Skip to main content
SpringerLink
Log in

Assessing the generalization of forecasting ability of machine learning and probabilistic models for complex climate characteristics

  • ORIGINAL PAPER
  • Published:
Stochastic Environmental Research and Risk Assessment Aims and scope Submit manuscript

Abstract

Climate changes and global warming increase risk of recurrent extreme and complex climatic features. It necessitates accurate modeling and forecasting of climate phenomena for sustainable development goals. However, machine learning algorithms and advanced statistical models are extensively employed to analyze complex data and make predictions related to climate phenomena. It is important to have comprehensive knowledge to use these models and consider their potential implications. This study aims to evaluate and compare some popular machine learning and probabilistic methods by analyzing various time series indices associated with precipitation and temperature. For application, time series data of Standardized Precipitation Temperature Index (SPTI), Standardized Temperature Index (STI), Standardized Compound Drought and Heat Index (SCDHI), and Biased Diminished Weighted Regional Drought Index (BDWRDI) are used from various meteorological regions of Pakistan. The performance of each algorithm is compared using Residual Mean Square Error (RMSE) and Mean Average Error (MAE). The outcomes associated with this research indicate a higher preference of neural networks over machine learning methods in the training sets. However, the efficiency varies from model to model, indicator to indicator, time scale to time scale, and location to location during the testing phase. The most appropriate models are found by considering a list of candidates forecasting models and investigating the performance of each model.

This is a preview of subscription content, log in via an institution to check access.

Access this article

Log in via an institution

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Institutional subscriptions

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7

Similar content being viewed by others

Data availability

The data that support the findings of this study are available from the corresponding author upon reasonable request.

References

  • Abramowitz M, Stegun IA (1965) With formulas, graphs, and mathematical tables. Natl Bur Standa Appl Math Ser E 55:953

  • Aghelpour P, Bahrami-Pichaghchi H, Varshavian V (2021) Hydrological drought forecasting using multi-scalar streamflow drought index, stochastic models and machine learning approaches, in northern Iran. Stoch Environ Res Risk Assess 35(8):1615–1635

    Article  Google Scholar 

  • Ali Z, Hussain I, Faisal M, Nazir HM, Hussain T, Shad MY, Mohamd Shoukry A, Hussain Gani S (2017a) Forecasting drought using multilayer perceptron artificial neural network model. Adv Meteorol 2017:5681308

  • Ali Z, Hussain I, Faisal M, Nazir HM, Moemen MAE, Hussain T, Shamsuddin S (2017b) A novel multi-scalar drought index for monitoring drought: the standardized precipitation temperature index. Water Resour Manage 31:4957–4969

    Article  Google Scholar 

  • Ali F, Li BZ, Ali Z (2022) A new weighting scheme for diminishing the effect of extreme values in regional drought analysis. Water Resour Manage 36(11):4099–4114

    Article  Google Scholar 

  • Assimakopoulos V, Nikolopoulos K (2000) The theta model: a decomposition approach to forecasting. Int J Forecast 16(4):521–530

    Article  Google Scholar 

  • Athanasopoulos G, Hyndman RJ, Kourentzes N, Petropoulos F (2017) Forecasting with temporal hierarchies. Eur J Oper Res 262(1):60–74

    Article  Google Scholar 

  • Bonaccorso B, Cammalleri C, Loukas A, Kreibich H (2022) Preface: recent advances in drought and water scarcity monitoring, modelling, and forecasting. Nat Hazard 22(6):1857–1862

    Article  Google Scholar 

  • Chatfield C (1978) The holt-winters forecasting procedure. Appl Stat 27:264–279

    Article  Google Scholar 

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

    Article  Google Scholar 

  • Docheshmeh Gorgij A, Alizamir M, Kisi O, Elshafie A (2022) Drought modelling by standard precipitation index (SPI) in a semi-arid climate using deep learning method: long short-term memory. Neural Comput Applic 1–18

  • Ebtehaj I, Bonakdari H (2016) Bed load sediment transport estimation in a clean pipe using multilayer perceptron with different training algorithms. KSCE J Civ Eng 20:581–589

    Article  Google Scholar 

  • Farahmand A, AghaKouchak A (2015) A generalized framework for deriving nonparametric standardized drought indicators. Adv Water Resour 76:140–145

    Article  Google Scholar 

  • Fioruci JA, Pellegrini TR, Louzada F, Petropoulos F (2015) The optimised theta method. arXiv preprint, arXiv:1503.03529

  • Fiorucci JA, Pellegrini TR, Louzada F, Petropoulos F, Koehler A (2016) Models for optimising the theta method and their relationship to state space models. Int J Forecast 32(4):1151–1161

    Article  Google Scholar 

  • Gamble DW, Campbell D, Allen TL, Barker D, Curtis S, McGregor D, Popke J (2010) Climate change, drought, and Jamaican agriculture: local knowledge and the climate record. Ann Assoc Am Geogr 100(4):880–893

    Article  Google Scholar 

  • García-León D, Casanueva A, Standardi G, Burgstall A, Flouris AD, Nybo L (2021) Current and projected regional economic impacts of heatwaves in Europe. Nat Commun 12(1):5807

    Article  Google Scholar 

  • Gleick PH (2014) Water, drought, climate change, and conflict in Syria. Weather Clim Soc 6(3):331–340

    Article  Google Scholar 

  • Guan X, Zang Y, Meng Y, Liu Y, Lv H, Yan D (2021) Study on spatiotemporal distribution characteristics of flood and drought disaster impacts on agriculture in China. Int J Disaster Risk Reduct 64:102504

    Article  Google Scholar 

  • Guisan A, Thuiller W (2005) Predicting species distribution: offering more than simple habitat models. Ecol Lett 8(9):993–1009

    Article  Google Scholar 

  • Harvey AC (1989) Forecasting, structural time series models and the kalman filter. Cambridge University Press, UK

  • Haslett J, Raftery AE (1989) Space-time modelling with long-memory dependence: assessing Ireland’s wind power resource. J Roy Stat Soc: Ser C (Appl Stat) 38(1):1–21

    Google Scholar 

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

    Article  CAS  Google Scholar 

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

    Article  Google Scholar 

  • Hotez P (2021) Preventing the next pandemic: vaccine diplomacy in a time of anti-science. Johns Hopkins University Press, Baltimore

  • Huang GB, Zhu QY, Siew CK (2006) Extreme learning machine: theory and applications. Neurocomputing 70(1–3):489–501

    Article  Google Scholar 

  • Hyndman RJ, Athanasopoulos G (2018) Forecasting: principles and practice. Otexts, Australia

    Google Scholar 

  • Hyndman RJ, Khandakar Y (2008) Automatic time series forecasting: the forecast package for R. J Stat Softw 27:1–22

    Article  Google Scholar 

  • Hyndman RJ, Koehler AB, Snyder RD, Grose S (2002) A state space framework for automatic forecasting using exponential smoothing methods. Int Forecast 18(3):439–454

    Article  Google Scholar 

  • Kożuch A, Cywicka D, Adamowicz K (2023) A Comparison of artificial neural network and time series models for timber price forecasting. Forests 14(2):177

    Article  Google Scholar 

  • Lai Y, Dzombak DA (2020) Use of the Autoregressive Integrated Moving Average (ARIMA) model to forecast near-term regional temperature and precipitation. Weather Forecast 35(3):959–976

    Article  Google Scholar 

  • Li J, Wang Z, Wu X, Zscheischler J, Guo S, Chen X (2021) A standardized index for assessing sub-monthly compound dry and hot conditions with application in China. Hydrol Earth Syst Sci 25(3):1587–1601

    Article  Google Scholar 

  • Manzoor Z, Ehsan M, Khan MB, Manzoor A, Akhter MM, Sohail MT, ... & Abioui M (2022) Floods and flood management and its socio-economic impact on Pakistan: A review of the empirical literature. Front Environ Sci 10:2480

  • Marengo JA (2009) Long-term trends and cycles in the hydrometeorology of the Amazon basin since the late 1920s. Hydrol Process 23(22):3236–3244

    Article  Google Scholar 

  • McCulloch WS, Pitts W (1943) A logical calculus of the ideas immanent in nervous activity. Bull Math Biophys 5:115–133

    Article  Google Scholar 

  • Metzger KB, Ito K, Matte TD (2010) Summer heat and mortality in New York City: how hot is too hot? Environ Health Perspect 118(1):80–86

    Article  Google Scholar 

  • Mousavi SR, Rezaei M (2011) Nanotechnology in agriculture and food production. J Appl Environ Biol Sci 1(10):414–419

    Google Scholar 

  • Mukherjee S, Mishra A, Trenberth KE (2018) Climate change and drought: a perspective on drought indices. Curr Clim Change Rep 4:145–163

    Article  Google Scholar 

  • Perkins-Kirkpatrick SE, Lewis SC (2020) Increasing trends in regional heatwaves. Nat Commun 11(1):3357

    Article  CAS  Google Scholar 

  • Petris G, Petrone S (2011) State space models in R. J Stat Softw 41:1–25

    Article  Google Scholar 

  • Raza MA, Almazah MM, Ali Z, Hussain I, Al-Duais FS (2022) Application of extreme learning machine algorithm for drought forecasting. Complexity 2022:1–28

    Article  Google Scholar 

  • Ripley BD (2011) Time series in R 1.5.0. R News 2:2–7

  • Rolnick D, Donti PL, Kaack LH, Kochanski K, Lacoste A, Sankaran K, ... & Bengio Y (2022) Tackling climate change with machine learning. ACM Comput Surv (CSUR) 55(2):1–96

  • Rosenblatt F (1962) Principales of Neurodynamics. Spartan, New York

    Google Scholar 

  • Russo S, Dosio A, Graversen RG, Sillmann J, Carrao H, Dunbar MB, ... & Vogt JV (2014) Magnitude of extreme heat waves in present climate and their projection in a warming world. J Geophys Res Atmos 119(22):12–500

  • Shah D, Mishra V (2020) Integrated Drought Index (IDI) for drought monitoring and assessment in India. Water Resour Res 56(2):e2019WR026284

  • Stagge JH, Tallaksen LM, Gudmundsson L, Van Loon AF, Stahl K (2015) Candidate distributions for climatological drought indices (SPI and SPEI). Int J Climatol 35(13):4027–4040

    Article  Google Scholar 

  • Velo A, Pérez FF, Tanhua T, Gilcoto M, Ríos AF, Key RM (2013) Total alkalinity estimation using MLR and neural network techniques. J Mar Syst 111:11–18

    Article  Google Scholar 

  • Wang GC, Zhang Q, Band SS, Dehghani M, Chau KW, Tho QT, ... & Mosavi A (2022a) Monthly and seasonal hydrological drought forecasting using multiple extreme learning machine models. Eng Applic Comput Fluid Mech 16(1):1364–1381

  • Wang T, Tu X, Singh VP, Chen X, Lin K, Lai R, Zhou Z (2022b) Socioeconomic drought analysis by standardized water supply and demand index under changing environment. J Clean Prod 347:131248

    Article  Google Scholar 

  • Xie W, Zhou B, You Q, Zhang Y, Ullah S (2020) Observed changes in heat waves with different severities in China during 1961–2015. Theor Appl Climatol 141:1529–1540

    Article  Google Scholar 

  • Zhang Y, Yang H, Cui H, Chen Q (2020) Comparison of the ability of ARIMA, WNN and SVM models for drought forecasting in the Sanjiang Plain, China. Nat Resour Res 29:1447–1464

    Article  Google Scholar 

  • Zscheischler J, Michalak AM, Schwalm C, Mahecha MD, Huntzinger DN, Reichstein M, ... & Zeng N (2014) Impact of large‐scale climate extremes on biospheric carbon fluxes: An intercomparison based on MsTMIP data. Glob Biogeochem Cycles 28(6):585–600

Download references

Acknowledgements

The authors extend their appreciation to the Deanship of Scientific Research at King Khalid University for funding this work through large group Research Project under grant number RGP2/171/44.

Author information

Authors and Affiliations

  1. College of Statistical Sciences, University of the Punjab, Lahore, Pakistan

    Aamina Batool, Zulfiqar Ali & Muhammad Mohsin

  2. College of Computer Science, King Khalid University, Abha, Saudi Arabia

    Atef Masmoudi

  3. Civil Engineering, Engineering Faculty, Siirt University, Siirt, Turkey

    Veysi Kartal

  4. Department of Statistics, University of Wah, Rawalpindi, Pakistan

    Samina Satti

Authors
  1. Aamina Batool
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Zulfiqar Ali
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Muhammad Mohsin
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Atef Masmoudi
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Veysi Kartal
    View author publications

    You can also search for this author in PubMed Google Scholar

  6. Samina Satti
    View author publications

    You can also search for this author in PubMed Google Scholar

Contributions

Aamina Batool and Zulfiqar Ali conceived the presented idea. Aamina Batool developed the theory and performed the computations. Muhammad Mohsin verified the analytical methods and computations. Atef MASMOUDI, Veysi Kartal and Samina Satti helped in technical aspects of the study.  All the authors discussed the results and contributed to the final manuscript.

Corresponding author

Correspondence to Zulfiqar Ali.

Ethics declarations

Ethical approval

Not Applicable.

Consent to participate

Not Applicable.

Consent to publish

Not Applicable.

Competing interests

The authors declare no competing interests.

Additional information

Publisher's Note

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

Rights and permissions

Springer Nature or its licensor (e.g. a society or other partner) holds exclusive rights to this article under a publishing agreement with the author(s) or other rightsholder(s); author self-archiving of the accepted manuscript version of this article is solely governed by the terms of such publishing agreement and applicable law.

Reprints and permissions

About this article

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Batool, A., Ali, Z., Mohsin, M. et al. Assessing the generalization of forecasting ability of machine learning and probabilistic models for complex climate characteristics. Stoch Environ Res Risk Assess (2024). https://doi.org/10.1007/s00477-024-02721-3

Download citation

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s00477-024-02721-3

Keywords

Search

Navigation