Skip to main content

Hybrid deep learning method for a week-ahead evapotranspiration forecasting

Abstract

Reference crop evapotranspiration (ETo) is an integral hydrological factor in soil–plant-atmospheric water balance studies and the management of drought events. This paper proposes a new hybrid-deep learning approach, combining convolutional neural network (CNN) and gated recurrent unit (GRU) along with Ant Colony Optimization (ACO), for a multi-step (week 1 to 4) daily-ETo forecast. The method also assimilates a comprehensive dataset with 52 diverse predictors, i.e., satellite-derived moderate resolution imaging spectroradiometer, ground-based datasets from scientific information for landowners and synoptic-scale climate indices. To develop a vigorous CNN-GRU model, a feature selection stage entails the ant colony optimization method implemented to improve the ETo forecast model for the three selected sites in Australian Murray Darling Basin. The results demonstrate excellent forecasting capability of the hybrid CNN-GRU model against the counterpart benchmark models, evidenced by a relatively small mean absolute error and high efficiency. Overall, this study shows that the proposed hybrid CNN-GRU model successfully apprehends the complex and non-linear relationships between predictor variables and the daily ETo.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5
Fig. 6
Fig. 7
Fig. 8
Fig. 9
Fig. 10
Fig. 11
Fig. 12

Abbreviations

AA:

Advection–Aridity

ACO:

Ant colony optimization

ANN:

Artificial neural network

AO:

Arctic oscillation

BOM:

Australian bureau of meteorology

CCF:

Cross correction function

CNN:

Convolutional neural network

CNN-GRU:

Hybrid model integrating the ACO and CNN algorithm with GRU

CNN-LSTM:

Hybrid model integrating the ACO and CNN algorithm with LSTM

CI:

Climate indices

DL:

Deep learning

DMI:

Dipole model index

ECDF:

Empirical cumulative distribution function

ELM:

Extreme learning machine

EMD:

Empirical mode decomposition

EMI:

El-Nino southern oscillation Modoki index

ENSO:

El Niño Southern oscillation

ETo :

Reference crop evapotranspiration

FAO:

Food and agriculture organization

FE:

Forecasting error

FFNN:

Feed forward neural networks

GB:

Giga bite

GCM:

Global climate model

GRU:

Gated recurrent unit

GIOVANNI:

Geospatial online interactive visualization and analysis infrastructure

KNMI:

Royal Netherlands meteorological institute

LM:

Legates-McCabe's index

LSTM:

Long- short term memory

LS-SVM:

Least-squares support vector machines

MAE:

Mean absolute error

MAPE:

Mean absolute percentage error

MARS:

Multivariate adaptive regression splines

MDB:

Murray-Darling basin

ML:

Machine learning

MLP:

Multi-layer perceptron

MLR:

Multilinear regression

MJO:

Madden–Julian oscillation

MODIS:

Moderate resolution imaging spectroradiometer

MSE:

Mean squared error

NOAA:

National oceanic and atmospheric administration

NSE:

Nash–sutcliffe efficiency

PACF:

Partial autocorrelation function

PM:

Penman–Monteith

PT–FC:

Priestley–Taylor and Flint–Childs

R:

Correlation coefficient

RF:

Random forest

RMSE:

Root-mean-square-error

RNN:

Recurrent neural network

RRMSE:

Relative root-mean-square error

SD:

Standard deviation

SAM:

Southern annular mode

SILO:

Scientific information for landowners

SOI:

Southern oscillation index

SST:

Sea surface temperature

SVR:

Support vector regression

SW:

Shuttleworth–Wallace

References

  1. Abdullah SS, Malek MA, Abdullah NS, Kisi O, Yap KS (2015) Extreme learning machines: a new approach for prediction of reference evapotranspiration. J Hydrol 527:184–195

    Article  Google Scholar 

  2. Adamowski J, Fung Chan H, Prasher SO, Ozga-Zielinski B, Sliusarieva A (2012) Comparison of multiple linear and nonlinear regression, autoregressive integrated moving average, artificial neural network, and wavelet artificial neural network methods for urban water demand forecasting in Montreal, Canada. Water Resour Res 48(1):W01528. https://doi.org/10.1029/2010WR009945

  3. Adnan M, Rehman N, Sheikh M, Khan A, Mir K, Khan M (2016) Influence of natural forcing phenomena on precipitation of Pakistan. Pakistan J Meteorol 12(24):23–35

    Google Scholar 

  4. Adnan RM, Heddam S, Yaseen ZM, Shahid S, Kisi O, Li B (2021) Prediction of potential evapotranspiration using temperature-based heuristic approaches. Sustainability 13(1):297

    Article  Google Scholar 

  5. Ahmed AAM (2017) Prediction of dissolved oxygen in Surma River by biochemical oxygen demand and chemical oxygen demand using the artificial neural networks (ANNs). J King Saud Univ Eng Sci 29(2):151–158

    Article  Google Scholar 

  6. Ahmed AAM, Deo RC, Raj N, Ghahramani A, Feng Q, Yin Z, Yang L (2021a) Deep learning forecasts of soil moisture: convolutional neural network and gated recurrent unit models coupled with satellite-derived MODIS, observations and synoptic-scale climate index data. Remote Sens 13(4):554

    Article  Google Scholar 

  7. Ahmed AAM, Shah SMA (2017) Application of adaptive neuro-fuzzy inference system (ANFIS) to estimate the biochemical oxygen demand (BOD) of Surma River. J King Saud Univ Eng Sci 29(3):237–243

    Google Scholar 

  8. Ahmed AM, Deo RC, Feng Q, Ghahramani A, Raj N, Yin Z, Yang L (2021b) Deep learning hybrid model with Boruta-Random forest optimiser algorithm for streamflow forecasting with climate mode indices, rainfall, and periodicity. J Hydrol 599:126350

    Article  Google Scholar 

  9. Ahmed AM, Deo RC, Ghahramani A, Raj N, Feng Q, Yin Z, Yang L (2021c) LSTM integrated with Boruta-random forest optimiser for soil moisture estimation under RCP4. 5 and RCP8. 5 global warming scenarios. Stoch Environ Res Risk Assess: 1–31

  10. Ali M, Deo RC, Maraseni T, Downs NJ (2019) Improving SPI-derived drought forecasts incorporating synoptic-scale climate indices in multi-phase multivariate empirical mode decomposition model hybridized with simulated annealing and kernel ridge regression algorithms. J Hydrol 576:164–184

    Article  Google Scholar 

  11. Allen RG, Pereira LS, Raes D, Smith M (1998) Crop evapotranspiration-Guidelines for computing crop water requirements-FAO Irrigation and drainage paper 56. Fao Rome 300(9):D05109

    Google Scholar 

  12. BOM (2020) Bureau of meteorology

  13. Bonan GB (2008) Forests and climate change: forcings, feedbacks, and the climate benefits of forests. Science 320(5882):1444–1449

    CAS  Article  Google Scholar 

  14. Breiman L (2001) Random forests. Mach Learn 45:5–32

    Article  Google Scholar 

  15. Chen C, Jiang H, Zhang Y, Wang Y (2010) Investigating spatial and temporal characteristics of harmful Algal Bloom areas in the East China Sea using a fast and flexible method. In: 2010 18th international conference on geoinformatics. IEEE, pp 1–4.

  16. Chen Z, Zhu Z, Jiang H, Sun S (2020) Estimating daily reference evapotranspiration based on limited meteorological data using deep learning and classical machine learning methods. J Hydrol 591:125286

    Article  Google Scholar 

  17. Cho K, Van Merriënboer B, Gulcehre C, Bahdanau D, Bougares F, Schwenk H, Bengio Y (2014) Learning phrase representations using RNN encoder-decoder for statistical machine translation. arXiv:1406.1078

  18. Damavandi HG, Shah R, Stampoulis D, Wei Y, Boscovic D, Sabo J (2019) Accurate prediction of streamflow using long short-term memory network: a case study in the Brazos River Basin in Texas. Int J Environ Sci Dev 10(10):294–300

    Article  Google Scholar 

  19. Deo RC, Downs N, Parisi AV, Adamowski JF, Quilty JM (2017) Very short-term reactive forecasting of the solar ultraviolet index using an extreme learning machine integrated with the solar zenith angle. Environ Res 155:141–166

    CAS  Article  Google Scholar 

  20. Deo RC, Şahin M (2015) Application of the artificial neural network model for prediction of monthly standardized precipitation and evapotranspiration index using hydrometeorological parameters and climate indices in eastern Australia. Atmos Res 161–162:65–81

    Article  Google Scholar 

  21. Deo RC, Şahin M (2017) Forecasting long-term global solar radiation with an ANN algorithm coupled with satellite-derived (MODIS) land surface temperature (LST) for regional locations in Queensland. Renew Sustain Energy Rev 72:828–848

    Article  Google Scholar 

  22. Dorigo M, Di Caro G (1999) Ant colony optimization: a new meta-heuristic. In: Proceedings of the 1999 congress on evolutionary computation-CEC99 (Cat. No. 99TH8406). IEEE, pp 1470–1477

  23. Du S, Li T, Yang Y, Horng S-J (2018) Deep air quality forecasting using hybrid deep learning framework. arXiv:1812.04783

  24. Feng Y, Peng Y, Cui N, Gong D, Zhang K (2017) Modeling reference evapotranspiration using extreme learning machine and generalized regression neural network only with temperature data. Comput Electron Agric 136:71–78

    Article  Google Scholar 

  25. Gao S, Huang Y, Zhang S, Han J, Wang G, Zhang M, Lin Q (2020) Short-term runoff prediction with GRU and LSTM networks without requiring time step optimization during sample generation. J Hydrol 589:125188

    Article  Google Scholar 

  26. Ghimire S, Deo RC, Raj N, Mi J (2019a) Deep learning neural networks trained with MODIS satellite-derived predictors for long-term global solar radiation prediction. Energies 12(12):2407

    Article  Google Scholar 

  27. Ghimire S, Deo RC, Raj N, Mi J (2019b) Deep solar radiation forecasting with convolutional neural network and long short-term memory network algorithms. Appl Energy 253:113541

    Article  Google Scholar 

  28. Haidar A, Verma B (2018) Monthly rainfall forecasting using one-dimensional deep convolutional neural network. IEEE Access 6:69053–69063

    Article  Google Scholar 

  29. Hu C, Wu Q, Li H, Jian S, Li N, Lou Z (2018) Deep learning with a long short-term memory networks approach for rainfall-runoff simulation. Water 10(11):1543

    Article  Google Scholar 

  30. Huo Z, Feng S, Kang S, Dai X (2012) Artificial neural network models for reference evapotranspiration in an arid area of northwest China. J Arid Environ 82:81–90

    Article  Google Scholar 

  31. Kazemi MH, Majnooni-Heris A, Kisi O, Shiri J (2021) Generalized gene expression programming models for estimating reference evapotranspiration through cross-station assessment and exogenous data supply. Environ Sci Pollut Res 28(6):6520–6532

    Article  Google Scholar 

  32. Liu Y, Racah E, Correa J, Khosrowshahi A, Lavers D, Kunkel K, Wehner M, Collins W (2016) Application of deep convolutional neural networks for detecting extreme weather in climate datasets. arXiv:1605.01156

  33. Mehdizadeh S (2018) Estimation of daily reference evapotranspiration (ETo) using artificial intelligence methods: Offering a new approach for lagged ETo data-based modeling. J Hydrol 559:794–812

    Article  Google Scholar 

  34. Morison M, Petrone R, Wilkinson S, Green A, Waddington J (2020) Ecosystem scale evapotranspiration and CO2 exchange in burned and unburned peatlands: implications for the ecohydrological resilience of carbon stocks to wildfire. Ecohydrology 13(2):e2189

    CAS  Article  Google Scholar 

  35. Nash JE, Sutcliffe JV (1970) River flow forecasting through conceptual models part I—a discussion of principles. J Hydrol 10(3):282–290

    Article  Google Scholar 

  36. Nguyen-Huy T, Deo RC, An-Vo D-A, Mushtaq S, Khan S (2017) Copula-statistical precipitation forecasting model in Australia’s agro-ecological zones. Agric Water Manag 191:153–172

    Article  Google Scholar 

  37. Nguyen-Huy T, Deo RC, Mushtaq S, An-Vo D-A, Khan S (2018) Modeling the joint influence of multiple synoptic-scale, climate mode indices on Australian wheat yield using a vine copula-based approach. Eur J Agron 98:65–81

    Article  Google Scholar 

  38. Nunez JC, Cabido R, Pantrigo JJ, Montemayor AS, Velez JF (2018) Convolutional neural networks and long short-term memory for skeleton-based human activity and hand gesture recognition. Pattern Recogn 76:80–94

    Article  Google Scholar 

  39. Oehmcke S, Zielinski O, Kramer O (2018) Input quality aware convolutional LSTM networks for virtual marine sensors. Neurocomputing 275:2603–2615

    Article  Google Scholar 

  40. Olah C (2015) Understanding lstm networks, 2015. URL http://colah.github.io/posts/2015–08-Understanding-LSTMs.

  41. Patil AP, Deka PC (2016) An extreme learning machine approach for modeling evapotranspiration using extrinsic inputs. Comput Electron Agric 121:385–392

    Article  Google Scholar 

  42. Pejić B, Aksić M, Mačkić K, Šekularac G (2015) Response of potato to water stress in Southern Serbia. Austin J Irrig Austin Publ Group 1(1):1–4

    Google Scholar 

  43. Piticar A, Mihăilă D, Lazurca LG, Bistricean P-I, Puţuntică A, Briciu A-E (2016) Spatiotemporal distribution of reference evapotranspiration in the Republic of Moldova. Theoret Appl Climatol 124(3–4):1133–1144

    Article  Google Scholar 

  44. Prasad R, Deo RC, Li Y, Maraseni T (2017) Input selection and performance optimization of ANN-based streamflow forecasts in the drought-prone Murray Darling Basin region using IIS and MODWT algorithm. Atmos Res 197:42–63

    Article  Google Scholar 

  45. Prasad R, Deo RC, Li Y, Maraseni T (2018) Ensemble committee-based data intelligent approach for generating soil moisture forecasts with multivariate hydro-meteorological predictors. Soil Tillage Res 181:63–81

    Article  Google Scholar 

  46. Rahman AS, Hosono T, Kisi O, Dennis B, Imon AR (2020) A minimalistic approach for evapotranspiration estimation using the Prophet model. Hydrol Sci J 65(12):1994–2006

    Article  Google Scholar 

  47. Sweetlin JD, Nehemiah HK, Kannan A (2017) Feature selection using ant colony optimization with tandem-run recruitment to diagnose bronchitis from CT scan images. Comput Methods Programs Biomed 145:115–125

    Article  Google Scholar 

  48. Thomas A (2000) Spatial and temporal characteristics of potential evapotranspiration trends over China. Int J Climatol J R Meteorol Soc 20(4):381–396

    Article  Google Scholar 

  49. Tikhamarine Y, Malik A, Kumar A, Souag-Gamane D, Kisi O (2019) Estimation of monthly reference evapotranspiration using novel hybrid machine learning approaches. Hydrol Sci J 64(15):1824–1842

    Article  Google Scholar 

  50. Tikhamarine Y, Malik A, Souag-Gamane D, Kisi O (2020) Artificial intelligence models versus empirical equations for modeling monthly reference evapotranspiration. Environ Sci Pollut Res 27:30001–30019

    CAS  Article  Google Scholar 

  51. Tiwari M, Adamowski J, Adamowski K (2016) Water demand forecasting using extreme learning machines. J Water Land Dev 28(1):37–52

    Article  Google Scholar 

  52. Torrence C, Webster PJ (1999) Interdecadal changes in the ENSO–monsoon system. J Clim 12(8):2679–2690

    Article  Google Scholar 

  53. Traore S, Wang Y-M, Kerh T (2010) Artificial neural network for modeling reference evapotranspiration complex process in Sudano-Sahelian zone. Agric Water Manag 97(5):707–714

    Article  Google Scholar 

  54. Wei G, Zhang X, Ye M, Yue N, Kan F (2019) Bayesian performance evaluation of evapotranspiration models based on eddy covariance systems in an arid region. Hydrol Earth Syst Sci 23(7):2877–2895

    Article  Google Scholar 

  55. Wen X, Feng Q, Deo RC, Wu M, Yin Z, Yang L, Singh VP (2019) Two-phase extreme learning machines integrated with the complete ensemble empirical mode decomposition with adaptive noise algorithm for multi-scale runoff prediction problems. J Hydrol 570:167–184

    Article  Google Scholar 

  56. Wu M, Feng Q, Wen X, Deo RC, Yin Z, Yang L, Sheng D (2020) Random forest predictive model with uncertainty analysis capability for estimation of evapotranspiration in an arid oasis region. Hydr Res 51(4):648–665

    Article  Google Scholar 

  57. Yin Z, Feng Q, Yang L, Deo RC, Wen X, Si J, Xiao S (2017) Future projection with an extreme-learning machine and support vector regression of reference evapotranspiration in a mountainous inland watershed in north-west China. Water 9(11):880

    Article  Google Scholar 

  58. Zeng Z, Wu W, Zhou Y, Li Z, Hou M, Huang H (2019) Changes in reference evapotranspiration over southwest China during 1960–2018: attributions and implications for drought. Atmosphere 10(11):705

    Article  Google Scholar 

  59. Zhang J, Zhu Y, Zhang X, Ye M, Yang J (2018) Developing a long short-term memory (LSTM) based model for predicting water table depth in agricultural areas. J Hydrol 561:918–929

    Article  Google Scholar 

  60. Zhang P, Zhang L, Leung H, Wang J (2017) A deep-learning based precipitation forecasting approach using multiple environmental factors. In: 2017 IEEE international congress on big data (bigdata congress). IEEE, pp 193–200

  61. Zhu R, Zheng H, Wang E, Zhao W (2013) Multi-model ensemble simulation of flood events using Bayesian model averaging, MODSIM2013. In: 20th Int. Congress on Modelling and Simulation. Modelling and Simulation Society of Australia and New Zealand, pp 455–461

  62. Zou M, Kang S, Niu J, Lu H (2019) Untangling the effects of future climate change and human activity on evapotranspiration in the Heihe agricultural region, Northwest China. J Hydrol 585:124323

    Article  Google Scholar 

Download references

Acknowledgements

The research was supported by the Chinese Academy of Science (CAS) and the University of Southern Queensland (USQ) under the USQ-CAS Postgraduate Research Scholarship (2019–2021). Data were obtained from MODIS-satellite, SILO, and NOAA databases, which are duly acknowledged. We also thank the Editor and Reviewers for their insightful comments.

Author information

Affiliations

Authors

Contributions

A. A. Masrur Ahmed: Writing—original draft, Conceptualization, Methodology, Software, Model development, and application. Ravinesh C. Deo: Conceptualization, Writing—review & editing, Investigation, Supervision. Afshin Ghahramani: Writing—review & editing. Nawin Raj: Writing—review & editing, Qi Feng: Writing—review & editing, Zhenliang Yin: Writing—review & editing, Linshan Yang: Writing—review & editing.

Corresponding authors

Correspondence to A. A. Masrur Ahmed or Ravinesh C. Deo.

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

Verify currency and authenticity via CrossMark

Cite this article

Ahmed, A.A.M., Deo, R.C., Feng, Q. et al. Hybrid deep learning method for a week-ahead evapotranspiration forecasting. Stoch Environ Res Risk Assess (2021). https://doi.org/10.1007/s00477-021-02078-x

Download citation

Keywords

  • Convolutional neural network
  • Gated recurrent unit
  • Hybrid-deep learning
  • ETo forecasting