temperatures and precipitation. Science 269(5224):676–679

    Article  Google Scholar 

  • Hurrell JW, Deser C (2010) North atlantic climate variability: the role of the north atlantic oscillation. J Mar Syst 79(3-4):231–244

    Article  Google Scholar 

  • Hurrell JW, Kushnir Y, Ottersen G, Visbeck M (2003) An overview of the north atlantic oscillation. Geophys Monograph-Amer Geophys Union 134:1–36

    Google Scholar 

  • Hurrell JW, Van Loon H (1997) Decadal variations in climate associated with the north atlantic oscillation. In: Climatic change at high elevation sites. Springer, pp 69–94

  • Hurvich CM, Tsai C-L (1993) A corrected akaike information criterion for vector autoregressive model selection. J Time Ser Anal 14(3):271–279

    Article  Google Scholar 

  • Hwang J, Orenstein P, Cohen J, Pfeiffer K, Mackey L (2019) Improving subseasonal forecasting in the western us with machine learning. In: Proceedings of the 25th ACM SIGKDD International Conference on Knowledge Discovery & Data Mining, pp 2325–2335

  • Hyndman RJ, Athanasopoulos G (2020) Forecasting: principles and practice, 2nd edn. OTexts, Melbourne

    Google Scholar 

  • Hyndman RJ, Koehler AB (2006) Another look at measures of forecast accuracy. Int J Forecast 22(4):679–688

    Article  Google Scholar 

  • Jones PD, Osborn TJ, Briffa KR (2003) Pressure-based measures of the north atlantic oscillation (nao): A comparison and an assessment of changes in the strength of the nao and in its influence on surface climate parameters. North Atlantic Oscillation: Clim Signif Environ Impact 134:51–62

    Google Scholar 

  • Jovanović G, Reljin I, Reljin B (2008) The influence of arctic and north atlantic oscillation on precipitation regime in serbia. In: IOP Conference Series: Earth and Environmental Science, vol 4. IOP Publishing, p 012025

  • Junqué de Fortuny E, Martens D, Provost F (2013) Predictive modeling with big data: is bigger really better?. Big Data 1(4):215–226

    Article  Google Scholar 

  • Kajewska-Szkudlarek J (2020) Clustering approach to urban rainfall time series prediction with support vector regression model. Urban Water J 17(3):235–246

    Article  Google Scholar 

  • King MP, Herceg-Bulić I, Kucharski F, Keenlyside N (2018) Interannual tropical pacific sea surface temperature anomalies teleconnection to northern hemisphere atmosphere in november. Clim Dyn 50(5):1881–1899

    Article  Google Scholar 

  • Kryjov VN (2002) The influence of the winter arctic oscillation on the northern russia spring temperature. Int J Climatol: J R Meteorol Soc 22(7):779–785

    Article  Google Scholar 

  • Liu X, Xu Z, Peng D, Wu G (2019) Influences of the north atlantic oscillation on extreme temperature during the cold period in china. Int J Climatol 39(1):43–49

    Article  Google Scholar 

  • Maity R, Chanda K, Dutta R, Ratnam JV, Nonaka M, Behera S (2020) Contrasting features of hydroclimatic teleconnections and the predictability of seasonal rainfall over east and west japan. Meteorol Appl 27(1):e1881

    Article  Google Scholar 

  • Mercer A (2020) Predictability of common atmospheric teleconnection indices using machine learning. Procedia Comput Sci 168:11–18

    Article  Google Scholar 

  • Paniagua-Tineo A, Salcedo-Sanz S, Casanova-Mateo C, Ortiz-García EG, Cony MA, Hernández-Martín E (2011) Prediction of daily maximum temperature using a support vector regression algorithm. Renew Energy 36(11):3054–3060

    Article  Google Scholar 

  • Pham QB, Yang T-C, Kuo C-M, Tseng H-W, Yu P-S (2019) Combing random forest and least square support vector regression for improving extreme rainfall downscaling. Water 11(3):451

    Article  Google Scholar 

  • Qian QF, Jia XJ, Lin H (2020) Machine learning models for the seasonal forecast of winter surface air temperature in north america. Earth Space Sci 7(8):e2020EA001140

    Article  Google Scholar 

  • Riaz SMF, Iqbal MJ, Hameed S (2017) Impact of the north atlantic oscillation on winter climate of germany. Tellus A: Dyn Meteorol Oceanogr 69(1):1406263

    Article  Google Scholar 

  • Rogerson PA (2019) Statistical methods for geography: a student’s guide. Sage

  • Rostam MG, Sadatinejad SJ, Malekian A (2020) Precipitation forecasting by large-scale climate indices and machine learning techniques. J Arid Land:1–11

  • Sapankevych NI, Sankar R (2009) Time series prediction using support vector machines: a survey. IEEE Comput Intell Mag 4(2):24–38

    Article  Google Scholar 

  • Sen AK, Ogrin D (2016) Analysis of monthly, winter, and annual temperatures in zagreb, croatia, from 1864 to 2010: the 7.7-year cycle and the north atlantic oscillation. Theor Appl Climatol 123(3-4):733–739

    Article  Google Scholar 

  • Singh N, Chaturvedi S, Akhter S (2019) Weather forecasting using machine learning algorithm. In: 2019 International Conference on Signal Processing and Communication (ICSC). IEEE, pp 171–174

  • Slonosky VC, Jones PD, Davies TD (2001) Atmospheric circulation and surface temperature in europe from the 18th century to 1995. Int J Climatol: J R Meteorol Soc 21(1):63–75

    Article  Google Scholar 

  • Suzuki Y, Kaneda Y, Mineno H (2015) Analysis of support vector regression model for micrometeorological data prediction. Comput Sci Inf Technol 3(2):37–48

    Google Scholar 

  • Thompson DWJ, Wallace JM (1998) The arctic oscillation signature in the wintertime geopotential height and temperature fields. Geophys Res Lett 25(9):1297–1300

    Article  Google Scholar 

  • Tian Y, Xu Y-P, Wang G (2018) Agricultural drought prediction using climate indices based on support vector regression in xiangjiang river basin. Sci Total Environ 622:710–720

    Article  Google Scholar 

  • Trigo RM, Osborn TJ, Corte-Real JM (2002) The north atlantic oscillation influence on europe: climate impacts and associated physical mechanisms. Clim Res 20(1):9–17

    Article  Google Scholar 

  • Tseng K-C, Barnes EA, Maloney E (2020) The importance of past mjo activity in determining the future state of the midlatitude circulation. J Clim 33(6):2131–2147

    Article  Google Scholar 

  • Van den Dool HM, Saha S, Johansson AAke (2000) Empirical orthogonal teleconnections. J Clim 13(8):1421–1435

    Article  Google Scholar 

  • Wallace JM (2000) North atlantic oscillatiodannular mode: two paradigms—one phenomenon. Q J R Meteorol Soc 126(564):791–805

    Google Scholar 

  • Wang L, Ting M, Kushner PJ (2017) A robust empirical seasonal prediction of winter nao and surface climate. Sci Rep 7(1):1–9

    Article  Google Scholar 

  • Weizhen H, Zhengqiang L, Yuhuan Z, Hua X, Ying Z, Kaitao L, Donghui L, Peng W, Yan M (2014) Using support vector regression to predict pm10 and pm2. 5. In: IOP conference series: earth and environmental science, vol 17. IOP Publishing, p 012268

  • Wettstein JJ, Mearns LO (2002) The influence of the north atlantic–arctic oscillation on mean, variance, and extremes of temperature in the northeastern united states and canada. J Clim 15(24):3586–3600

    Article  Google Scholar 

  • Weyn JA, Durran DR, Caruana R (2019) Can machines learn to predict weather? using deep learning to predict gridded 500-hpa geopotential height from historical weather data. J Adv Model Earth Syst 11(8):2680–2693

    Article  Google Scholar 

  • Whittle P (1951) Hypothesis testing in time series analysis, vol 4. Almqvist & Wiksells Boktr

  • Winters PR (1960) Forecasting sales by exponentially weighted moving averages. Manag Sci 6 (3):324–342

    Article  Google Scholar 

  • Yakut E, Süzülmüş S (2020) Modelling monthly mean air temperature using artificial neural network, adaptive neuro-fuzzy inference system and support vector regression methods: A case of study for turkey. Netw Comput Neural Syst 31(1-4):1–36

    Article  Google Scholar 

  • Young PC, Pedregal DJ, Tych W (1999) Dynamic harmonic regression. J Forecast 18 (6):369–394

    Article  Google Scholar 

Download references

Funding

This research has been supported in part by the European Regional Development Fund under the grant KK.01.1.1.01.0009 (DATACROSS), which includes the salary of a PhD student and reimbursement for attending scientific conferences. This work has been supported in part by Croatian Science Foundation under the project UIP-2017-05-9066, which includes the salary of a PhD student, cost of equipment on which our experiments are performed and reimbursement for attending scientific conferences.

Author information

Authors and Affiliations

Authors

Contributions

Conceptualization, D.K., K.P., M.M. and M.P.; methodology, D.K., K.P., M.M. and M.P.; software, D.K. and K.P.; validation, D.K., K.P., M.M. and M.P.; formal analysis, D.K., K.P. and M.M.; investigation, D.K., K.P., M.M. and M.P.; resources, K.P. and M.M.; data curation, D.K.; writing—original draft preparation, D.K., K.P., M.M. and M.P.; writing—review and editing, D.K., K.P., M.M. and M.P.; visualization, D.K.; supervision, K.P. and M.M.; project administration, K.P.; funding acquisition, K.P. All authors have read and agreed to the published version of the manuscript.

Corresponding author

Correspondence to Krešimir Pripužić.

Ethics declarations

Ethics approval

Not applicable.

Consent to participate

Not applicable.

Conflicts of interest

The authors do not have other interests that could impart bias on the work submitted for publication.

Consent for publication

Not applicable.

Additional information

Communicated by: H. Babaie

Publisher’s note

Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Katušić, D., Pripužić, K., Maradin, M. et al. A comparison of data-driven methods in prediction of weather patterns in central Croatia. Earth Sci Inform 15, 1249–1265 (2022). https://doi.org/10.1007/s12145-022-00792-w

Download citation

  • Received:

  • Accepted:

  • Published:

  • Issue Date:

  • DOI: https://doi.org/10.1007/s12145-022-00792-w

Keywords

  • Weather prediction
  • Climatology
  • Machine learning
  • Statistics