Skip to main content

Advertisement

SpringerLink
Log in

Hydrological drought class early warning using support vector machines and rough sets

  • Original Article
  • Published:
Environmental Earth Sciences Aims and scope Submit manuscript

Abstract

Prediction of drought severity class/state can provide useful insight into preparedness actions. In this study, hydrological drought class, as determined by the standardized hydrological drought index (SHDI), was predicted. SHDI1 and SHDI3 drought classes were determined in seven and nine drought class systems. Support vector regression (SVR), support vector classification (SVC), and rough set theory (RST) were tested and compared as forecast modelling tools. Different combination of historic monthly streamflow and precipitation time series, or values/classes of SHDI and SPI, were considered as predictors to tackle the following question; is it possible to achieve the same or better accuracy by directly predicting the drought class, instead of predicting the streamflow (or drought index values) first and subsequently estimating the qualitative severity (class) of the drought? The results were more accurate in case of considering drought classes as inputs/output. However, the number of drought/wet classes may affect prediction accuracy. Prediction in case of fewer drought/wet classes leads to more accurate results. In addition, the SHDI3 prediction was more accurate than the SHDI1 prediction. RST showed slightly better accuracy than SVC and SVR. In case of nine-class forecast, the overall accuracy of RST model in correctly predicting the exact class, or with maximum one class shift, was 90.6% for SHDI1 and 96.5% for SHDI3. These values were 92.9% for SHDI1 and 98.8% for SHDI3 in seven-class system. Overall, direct classification methods (SVC and RST), in addition to simplicity, were more successful than the indirect method (SVR) in determination of severe dry/wet classes.

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
Fig. 8

Similar content being viewed by others

Code availability

All data, models, or code generated or used during the study are available from the corresponding author by request.

Availability of data and material

All data used during the study are available from the corresponding author by request.

References

  • Abbas Z, Burney A (2016) A survey of software packages used for rough set analysis. J Comput Commun 4:10–18

    Article  Google Scholar 

  • Abrha H, Hagos H (2019) Future drought and aridity monitoring using multi-model approach under climate change in Hintalo Wejerat district. Ethiopia Sustain Water Resour Manag 5:1963–1972. https://doi.org/10.1007/s40899-019-00350-1

    Article  Google Scholar 

  • Adnan R, Yuan X, Kisi O, Yuan Y (2017) Streamflow forecasting using artificial neural network and support vector machine models. Am Sci Res J Eng Technol Sci (ASRJETS) 29(1):286–294

    Google Scholar 

  • An Y, Zou Zh, Li R (2014) Water quality assessment in the harbin reach of the Songhuajiang River (China) based on a fuzzy rough set and an attribute recognition theoretical model. Int J Environ Res Public Health 11:3507–3520. https://doi.org/10.3390/ijerph110403507

    Article  Google Scholar 

  • Andreadis KM, Lettenmaier DP (2006) Trends in 20th century drought over the continental United States. Geophys Res Lett 33(10):L10403. https://doi.org/10.1029/2006GL025711

    Article  Google Scholar 

  • Andreu J, Haro D, Solera A, Paredes J, Assimacopoulos D, Wolters W, van Lanen HAJ, Kampragou E, Bifulco C, de Carli A, Dias S, Tánago IG, Massarutto A, Musolino D, Rego F, Seidl I, De Stefano L, Reguera JU (2015) Drought indicators: monitoring, forecasting and early warning at the case study scale, DROUGHT-R&SPI project, Technical Report No.33

  • Arabani M, Pirouz M (2016) Water treatment plant site location using rough set theory. Environ Monit Assess 188:552. https://doi.org/10.1007/s10661-016-5539-1

    Article  Google Scholar 

  • Araghi A, Martinez CJ, Adamowski J, Olesen (2018) Spatiotemporal variations of aridity in Iran using high-resolution gridded data. Int J Climatol 38(6):2701–2717. https://doi.org/10.1002/joc.5454

    Article  Google Scholar 

  • Araghinejad Sh (2014) Data-driven modeling: using MATLAB® in water resources and environmental engineering. Part Water Sci Technol Library Book Ser. https://doi.org/10.1007/978-94-007-7506-0

    Article  Google Scholar 

  • Belayneh A, Adamowski J (2012) Standard precipitation index drought forecasting using neural networks, wavelet neural networks, and support vector regression. Appl Comput Intell Soft Comput 20:12. https://doi.org/10.1155/2012/794061

    Article  Google Scholar 

  • Bhuiyan C (2004) Various Drought Indices for Monitoring Drought Condition in Aravalli Terrain of India. Proceedings of the XXth ISPRS Conference. International Society for Photogrammetry and Remote Sensing, Istanbul, Turkey, http://www.isprs.org/proceedings/XXXV/congress/comm7/papers/243.pdf.

  • Blagus R, Lusa L (2010) Class prediction for high-dimensional class-imbalanced data. BMC Bioinformatics 11:523. https://doi.org/10.1186/1471-2105-11-523

    Article  Google Scholar 

  • Bloomfield JP, Marchant BP (2013) Analysis of groundwater drought building on the standardized precipitation index approach. Hydrol Earth Syst Sci 17:4769–4787

    Article  Google Scholar 

  • Borji M, Malekian A, Salajegheh A, Ghadimi M (2016) Multi-time-scale analysis of hydrological drought forecasting using support vector regression (SVR) and artificial neural networks (ANN). Arab J Geosci 9:725

    Article  Google Scholar 

  • Chen ShT, Yu PSh, Tang YH (2010) Statistical downscaling of daily precipitation using support vector machines and multivariate analysis. J Hydrol 385(2010):13–22. https://doi.org/10.1016/j.jhydrol.2010.01.021

    Article  Google Scholar 

  • Choubey V, Mishra S, Pandey SK (2014) Time series data mining in real time surface runoff forecasting through support vector machine. Int J Comp Appl 98(3):0975–8887

    Google Scholar 

  • Crochemore L, Ramos MH, Pappenberger F, Perrin Ch (2017) Seasonal streamflow forecasting by conditioning climatology with precipitation indices. Hydrol Earth Syst Sci 21:1573–1591

    Article  Google Scholar 

  • Das P, Naganna SR, Deka PC, Pushparaj J (2020) Hybrid wavelet packet machine learning approaches for drought modeling. Environ Earth Sci 79:221. https://doi.org/10.1007/s12665-020-08971-y

    Article  Google Scholar 

  • Dehghani M, Saghafian B, Nasiri Saleh F, Farokhnia A, Noori R (2013) Uncertainty analysis of streamflow drought forecast using artificial neural networks and Monte-Carlo simulation. Int J Climatol 3(4):1169–1180. https://doi.org/10.1002/joc.3754

    Article  Google Scholar 

  • Dehghani M, Saghafian B, Zargar M (2019) Probabilistic hydrological drought index forecasting based on meteorological drought index using Archimedean copulas. Hydrol Res. https://doi.org/10.2166/nh.2019.051 (in press)

    Article  Google Scholar 

  • Fundel F, Jörg-Hess S, Zappa M (2013) Monthly hydrometeorological ensemble prediction of streamflow droughts and corresponding drought indices. Hydrol Earth Syst Sci 17:395–407. https://doi.org/10.5194/hess-17-395-2013

    Article  Google Scholar 

  • Fung KF, Huang YF, Koo CH, Soh YW (2020) Drought forecasting: a review of modelling approaches 2007–2017. J Water Clim Change 11(3):771–799

  • Gao JB, Gunn SR, Harris CJ, Brown M (2002) A probabilistic framework for SVM regression and error bar estimation. Machine Learning 46:71–89

    Article  Google Scholar 

  • Gunn S (1998) Support vector machines for classification and regression. Technical Report, ISIS, Department of Electronics and Computer Science, University of Southampton.

  • Hao Z, Singh VP, Xia Y (2018) Seasonal drought prediction: advances, challenges, and future prospects. Rev Geophys 56:108–141. https://doi.org/10.1002/2016RG000549

    Article  Google Scholar 

  • Hatmoko W, Radhika RB, Tollenaar D, Vernimmen R (2015) Monitoring and prediction of hydrological drought using a drought early warning system in Pemali-Comal river basin Indonesia. Procedia Environ Sci 24(2015):56–64

    Article  Google Scholar 

  • Hayes M, Svoboda M, Wall N, Widhalm M (2011) The Lincoln declaration on drought indices: universal meteorological drought index recommended. Bull Am Meteor Soc 92(4):485–488

    Article  Google Scholar 

  • Hvidsten TR (2013) a tutorial-based guide to the ROSETTA system: A Rough Set Toolkit for Analysis of Data.

  • Jehanzaib M, Sattar MN, Lee J, Kim TW (2020) Investigating effect of climate change on drought propagation from meteorological to hydrological drought using multi-model ensemble projections. Stoch Environ Res Risk Assess 34:7–21. https://doi.org/10.1007/s00477-019-01760-5

    Article  Google Scholar 

  • Johnson DS (1974) Approximation algorithms for combinatorial problems. J Comput Syst Sci 9:256–278

    Article  Google Scholar 

  • Karamouz M, Rasouli K, Nazif S (2009) Development of a hybrid index for drought prediction: case study. J Hydrol Eng 14(6):617–627. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000022

    Article  Google Scholar 

  • Kolachian R, Saghafian B (2019) Deterministic and probabilistic evaluation of raw and post processed sub-seasonal to seasonal precipitation forecasts in different precipitation regimes. Theor Appl Climatol 137:1479–1493. https://doi.org/10.1007/s00704-018-2680-5

    Article  Google Scholar 

  • Lashteh Neshaei MA, Pirouz M (2010) Rough sets theory in site selection decision making for water reservoirs. Comp Meth Civil Eng 1(1):85–94

    Google Scholar 

  • Li J, Zhou S, Hu R (2016) Hydrological drought class transition using SPI and SRI time series by loglinear regression. Water Res Manag 30(2):669–684

    Article  Google Scholar 

  • Li B, Zhu Ch, Liang Zh, Wang G, Zhang Y (2018) Connections between meteorological and hydrological droughts in a semi-arid basin of the middle Yellow River. Proc IAHS 379:403–407. https://doi.org/10.5194/piahs-379-403-2018

    Article  Google Scholar 

  • Liu Z, Lu G, He H, Wu Z, He J (2018) A conceptual prediction model for seasonal drought processes using atmospheric and oceanic standardized anomalies: application to regional drought processes in China. Hydrol Earth Syst Sci 22:529–546. https://doi.org/10.5194/hess-22-529-2018

    Article  Google Scholar 

  • Luo L, Sheffield J, Wood EF (2008) Towards a global drought monitoring and forecasting capability. Science and technology infusion climate bulletin, NOAA’s national weather service. 33rd NOAA Annual Climate Diagnostics and Prediction Workshop, Lincoln, NE, pp 20–24

    Google Scholar 

  • Ma F, Luo L, Ye A, Duan Q (2018) Seasonal drought predictability and forecast skill in the semi-arid endorheic Heihe River basin in northwestern China. Hydrol Earth Syst Sci 22:5697–5709. https://doi.org/10.5194/hess-22-5697-2018

    Article  Google Scholar 

  • Madadgar S, AghaKouchak A, Shukla S, Wood AW, Cheng L, Hsu KL, Svoboda M (2016) A hybrid statistical-dynamical framework for meteorological drought prediction: application to the southwestern United States. Water Resour Res. 52:5095–5110. https://doi.org/10.1002/2015WR018547

    Article  Google Scholar 

  • Maity R, Bhagwat PP, Bhatnagar A (2010) Potential of support vector regression for prediction of monthly streamflow using endogenous property. Hydrol Process 24:917–923. https://doi.org/10.1002/hyp.7535

    Article  Google Scholar 

  • Mallya G, Tripathi Sh, Govindaraju RS (2015) Probabilistic drought classification using gamma mixture models. J Hydrol 526(2015):116–126

    Article  Google Scholar 

  • McKee TB, Doesken NJ, Kleist J (1993) the relationship of drought frequency andduration totime scales. Proceedings of the 8th conference on applied climatology. American Meteorological Society, Boston, MA

    Google Scholar 

  • McKee TB, Doesken NJ, Kleist J (1995) Drought monitoring with multiple time scales. Ninth conference on applied climatology. American Meteorological Society, Boston, pp 233–236

    Google Scholar 

  • Men B, Liu H, Tian W, Liu H (2017) Evaluation of sustainable use of water resources in beijing based on rough set and fuzzy theory. Water 9:852. https://doi.org/10.3390/w9110852

    Article  Google Scholar 

  • Mishra S, Saravanan S, Dwivedi VK (2015) Study of time series data mining for the real time hydrological forecasting: a review. Int J Comp Appl 117(23):6–17

    Google Scholar 

  • Moreira E, Russo A, Trigo RM (2018) Monthly prediction of drought classes using log-linear models under the influence of NAO for early-warning of drought and water management. Water 10:65. https://doi.org/10.3390/w10010065

    Article  Google Scholar 

  • Nalbantis I, Tsakiris G (2008) Assessment of hydrological drought revisited. Water Resour Manage 23(5):881–897

    Article  Google Scholar 

  • Paulo AA, Pereira LS (2008) Stochastic prediction of drought class transitions. Water Resour Manage 22:1277–1296

    Article  Google Scholar 

  • Pawlak Z (1982) Rough sets. Int J Comput Inform Sci 11:341–356

    Article  Google Scholar 

  • Pawlak Z (2002) Rough set theory and its applications. J Telecommun Inf Technol 3:7–10

    Google Scholar 

  • Pour SH, Wahab AKA, Shahid S (2020) Spatiotemporal changes in aridity and the shift of drylands in Iran. Atmos Res. https://doi.org/10.1016/j.atmosres.2019.104704

    Article  Google Scholar 

  • Schepen A, Wang Q (2015) Model averaging methods to merge operational statistical and dynamic seasonal streamflow forecasts in Australia. Water Resour Res 51:1797–1812. https://doi.org/10.1002/2014WR016163

    Article  Google Scholar 

  • Sheffield J, Wood EF, Chaney N, Guan K, Sadri S, Yuan X, Olang L, Amani A, Ali A, Demuth S, Ogallo L (2014) A drought monitoring and forecasting system for Sub-Sahara African water resources and food security. Am Meteorol Soc 95(6):861–882

    Article  Google Scholar 

  • Shukla S, Wood AW (2008) Use of a standardized runoff index for characterizing hydrologic drought. Geophys Res Lett 35:L02405. https://doi.org/10.1029/2007GL032487

    Article  Google Scholar 

  • Singh KP, Basant N, Gupta Sh (2011) Support vector machines in water quality management. Anal Chim Acta 703(2011):152–162. https://doi.org/10.1016/j.aca.2011.07.027

    Article  Google Scholar 

  • Svoboda M, Fuchs B and Integrated Drought Management Programme (IDMP) (2016) Handbook of Drought Indicators and Indices”. Drought Mitigation Center Faculty Publications. 117.http://digitalcommons.unl.edu/droughtfacpub/117

  • Vapnik VN (1995) The nature of statistical learning theory. Springer, New York

    Book  Google Scholar 

  • Vicente-Serrano SM, López-Moreno JI, Beguería S, Lorenzo-Lacruz J, Azorin-Molina C, Morán-Tejeda E (2012) Accurate computation of a streamflow drought index. J Hydrol Eng 17:318–332

    Article  Google Scholar 

  • Wang WC, Chau KW, ChengQiu CTL (2009) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. J Hydrol 374(2009):294–306

    Article  Google Scholar 

  • Wilhite DA, Glantz MH (1985) Understanding the drought phenomenon: definitions. Water International 10:111–120

    Article  Google Scholar 

  • Wong G, van Lanen HAJ, Torfs PJJF (2013) Probabilistic analysis of hydrological drought characteristics using meteorological drought. Hydrol Sci J 58(2):253–270

    Article  Google Scholar 

  • World Meteorological Organization (WMO) (2006) Drought monitoring and early warning: Concepts, progress and future challenges. WMO- No. 1006.

  • Wu Z, Mao Y, Li X, Lu G, Lin Q, Xu H (2016) Exploring spatiotemporal relationships among meteorological, agricultural, and hydrological droughts in Southwest China. Stoch Environ Res Risk Assess 30:1033–1044. https://doi.org/10.1007/s00477-015-1080-y

    Article  Google Scholar 

  • Xu K, Qin G, Niu J, Wu C, Hu BH, Huang G, Wang P (2019) Comparative analysis of meteorological and hydrological drought over the Pearl River basin in southern China. Hydrol Res 50(1):301–318. https://doi.org/10.2166/nh.2018.178

    Article  Google Scholar 

  • Yan H, Moradkhani H, Zarekarizi M (2017) A probabilistic drought forecasting framework: a combined dynamical and statistical. Approach J Hydrol 548:291–304

    Article  Google Scholar 

  • Yuan X, Wood EF, Chaney NW, Sheffield J, Kam J, Liang M, Guan K (2013) Probabilistic seasonal forecasting of african drought by dynamical models. Journal of Hydrmeteorology 14(6):1706–1720

    Article  Google Scholar 

Download references

Author information

Authors and Affiliations

  1. Department of Civil Engineering, Science and Research Branch, Islamic Azad University, Tehran, Iran

    Roya Kolachian & Bahram Saghafian

Authors
  1. Roya Kolachian
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Bahram Saghafian
    View author publications

    You can also search for this author in PubMed Google Scholar

Corresponding author

Correspondence to Bahram Saghafian.

Ethics declarations

Conflict of interest

The authors declare that they have no conflict of interest.

Additional information

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

Check for updates. Verify currency and authenticity via CrossMark

Cite this article

Kolachian, R., Saghafian, B. Hydrological drought class early warning using support vector machines and rough sets. Environ Earth Sci 80, 390 (2021). https://doi.org/10.1007/s12665-021-09536-3

Download citation

  • Received:

  • Accepted:

  • Published:

  • DOI: https://doi.org/10.1007/s12665-021-09536-3

Keywords

Search

Navigation