Prediction of Dust Storm Frequency in Iraq by Artificial Neural Networks
Article Sidebar
Main Article Content
Abstract
Dust storms in deserts, arid, and semi-arid regions are considered a more costly and destructive atmospheric event that can cause massive damage to natural environments and human lives. This study uses an intelligent artificial neural network consisting of three layers (input, hidden, output) to predict the frequency of dust storm events. The neural network Back Propagation Artificial Neural Network (PBANN) algorithms employed; this network is divided into three algorithms training for predicted monthly dust storm frequency events for the first year, second monthly annual events, and third annual frequency events for a period extended to 47 years from 1971-2017. This year’s taken as a data basis in three stations (Baghdad, Basra, Rutba, and Mosul) that represent regions middle, south, west, and north respectively for Iraq country. To estimate the difference between the observed (O) and predicted (P), dust storm number events, many statistical indices were applied such as correlation coefficient R, Route Mean Square Error, Normal mean square error, and difference bias, these four indices were calculated to the performance of the optimum PBANN scheme. It was found that the optimum performance model according to these indices for the algorithmic function to predict monthly annual and annual frequency data events, but the situation difference for predicted one-year 2017 is because frequency observed data is few and sporadic it’s not continuous specifically in stations Rutba and Mosul.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution 4.0 International License.
How to Cite
References
[1] H. H. Mhmmod, M. Yilmaz, and S. O. Sulaiman, “Simulation of the flood wave caused by hypothetical failure of the Haditha Dam,” J. Appl. Water Eng. Res., vol. 11, pp. 66–76, 2023, https://doi.org/10.1080/23249676.2022.2050312.
[2] H. S. I. Harba, “Hybrid approach of prediction daily maximum and minimum air temperature for Baghdad city by used artificial neural network and simulated annealing,” Iraqi J. Sci., vol. 59, no. 1C, pp. 591–599, 2018, https://doi.org/10.24996/ijs.2018.59.1C.16.
[3] T. S. A. Almurayziq, An investigation of ensemble learning in dust storm prediction using machine learning techniques, Ph.D. dissertation, Univ. of Brighton, Brighton, UK, 2018. Available: https://research.brighton.ac.uk/files/6145705/Correction.pdf
[4] A. F. Hassoon, “Determination trends and abnormal seasonal wind speed in Iraq,” Int. J. Energy Environ., vol. 4, no. 4, pp. 615–628, 2013. Available: https://www.ijee.ieefoundation.org/vol4/issue4/IJEE_06_v4n4.pdf
[5] A. M. Al-Salihi, A. M. Al-Lami, and A. J. Mohammed, “Prediction of monthly rainfall for selected meteorological stations in Iraq using back propagation algorithms,” J. Environ. Sci. Technol., vol. 6, no. 1, pp. 16–28, 2013, https://doi.org/10.3923/jest.2013.16.28.
[6] K. Andrej, J. Bostjan, and A. Kozjek, “Introduction to the artificial neural networks,” in Artificial Neural Networks – Methodological Advances and Biomedical Applications, Slovenia, 2011. Available: https://www.researchgate.net/profile/Kenji-Suzuki-2/publication/319316102_Artificial_Neural_NetworksMethodological_Advances_and_Biomedical_Applications/links/59a42f16aca272a6461bb35e/Artificial-Neural-Networks-Methodological-Advances-and-Biomedical-Applications.pdf
[7] A. Bhat, A. Kumar, and K. Czajkowski, “Development and evaluation of a dispersion model to predict downwind concentrations of particulate emissions from land application of class B biosolids in unstable conditions,” Indoor and Outdoor Air Pollution, pp. 29–40, 2011, https://doi.org/10.5772/29513.
[8] M. I. Chacon-Murguía, Y. Quezada-Holguín, P. Rivas-Perea, and S. Cabrera, “Dust storm detection using a neural network with uncertainty and ambiguity output analysis,” in Mexican Conf. Pattern Recognition, Berlin, Germany: Springer, pp. 305–313, 2011. Available: https://link.springer.com/chapter/10.1007/978-3-642-21587-2_33
[9] T. Chai and R. R. Draxler, “Root mean square error (RMSE) or mean absolute error (MAE)? Arguments against avoiding RMSE in the literature,” Geosciences Model Dev., vol. 7, no. 3, pp. 1247–1250, 2014, https://doi.org/10.5194/gmd-7-1247-2014.
[10] Y. S. Chung and M. B. Yoon, “On the occurrence of yellow sand and atmospheric loadings,” Atmos. Environ., vol. 30, no. 13, pp. 2387–2397, 1996, https://doi.org/10.1016/1352-2310(95)00251-0.
[11] X. Feng et al., “Artificial neural networks forecasting of PM 2.5 pollution using air mass trajectory based geographic model and wavelet transformation,” Atmos. Environ., vol. 107, pp. 118–128, 2015, https://doi.org/10.1016/j.atmosenv.2015.02.030.
[12] H. K. H. Furman, “Dust storms in the Middle East: Sources of origin and their temporal characteristics,” Indoor Built Environ., vol. 12, no. 6, pp. 419–426, 2003, https://doi.org/10.1177/1420326X03037110.
[13] S. Ghosh, A. Nag, D. Biswas, J. P. Singh, S. Biswas, D. Sarkar, and P. P. Sarkar, “Weather data mining using artificial neural network,” in Proc. IEEE Recent Advances in Intelligent Computational Systems (RAICS), Trivandrum, India, pp. 192–195, 2011, https://doi.org/10.1109/RAICS.2011.6069300.
[14] E. Grossi and M. Buscema, “Introduction to artificial neural networks,” Eur. J. Gastroenterol. Hepatol., vol. 19, no. 12, pp. 1046–1054, 2007, https://doi.org/10.1097/meg.0b013e3282f198a0.
[15] M. Huang et al., “Application of artificial neural networks to the prediction of dust storms in Northwest China,” Global Planet Change, vol. 52, no. 1–4, pp. 216–224, 2006, https://doi.org/10.1016/j.gloplacha.2006.02.006.
[16] S. Kaboodvandpour et al., “Assessing the accuracy of multiple regressions, ANFIS, and ANN models in predicting dust storm occurrences in Sanandaj, Iran,” Nat. Hazards, vol. 78, no. 2, pp. 879–893, 2015, https://doi.org/10.1007/s11069-015-1748-0.
[17] H. Maleki et al., “Air pollution prediction by using an artificial neural network model,” Clean Technol. Environ. Policy, pp. 1–12, 2019. Available: https://pmc.ncbi.nlm.nih.gov/articles/PMC8075317/
[18] J. M. Mitchell, “The effect of atmospheric particles on radiation and temperature,” Man's Impact on Climate, 1971. Available: https://journals.ametsoc.org/view/journals/apme/10/4/1520-0450_1971_010_0703_teoaao_2_0_co_2.pdf
[19] T. Nihlén and S. Olsson, “Influence of eolian dust on soil formation in the Aegean area,” Z. Geomorphology, vol. 39, no. 3, pp. 341–361, 1995, https://doi.org/10.1034/j.1600-0889.47.issue3.7.x.
[20] P. Rivas-Perea, J. G. Rosiles, and M. I. M. Chacon, “Traditional and neural probabilistic multispectral image processing for the dust aerosol detection problem,” Southwest Symp. Image Anal. Interpret., pp. 169–172, 2010, https://doi.org/10.1109/SSIAI.2010.5483890.
[21] F. Wang et al., “Identification of regional atmospheric PM10 transport pathways using HYSPLIT, MM5-CMAQ and synoptic pressure pattern analysis,” Environ. Model Software, vol. 25, no. 8, pp. 927–934, 2010, https://doi.org/10.1016/j.envsoft.2010.02.004.
[22] S. S. Zanetti et al., “Estimating evapotranspiration using artificial neural network and minimum climatological data,” J. Irrigation Drain Eng., vol. 133, no. 2, pp. 83–89, 2007, https://doi.org/10.1061/(ASCE)0733-9437(2007)133:2(83).
[23] Y. Zhang et al., “Application of WRF/Chem over East Asia: Part I. Model evaluation and intercomparing with MM5/CMAQ,” Atmos. Environ., vol. 124, pp. 285–300, 2016, https://doi.org/10.1016/j.atmosenv.2015.07.022.
[24] P. J. Taylor, “City generics: external urban relations in ancient-Mesopotamian and modern-global city networks,” Urban Geography, vol. 40, no. 8, pp. 1210–1230, Sep. 2019, https://doi.org/10.1080/02723638.2019.1567203.