Performance Evaluation of Artificial Neural Network Models for Downscaling and Predicting of Climate Variables

Omidvar, Ebrahim; Rezaei, Maryam; Pirnia, Abdollah

doi:10.29252/jwmr.9.18.80

Volume 9, Issue 18 (1-2019) J Watershed Manage Res 2019, 9(18): 80-90 | Back to browse issues page

‎ 10.29252/jwmr.9.18.80

‎ 20.1001.1.22516174.1397.9.18.5.9

Mendeley

Zotero

RefWorks

Omidvar E, Rezaei M, Pirnia A. (2019). Performance Evaluation of Artificial Neural Network Models for Downscaling and Predicting of Climate Variables . J Watershed Manage Res. 9(18), 80-90. doi:10.29252/jwmr.9.18.80
URL: http://jwmr.sanru.ac.ir/article-1-811-en.html

Performance Evaluation of Artificial Neural Network Models for Downscaling and Predicting of Climate Variables

Ebrahim Omidvar ^*¹, Maryam Rezaei¹, Abdollah Pirnia²

1- University of Kashan
2- Sari agriculture and natural resource University

Abstract: (4171 Views)

Atmosphere–ocean coupled global climate models (GCMs) are the main source to simulate the climate of the earth climate. The computational grid of the GCMs is coarse and so, they are unable to provide reliable information for hydrological modelling. To eliminate such limitations, the downscaling methods are used. The present study is focused on simulating the impact of climate change on the behavior of precipitation and temperature of Sirjan synoptic station in Kerman Province. At first, the capability of artificial neural network to downscaling of climate variables that predicted by CanESM2 is tested. Then, using the most appropriate models, the mean monthly temperature and precipitation amounts forecast for future periods under RCP 4.5 scenario. Results of this study for monthly temperature downscaling indicated that the artificial neural network with 2 hidden layer, 8 neurons, with Tangent and Log sigmoid activation function was the best model, so that RMSE, NS and R² were 0.387 , 0.973 and 0.917 respectively. Also, for precipitation variable, the structure with 2 hidden layer feed forward perceptron, 8 neurons, Tangent and Log sigmoid activation function and Levenberg-Marquardt algorithm had better performance, so that RMSE, NS and R² were 2.867, 0.849 and 0.924, respectively. Results indicate that until 2099, amount of monthly mean temperature under RCP 4.5 emission scenario will be increased by 3 (˙C) and the highest increase is predicted for August by 3.9 (˙C) and a lower increase in April by 1.8 (˙C). The results also showed considerable increase of precipitation for June to November and noticeable decrease for March and May months. However, no change occure in annaul scale (inter-annual).

Keywords: Artificial Neural Network, General Circulation Model, Fifth Assessment Report of IPCC, Precipitation, Temperature, Sirjan

Full-Text [PDF 907 kb] (1180 Downloads)

Type of Study: Research | Subject: هواشناسی
Received: 2017/06/7 | Accepted: 2018/06/11

References

1. 1. Arora, V.K., J.F. Scinocca, G.J. Boer, J.R. Christian, K.L. Denman and G.M. Flato. 2011. Carbon emission limits required to satisfy future representative concentration pathways of greenhouse gases. Geophysical Research Letters, 38(5): 1-6. [DOI:10.1029/2010GL046270]

2. Banihabib, M.E., K. Hasani and A.R. Massah Bavani. 2016. Assessment of Climate Change Effects on Shahcheraghi Reservoir Inflow. Journal of water and soil, 30(1): 1-14.

3. Campozano, L., D. Tenelanda, E. Sanchez, E. Samaniego and J. Feyen. 2016. Comparison of Statistical Downscaling Methods for Monthly Total Precipitation: Case Study for the Paute River Basin in Southern Ecuador. Advances in Meteorology, 13 pp. [DOI:10.1155/2016/6526341]

4. Chun, K.P., H.S. Wheater, A. Nazemi and M.N. Khaliq. 2013. Precipitation downscaling in Canadian Prairie Provinces using the LARS-WG and GLM approaches. Canadian Water Resources Journal, 38(4): 311-332. [DOI:10.1080/07011784.2013.830368]

5. Da Silva, I.N., D.H. Spatti, R.A. Flauzino, L. Liboni and S.F. Reis Alves. 2017. Artificial Neural Networks A Practical Course. Springer International Publishing Switzerland, 309pp. [DOI:10.1007/978-3-319-43162-8]

6. De Beule, M., E. Maes, O. De Winter, W. Vanlaere and R. Van Impe. 2007. Artificial neural networks and risk stratification: A promising combination. Mathematical and Computer Modelling, 46: 88-94. [DOI:10.1016/j.mcm.2006.12.024]

7. Falahghalohri, GH. and F. Shakeri. 2016. The application of Artificial Neural Networks in the rainfall prediction. Iranian Journal of Watershed Management Science and Engineering, 9(31): 98-110.

8. Jalali, M., A. Pirnia, K. Solaimani and M. Habibnejad Roushan. 2015. Investigation of Artificial Neural Network in prediction of Stream Flow (Case study: Ghareh Aghaj, Fars province). Journal of Engineering Biaban Ecosystem, 4(6): 15-26.

9. Kan, G.C.H., Q. Li. Yao. Z. Li., Z. Yu, Z. Liu, L. Ding, X. He. and K. Liang. 2015. Improving event-based rainfall-runoff simulation using an ensemble artificial neural network based hybrid data-driven model. Stochastic Environmental Research and Risk Assessment, 29(5): 1345-1370. [DOI:10.1007/s00477-015-1040-6]

10. Kermani, B.G., S.S. Schiffman and H. Troy Nagle. 2005. Performance of the Levenberg-Marquardt neural network training method in electronic nose applications. Sensors and Actuators, 110: 13-22. [DOI:10.1016/j.snb.2005.01.008]

11. Khamchin Moghaddam, F. and H. Rezaee Pajand. 2009. Criticising de martonne regionalization method according to linear moments for maximum daily precipitation in Iran. Journal of Technical Engineering, 2(2): 93-103.

12. Kumar Mann, A., D.A. Jayadevi and A. Pappachen James. 2016. A Survey of Memristive Threshold Logic Circuits. Ieee Transactions On Neural Networks And Learning Systems, 13 pp.

13. Ling, H., H. Xu and J. Fu. 2014. Changes in intra-annual runoff and its response to climate change and human activities in the headstream areas of the Tarim River Basin; China. Quatern. Int. 336: 158-170. [DOI:10.1016/j.quaint.2013.08.003]

14. Mahdi zadeh, S., M. Meftah halghi, S. Seyyed Ghasemi and A. Mosaedi. 2011. Study of precipitation variation due to climate change (Case study: Golestan dam basin). Journal of water and soil conservation, 18(3): 117-132.

15. Maier, H.R. and G.C. Dandy. 2000. Neural networks for the prediction and forecasting of water resources variables: a review of modeling issues and application. Environmental Modeling and Software, 15: 101-124. [DOI:10.1016/S1364-8152(99)00007-9]

16. Meehl, G., C. Covey, T. Delworth, M. Latif, B. McAvaney, J. Mitchell, R. Stouffer and K. Taylor. 2007. The WCRP CMIP3 Multi-Model Dataset: a New Era in Climate Change Research. Bulletin of the American Meteorological Society, 88: 1383-1394. [DOI:10.1175/BAMS-88-9-1383]

17. Meena, P.K., D. Khare and M.K. Nema. 2016. Constructing the downscale precipitation using ANN model over the Kshipra river basin, Madhya Pradesh. Journal of Agrometeorology, 18(1): 113-119.

18. Muhire, I. and F. Ahmed. 2016. Spatiotemporal trends in mean temperatures and aridity index over Rwanda. Theoretical and Applied Climatology, 123(1-2): 399-414 [DOI:10.1007/s00704-014-1353-2]

19. Nastos, P.T., A.G. Paliatsos, K.V. Koukouletsos, I.K. Larissi and K.P. Moustris. 2014. Artiﬁcial neural networks modeling for forecasting the maximum daily total precipitation at Athens, Greece. Atmospheric Research, 144: 141-150. [DOI:10.1016/j.atmosres.2013.11.013]

20. Nazari Sharbian, M., M. Taherioun and A. Ahmadi. 2016. Prediction of climate change effects on notrient of watershed (Case study: Mahabad dam basin). The ninth conference of civil engineering, 10 and 11 May 2016, Ferdouwsi Mashad university.

21. Pirnia, A., K. Solaimani, M. Habibnejad Roshan and A. Besalatpour. 2017. Investigation of land use and climate change impacts on green and blue water resources in the Haraz River Basin of northern Iran, PhD thesis, Agriculture Sciences and Natural Resources of Sari.

22. Plattner, G.K. and T.F. Stocker. 2010. From AR4 to AR5: New Scenarios in the IPCC Process. Workshop Report, 2010.

23. Poitras, V., L. Sushama, F. Seglenieks, M.N. Khaliq and E. Soulis. 2011. Projected Changes to Streamflow Characteristics over Western Canada as Simulated by the Canadian RCM. Journal of Hydrometeorology, 12(6): 1395-1413. [DOI:10.1175/JHM-D-10-05002.1]

24. Santos, T.S., J.R. Chicholikar and L.S. Rathore. 2013. Artificial neural networks and multiple linear regression model using principal components to estimate rainfall over South America, Current science, pp: 2083-2094.

25. Sattari, M.T. and F. Nahrain. 2014. Monthly rainfall prediction using Artificial Neural Networks and M5 model tree (Case study: Stations of Ahar and Jolfa). Irrigation & Water Engineering, 4(14): 83-98.

26. Vu, M.T., T.H. Aribarg, S. Supratid and S. Raghavan. 2015. Statistical downscaling rainfall using artificial neural network: significantly wetter Bangkok. Theor Appl Climatol, pp: 1-15.

27. Wang, H., L. Chen and X. Yu. 2015. Distinguishing human and climate influences on stream flow changes in Luan River basin in China; Catena, 136: 182-188. [DOI:10.1016/j.catena.2015.02.013]

28. Yesilkanat, C.M., Y. Kobya. H. Tas¸kın and U. Çevik. 2017. Spatial interpolation and radiological mapping of ambient gamma dose rate by using artificial neural networks and fuzzy logic methods. Journal of Environmental Radioactivity, (175-176): 78-93. [DOI:10.1016/j.jenvrad.2017.04.015]

29. Zhang, D., X.B. Liu, Q. Zhang, K. Liang and C. Liu. 2016. Investigation of factors affecting intra-annual variability of evapotranspiration and stream flow under different climate conditions; Journal of Hydrology, 543: 759-769. [DOI:10.1016/j.jhydrol.2016.10.047]

30. Zhang, Y., Q. You, C. Chen and J. Ge. 2016. Impacts of climate change on stream flows under RCP scenarios: A case study in Xin River Basin, China. Atmospheric Research, 178: 521-534. [DOI:10.1016/j.atmosres.2016.04.018]

31. Zoqi, M.J. and M. Saeeidi. 2010. Modeling Leachate Generation Using Artificial Neural Networks. Journal of water and waste water, 22(1): 76-84.