Lake level dynamics exploration using deep learning, artificial neural network, and multiple linear regression techniques

  • Jinfeng Wen
  • Peng-Fei HanEmail author
  • Zhangbing Zhou
  • Xu-Sheng Wang
Original Article


Estimating the lake level dynamics accurately on a daily or finer timescale is important for a better understanding of ecosystems, especially the lakes in Badain Jaran Desert, China. In this study, lake level dynamics of Sumu Barun Jaran are simulated and predicted on a 2-h timescale using the deep learning (DL) model, which is structured for the first time in this area by considering critical environmental factors. Two machine learning methods, namely multiple linear regression (MLR) and the three-layered back-propagation artificial neural network (ANN), are also adopted for the prediction purpose. The performances of these models are evaluated by comparing the values of average relative error, the mean squared error, and the coefficient of determination. The result shows that the DL model performs better than MLR and ANN on these three criteria, and this DL model is beneficial for exploring the mechanism of lake level dynamics in Badain Jaran Desert.


Lake level Sumu Barun Jaran Badain Jaran Desert Deep learning Artificial neural network 



This work was supported partially by the National Natural Science Foundation of China (nos. 61379126, 61662021, and 61772479), the Fundamental Research Funds for the Central Universities (2652017169) and by the Fundamental Research Funds for the Central Universities (China University of Geosciences (Beijing), China). The authors are grateful to the anonymous reviewers for their constructive comments.


  1. Adamowski J, Chan HF (2011) A wavelet neural network conjunction model for groundwater level forecasting. J Hydrol 407(1):28–40CrossRefGoogle Scholar
  2. Bardossy A (2007) Calibration of hydrological model parameters for ungauged catchments. Hydrol Earth Syst Sci Discuss 11(2):703–710CrossRefGoogle Scholar
  3. Chen T, Wang X, Hu X, Lu H, Gong Y (2015) Clines in salt lakes in the Badain Jaran Desert and their significances in indicating fresh groundwater discharge. J Lake Sci 27(1):183–189CrossRefGoogle Scholar
  4. Costarelli D, Spigler R (2013) Multivariate neural network operators with sigmoidal activation functions. Neural Netw 48(6):72–77CrossRefGoogle Scholar
  5. Crapper PF, Fleming PM, Kalma JD (1996) Prediction of lake levels using water balance models. Environ Softw 11(4):251–258CrossRefGoogle Scholar
  6. Ditzler G, Polikar R, Rosen G (2015) Multi-layer and recursive neural networks for metagenomic classification. IEEE Trans Nanobiosci 14(6):608–616CrossRefGoogle Scholar
  7. Goh G, Hodas N, Vishnu A (2017) Deep learning for computational chemistry. J Comput Chem 38(16):1291CrossRefGoogle Scholar
  8. Gong Y, Wang X, Hu BX, Zhou Y, Hao C, Li W (2016) Groundwater contributions in water-salt balances of the lakes in the Badain Jaran Desert, China. J Arid Land 8(5):694–706CrossRefGoogle Scholar
  9. Havaei M, Davy A, Warde-Farley D, Biard A, Courville A, Bengio Y, Pal C, Jodoin PM, Larochelle H (2017) Brain tumor segmentation with deep neural networks. Med Image Anal 35:18–31CrossRefGoogle Scholar
  10. Khan MS, Coulibaly P (2006) Bayesian neural network for rainfall-runoff modeling. Water Resour Res 420(7):379–393Google Scholar
  11. Kia MB, Pirasteh S, Pradhan B, Wan NAS, Moradi A (2012) An artificial neural network model for flood simulation using GIS: Johor River Basin, Malaysia. Environ Earth Sci 67(1):251–264CrossRefGoogle Scholar
  12. Knotters M, Bierkens MFP (2000) Physical basis of time series models for water table depths. Water Resour Res 36(1):181–188CrossRefGoogle Scholar
  13. Kumar DN, Maity R (2008) Bayesian dynamic modelling for nonstationary hydroclimatic time series forecasting along with uncertainty quantification. Hydrol Process 22(17):3488–3499CrossRefGoogle Scholar
  14. Li X, Cui B, Yang Q, Lan Y (2016) Impacts of water level fluctuations on detritus accumulation in Lake Baiyangdian, China. Ecohydrology 9(1):52–67CrossRefGoogle Scholar
  15. Li X, Pan R, Duan F (2017) Parameterizing stellar spectra using deep neural networks. Res Astron Astrophys 17(4):036CrossRefGoogle Scholar
  16. Maier HR, Dandy GC (1996) The use of artificial neural networks for the prediction of water quality parameters. Water Resour Res 32(4):1013–1022CrossRefGoogle Scholar
  17. Maiti S, Tiwari RK (2014) A comparative study of artificial neural networks, Bayesian neural networks and adaptive neuro-fuzzy inference system in groundwater level prediction. Environ Earth Sci 71(7):3147–3160CrossRefGoogle Scholar
  18. Mills K, Spanner M, Tamblyn I (2017) Deep learning and the Schrödinger equation. Phys Rev A 96(4):1–9CrossRefGoogle Scholar
  19. Park E, Parker J (2008) A simple model for water table fluctuations in response to precipitation. J Hydrol 356(3):344–349CrossRefGoogle Scholar
  20. Pollacco JAP, Ugalde JMS, Angulo-Jaramillo R, Braud I, Saugier B (2008) A linking test to reduce the number of hydraulic parameters necessary to simulate groundwater recharge in unsaturated soils. Adv Water Resour 31(2):355–369CrossRefGoogle Scholar
  21. Qian K, Liu X, Chen Y (2016) Effects of water level fluctuation on phytoplankton succession in Poyang Lake, China—a five year study. Ecohydrol Hydrobiol 16(3):175–184CrossRefGoogle Scholar
  22. Sartin MA, Silva ACRD (2013) Approximation of hyperbolic tangent activation function using hybrid methods. In: 2013 8th international workshop on reconfigurable and communication-centric systems-on-chip (ReCoSoC). IEEE, pp 1–6Google Scholar
  23. Schmidhuber J (2015) Deep learning in neural networks: an overview. Neural Netw 61:85–117CrossRefGoogle Scholar
  24. Talebizadeh M, Moridnejad A (2011) Uncertainty analysis for the forecast of lake level fluctuations using ensembles of ANN and ANFIS models. Expert Syst Appl 38(4):4126–4135CrossRefGoogle Scholar
  25. Wang T (1990) Formation and evolution of Badain Jirin Sandy Desert, China. China J Desert Res 10(1):29–40Google Scholar
  26. Wei CC (2015) Comparing lazy and eager learning models for water level forecasting in river-reservoir basins of inundation regions. Environ Model Softw 63:137–155CrossRefGoogle Scholar
  27. Xu T, Wang Y, Chen K (2016) Tailings saturation line prediction based on genetic algorithm and BP neural network. J Intell Fuzzy Syst 30(4):1947–1955CrossRefGoogle Scholar
  28. Yarar A, Onucyıldız M, Copty NK (2009) Modelling level change in lakes using neuro-fuzzy and artificial neural networks. J Hydrol 365(3):329–334CrossRefGoogle Scholar
  29. Yihdego Y, Webb JA, Leahy P (2015) Modelling of lake level under climate change conditions: Lake Purrumbete in southeastern Australia. Environ Earth Sci 73(7):3855–3872CrossRefGoogle Scholar
  30. Zhang J, Wang X, Jia F, Li G, Dong Y (2015) New insights into the flow directions of groundwater in Western Alxa, Inner Mongolia. Geoscience 35(3):774–782Google Scholar
  31. Zhang J, Wang X, Hu X, Lu H, Ma Z (2017) Research on the recharge of the lakes in the Badain Jaran Desert: simulation study in the Sumu Jaran lakes area. J Lake Sci 29(2):467–479CrossRefGoogle Scholar

Copyright information

© Springer-Verlag GmbH Germany, part of Springer Nature 2019

Authors and Affiliations

  1. 1.Ministry of Education Key Laboratory of Groundwater Circulation and Environmental EvolutionChina University of GeosciencesBeijingChina
  2. 2.Computer Science DepartmentTELECOM SudParisEvryFrance

Personalised recommendations