Improving ANN-based streamflow estimation models for the Upper Indus Basin using satellite-derived snow cover area

Abstract

The mountainous catchments often witness contrasting regimes and the limited available meteorological network creates uncertainty in both the hydrological data and developed models. To overcome this problem, remotely sensed data could be used in addition to on-ground observations for hydrological forecasting. The fusion of these two types of data gives a better picture and helps to generate adequate hydrological forecasting models. The study aims at the improvement of ANN-based streamflow estimation models by using an integrated data-set containing, the satellite-derived snow cover area (SCA) with on-ground flow observations. For this purpose, SCA of three sub catchments of Upper Indus Basin, namely Gilgit, Astore and Bunji coupled with their respective gauge discharges is used as model inputs. The weekly stream-flow models are developed for inflows at Besham Qila located just upstream of Tarbela dam. The data-set for modeling is prepared through normalizing all variables by scaling between 0 and 1. A mathematical tool, Gamma test is applied to fuse the inputs, and a best input combination is selected on the basis of minimum gamma value. A feed forward neural network trained via two layer Broyden Fletcher Goldfarb Shanno algorithm is used for model development. The models are evaluated on the basis of set of performance indicators, namely, Nash–Sutcliffe Efficiency, Root Mean Square Error, Variance and BIAS. A comparative assessment has also been made using these indicators for models developed, through data-set containing gauge discharges, only and the data-set fused with satellite-derived SCA. In particular, the current study concluded that the efficiency of ANN-based streamflow estimation models developed for mountainous catchments could be improved by integrating the SCA with the gauge discharges.

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

Fig. 1
Fig. 2
Fig. 3
Fig. 4
Fig. 5

References

  1. Abrahart RJ, See L (2002) Multi-model data fusion for river flow forecasting: an evaluation of six alternative methods based on two contrasting catchments. Hydrol Earth Syst Sci 6(4):655–670

    Article  Google Scholar 

  2. Afzal MT, Arslan M, Zafar S, Waqar MM (2014) Satellite derived snow cover status and trends in the Indus Basin. J Sp Technol 4:26–31

    Google Scholar 

  3. Ahmed F, Hassan M, Nisar H (2018) Developing nonlinear models for sediment load estimation in an irrigation canal. Acta Geophys. https://doi.org/10.1007/s11600-018-0221-3

    Article  Google Scholar 

  4. Andermann C (2011) Evaluation of precipitation data sets along the Himalayan front. Bull Am Meteorol Soc. https://doi.org/10.1029/2011GC003513

    Article  Google Scholar 

  5. Archer DR, Fowler HJ (2004) Spatial and temporal variations in precipitation in the Upper Indus Basin, global teleconnections and hydrological implications. Hydrol Earth Syst Sci 8:47–61

    Article  Google Scholar 

  6. Arfan M, Lund J, Hassan D, Saleem M, Ahmad A et al (2019) Assessment of spatial and temporal flow variability of the Indus River. Resources 8:103

    Article  Google Scholar 

  7. Ata M, Tekeli AE, Dönmez S, Fouli H (2016) Use of interactive multisensor snow and ice mapping system snow cover maps (IMS) and artificial neural networks for simulating river discharges in Eastern Turkey. Arab J Geosci. https://doi.org/10.1007/s12517-015-2074-2

    Article  Google Scholar 

  8. Azmi M, Araghinejad S, Kholghi M (2010) Multi model data fusion for hydrological forecasting using K-nearest neighbour method. Iran J Sci Technol 34:81–92

    Google Scholar 

  9. Bashir F, Rasul G (2003) Estimation of water discharge from gilgit basin using remote sensing. GIS Runoff Model Introd 6:97–113

    Google Scholar 

  10. Behrangi A, Khakbaz B, Chun T, Aghakouchak A, Hsu K (2011) Hydrologic evaluation of satellite precipitation products over a mid-size basin. J Hydrol 397:225–237. https://doi.org/10.1016/j.jhydrol.2010.11.043

    Article  Google Scholar 

  11. Brownlee J (2018) Deep learning performance. Machine Learning Mastery

  12. Broxton PD, Zeng X, Sulla-Menashe D, Troch PA (2014) A global land cover climatology using MODIS data. J Appl Meteorol Climatol. https://doi.org/10.1175/JAMC-D-13-0270.1

    Article  Google Scholar 

  13. Brubaker KL, Pinker RT, Deviatova E et al (2005) Evaluation and comparison of MODIS and IMS snow-cover estimates for the continental united states using station data. J Hydrometeorol 6:1002–1017

    Article  Google Scholar 

  14. Durrant PJ (2001) A non-linear data analysis and modeling tool with applications to flood prediction. Ph.D. Thesis, Department of Computer Science, Cardiff University, University of Wales, UK

  15. Elshorbagy A, Corzo G, Srinivasulu S, Solomatine DP (2010) Experimental investigation of the predictive capabilities of data driven modeling techniques in hydrology: Part 2. Hydrol Earth Syst Sci 14:1943–1961. https://doi.org/10.5194/hess-14-1943-2010

    Article  Google Scholar 

  16. Ercan MB, Asce M, Goodall JL, Asce AM (2013) Estimating watershed-scale precipitation by combining gauge- and radar-derived observations, pp 983–994. https://doi.org/10.1061/(ASCE)HE.1943-5584.0000687

  17. Forsythe N, Kilsby CG, Fowler HJ, Archer DR, Forsythe N, Kilsby CG, Fowler HJ, Archer DR (2011) Variability and potential change using MODIS satellite data products assessment of runoff sensitivity in the Upper Indus Basin to interannual climate variability and potential change using MODIS satellite data products. BioOne 32:16–29

    Google Scholar 

  18. Fowler HJ, Archer DR (2005) Hydro-climatological variability in the Upper Indus Basin and implications for water resources. Reg Hydrol Impacts Clim Change Impact Assess Decis Mak 295:131–138

    Google Scholar 

  19. Giustolisi O (2004) Sparse solution in training artificial neural networks. NeuroComputing 56C:284–304

    Google Scholar 

  20. Gökbulak F, Kamil Ş, Serengil Y (2015) Comparison of rainfall-runoff relationship modeling using different methods in a forested watershed. Water Resour Manag. https://doi.org/10.1007/s11269-015-1056-1

    Article  Google Scholar 

  21. Goodfellow I, Bengio Y, Courville A (2016) Deep learning. MIT Press, Cambridge

    Google Scholar 

  22. Hassan M, Shamim MA, Hashmi HN, Ashiq SZ, Ahmed I, Pasha GA, Naeem UA (2014) Predicting streamflows to a multipurpose reservoir using artificial neural networks and regression techniques. Earth Sci Inform. https://doi.org/10.1007/s12145-014-0161-7

    Article  Google Scholar 

  23. Hassan M, Shamim MA, Sikandar A, Mehmood I, Ahmed I, Ashiq SZ, Khitab A (2015) Development of sediment load estimation models by using artificial neural networking techniques. Environ Monit Assess. https://doi.org/10.1007/s10661-015-4866-y

    Article  Google Scholar 

  24. Hasson ul S, Böhner J, Lucarini V et al (2017) Prevailing climatic trends and runoff response from Hindukush–Karakoram–Himalaya, upper Indus Basin. Earth Syst Dyn 8:337–355. https://doi.org/10.5194/esd-8-337-2017

    Article  Google Scholar 

  25. Hasson S, Lucarini V, Khan, Petitta M, Bolch T, Gioli G (2014) Early 21st century snow cover state over the western river basins of the Indus River system. Hydrol Earth Syst Sci. https://doi.org/10.5194/hess-18-4077-2014

    Article  Google Scholar 

  26. Hayat H, Akbar TA, Tahir AA, Hassan QK, Dewan A, Irshad M (2019) Simulating current and future river-flows in the snowmelt-runo ff model and RCP scenarios. Water 11:1–19

    Article  Google Scholar 

  27. Immerzeel WW, Droogers P, De Jong SM, Bierkens MFP et al (2009) Remote Sensing of Environment Large-scale monitoring of snow cover and runoff simulation in Himalayan river basins using remote sensing. Remote Sens Environ 113:40–49. https://doi.org/10.1016/j.rse.2008.08.010

    Article  Google Scholar 

  28. Jamal K, Ahmad S, Li X, Rizwan M, Li H, Feng J (2018) Climate change and runoff contribution by hydrological zones of cryosphere catchment of Indus River, Pakistan. Hydrol Earth Syst Sci Discuss. https://doi.org/10.5194/hess-2018-548

    Article  Google Scholar 

  29. Jones AJ (2004) New tools in non-linear modelling and prediction. Comput Manage Sci 1(2):109–149. https://doi.org/10.1007/s10287-003-0006-1

  30. Khan A, Naz BS, Bowling LC (2015) Separating snow, clean and debris covered ice in the Upper Indus Basin, Hindukush–Karakoram–Himalayas, using Landsat images between 1998 and 2002. J Hydrol 521:46–64. https://doi.org/10.1016/j.jhydrol.2014.11.048

    Article  Google Scholar 

  31. Kisi O, Sanikhani H (2015) Prediction of long-term monthly precipitation using several. Int J Climatol 35:4139–4150. https://doi.org/10.1002/joc.4273

    Article  Google Scholar 

  32. Lang K, Waibel A, Hinton G (1990) A time-delay neural network architecture for isolated word recognition. Neural Netw 3:23–43

    Article  Google Scholar 

  33. Le Cun Y, Denker J S, Solla S A (1990) Optimal brain damage. In: Touretzky DS (ed) Advances in neural information processing systems, vol 2, Morgan Kaufmann, San Mateo, California, pp 598–605

  34. Lee G, Kim D, Kwon H, Choi E (2019) Estimation of maximum daily fresh snow accumulation using an artificial neural network model. Adv Meteorol. https://doi.org/10.1155/2019/2709351

    Article  Google Scholar 

  35. Liu X, Chen B (2000) Climatic warming in the Tibetan Plateau during recent decades. Int J Climatol 1742:1729–1742

    Article  Google Scholar 

  36. Lutz AF, Immerzeel WW, Kraaijenbrink PDA, Shrestha AB, Bierkens MFP (2016) Climate change impacts on the Upper Indus hydrology: sources, shifts and extremes. PLoS ONE. https://doi.org/10.1371/journal.pone.0165630

    Article  Google Scholar 

  37. Minsky M, Papert S (1969) Perceptrons. MIT Press, Cambridge, MA

    Google Scholar 

  38. Mishra B, Tripathi NK, Babel MS (2014) An artificial neural network-based snow cover predictive modeling in the higher Himalayas An Artificial Neural Network-Based Snow Cover Predictive Modeling in the Higher Himalayas. J Mt Sci 11:825–837. https://doi.org/10.1007/s11629-014-2985-5

    Article  Google Scholar 

  39. Mukhopadhyay B, Dutta A (2010) A stream water availability model of Upper Indus Basin based on a topologic model and global climatic datasets. Water Resour Manag. https://doi.org/10.1007/s11269-010-9666-0

    Article  Google Scholar 

  40. Naeem UA, Hashmi HN, Shamim MA, Ejaz N (2012) Flow variation in astore river under assumed glaciated extents due to climate change. Pak J Eng Appl Sci 11:73–81

    Google Scholar 

  41. Naeem U, Mughal H-U-R, Ghumman AR, Shamim MA (2014) Ranking sensitive calibrating parameters of UBC watershed model ranking sensitive calibrating parameters of UBC watershed model. KSCE J Civ Eng. https://doi.org/10.1007/s12205-013-0515-6

    Article  Google Scholar 

  42. Nagarajan K, Krekeler C, Member S, Slatton KC, Member S, Graham WD (2010) A scalable approach to fusing spatiotemporal data to estimate streamflow via a bayesian network. IEEE Trans Geosci Remote Sens 48:3720–3732

    Article  Google Scholar 

  43. Piotrowski AP, Napiorkowski JJ (2013) A comparison of methods to avoid overfitting in neural networks training in the case of catchment runoff modelling. J Hydrol 476:97–111. https://doi.org/10.1016/j.jhydrol.2012.10.019

    Article  Google Scholar 

  44. Prasad AK, Yang KS, Kafatos M (2009) Melting of major Glaciers in the western Himalayas: evidence of climatic changes from long term MSU derived tropospheric temperature trend (1979–2008). Annales Geophysicae 27:4505–4519

    Article  Google Scholar 

  45. Quiroga VM, Mano A, Kure S, Udo K (2013) Snow glacier melt estimation in tropical Andean glaciers using artificial neural networks. Hydrol Earth Syst Sci. https://doi.org/10.5194/hess-17-1265-2013

    Article  Google Scholar 

  46. Rastner P, Prinz R, Notarnicola C, Nicholson L, Sailer R, Schwaizer G, Paul F (2019) On the automated mapping of snow cover on glaciers and calculation of snow line altitudes from multi-temporal landsat data. Remote Sens 12:1–24

    Article  Google Scholar 

  47. Razavi T, Coulibaly P (2016) Improving streamflow estimation in ungauged basins using multi-modelling approach. Hydrol Sci J. https://doi.org/10.1080/02626667.2016.1154558

    Article  Google Scholar 

  48. Remesan R, Shamim MA, Han D (2008) Model data selection using gamma test for daily solar radiation estimation. Hydrol Process 2274:2267–2274. https://doi.org/10.1002/hyp

    Article  Google Scholar 

  49. Remesan R, Ali M, Han D, Mathew J (2009) Runoff prediction using an integrated hybrid modelling scheme. J Hydrol 372:48–60. https://doi.org/10.1016/j.jhydrol.2009.03.034

    Article  Google Scholar 

  50. Sakai A, Nuimura T, Fujita K, Takenaka S, Nagai H, Lamsal D (2015) Climate regime of Asian glaciers revealed by GAMDAM glacier inventory. Cryosph. https://doi.org/10.5194/tc-9-865-2015

    Article  Google Scholar 

  51. See L, Abrahart RJ (2001) Multi-model data fusion for hydrological forecasting. Comput Geosci 27:987–994

    Article  Google Scholar 

  52. Shamim MA, Hassan M, Ahmad S, Zeeshan M (2016) A comparison of artificial neural networks (ANN) and local linear regression (LLR) techniques for predicting monthly reservoir levels. KSCE J Civ Eng 20:971–977

    Article  Google Scholar 

  53. Sönmez I, Emre AT, Erdi E (2014) Snow cover trend analysis using Interactive Multisensor Snow and Ice Mapping System data over Turkey. Int J Climatol 2361:2349–2361. https://doi.org/10.1002/joc.3843

    Article  Google Scholar 

  54. Srinivasulu S, Jain A (2006) A comparative analysis of training methods for artificial neural network rainfall: runoff models. Appl Soft Comput 6:295–306. https://doi.org/10.1016/j.asoc.2005.02.002

    Article  Google Scholar 

  55. Stefánsson A, Končar N, Jones AJ (1997) A note on the Gamma test. Neural Comput Appl 5(3):131–133

    Article  Google Scholar 

  56. Sun L, Anderson MC, Gao F, Hain C, Alfieri JG, Sharifi A, Mccarty GW, Yang Y, Yang Y, Kustas WP, Mckee L (2017) Investigating water use over the Choptank River Watershed using a multi-satellite data fusion approach. Water Resour Res. https://doi.org/10.1002/2017WR020700

    Article  Google Scholar 

  57. Tahir AA, Adamowski JF, Chevallier P, Haq AU, Terzago S (2016) Comparative assessment of spatiotemporal snow cover changes and hydrological behavior of the Gilgit, Astore and Hunza River basins (Hindukush–Karakoram–Himalaya region. Meteorol Atmos Phys, Pakistan). https://doi.org/10.1007/s00703-016-0440-6

    Google Scholar 

  58. Tekeli AE, Sönmez I, Erdi E (2016) Snow-covered area determination based on satellite-derived probabilistic snow cover maps. Arab J Geosci. https://doi.org/10.1007/s12517-015-2149-0

    Article  Google Scholar 

  59. Tikhonov AN (1963) Solution of incorrectly formulated problems and the regularization method. Doklady Akademii Nauk SSSR 151:501–504

    Google Scholar 

  60. Uysal G, Arda A (2016) Streamflow forecasting using different neural network models with satellite data for a snow dominated region in Turkey. Procedia Eng 154:1185–1192. https://doi.org/10.1016/j.proeng.2016.07.526

    Article  Google Scholar 

  61. Uysal G, Ünal A (2018) Monthly streamflow estimation using wavelet-artificial neural network model: a case study on Çamlıdere dam basin, Turkey. Procedia Comput Sci. https://doi.org/10.1016/j.procs.2017.11.234

    Article  Google Scholar 

  62. Van Dijk AIJM (2011) Model-data fusion: using observations to understand and reduce uncertainty in hydrological models. 19th international congress on modelling and simulation, Perth, Australia, 12–16 December 2011. http://mssanz.org.au/modsim2011/index.htm

  63. Wang W, Xiang Y, Gao Y, Lu A, Yao T (2014) Rapid expansion of glacial lakes caused by climate and glacier retreat in the Central Himalayas. Hydrol Process. https://doi.org/10.1002/hyp.10199

    Article  Google Scholar 

  64. Yilmaz AG, Imteaz MA, Jenkins G (2011) Catchment flow estimation using Artificial Neural Networks in the mountainous Euphrates Basin. J Hydrol 410:134–140. https://doi.org/10.1016/j.jhydrol.2011.09.031

    Article  Google Scholar 

  65. Zhu X, Wu X (2004) Class noise versus attribute noise : a quantitative study of their impacts. Artif intell Rev 22:177–210

    Article  Google Scholar 

Download references

Author information

Affiliations

Authors

Corresponding author

Correspondence to Muhammad Hassan.

Ethics declarations

Conflict of interest

On behalf of all authors, the corresponding author states that there is no conflict of interest.

Electronic supplementary material

Below is the link to the electronic supplementary material.

Supplementary material 1 (RAR 4657 kb)

Rights and permissions

Reprints and Permissions

About this article

Verify currency and authenticity via CrossMark

Cite this article

Hassan, M., Hassan, I. Improving ANN-based streamflow estimation models for the Upper Indus Basin using satellite-derived snow cover area. Acta Geophys. 68, 1791–1801 (2020). https://doi.org/10.1007/s11600-020-00491-4

Download citation

Keywords

  • Mountainous catchments
  • Upper Indus Basin
  • Snow cover area
  • Streamflow
  • Artificial neural network (ANN)