Comparing the Performance of SARIMA and Holt-Winters Time Series Models With Artificial Intelligence Methods in Dust Storms Forecasting (Case Study: Sistan and Baluchestan Province)

Document Type : Full length article


1 Ph.D. Candidate, Department of Irrigation & Reclamation Engineering, Campus of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

2 Associate Professor, Department of Irrigation & Reclamation Engineering, Campus of Agriculture and Natural Resources, University of Tehran, Karaj, Iran

3 Professor, Department of Irrigation & Reclamation Engineering, Campus of Agriculture and Natural Resources, University of Tehran, Karaj, Iran


The impact of dust phenomenon in Iran is so great that it has involved more than half of the country's provinces with problems and limitations one way or another. In addition to environmental impacts, it has disrupted implementing sustainable national development plans, having already brought about many negative consequences. Increased number of dust storms in recent years in the east and southeast of the country, especially in Sistan and Baluchestan Province, and consequently the decrease of air quality in these areas, has doubled the importance of forecastingthis phenomenon. On the other hand, most domestic studies in this field are related to the process of small-scale dust phenomena, synoptic studies, and its satellites. Therefore, considering that this phenomenon has had adverse effects and negative consequences on social, economic, and healthcare aspects of human life, it is necessary to study, forecast, and measure its correlation with climate variations.
Materials and Methods
This study aimed at comparing the performance of SARIMA and Holt-Winters time series models with artificial intelligence methods, including neural networks based on Radial Base Functions (RBF) and Adaptive Neural-Fuzzy Inference System (ANFIS) to forecast the Frequency of Dust Storm Days (FDSD) in the next season. For this purpose, it used World Meteorological Organization codes as well as hourly dust data from five synoptic stations in Sistan and Baluchestan province with a statistical period of 25 years (1990-2014). The observations of meteorological phenomena were recorded once every three hours, making it eight times a day in total. In these observations, the visual phenomena of the climate were defined according to the guidelines of the World Meteorological Organization in 100 codes (00-99), in which 11 codes were used to record and report the phenomenon of dust in different meteorological stations. Following the time series of days with dust storms, the FDSD index was forecasted, using four methods SARIMA, Holt-Winters, RBF, and ANFIS.
Results and Discussion
According to the time series’ results, the FDSD index in Saravan, Khash, Iranshahr, and Zahedan stations displayed relatively small variations that were scattered throughout the time series, but with more dusty days at Zabol station, the variations’ scattering decreased and its intensity increased. Also, the peak values of dust were concentrated in close vicinity of one another, indicating the occurrence of successive dust storms at this station from 2000 onwards. As can be seen in ACF and PACF diagrams of the studied stations, significant time intervals indicate a correlation between the time values that make it possible to model and forecast the future values (next season) of the FDSD index for all five stations studied. The range of attraction change and moving average got determined according to partial autocorrelation and autocorrelation functions and using appropriate evaluation criteria, the best time series model was extracted for each station. In the Dickey-Fuller test, the significance level was considered to be P-Value < 0.05. According to this test, only the time series of Zabol Station was unstable, confirming the results of ACF and PACF diagrams of the studied stations. Results showed that ANFIS Method performed better than other methods in all studied stations. Thus, in this method the evaluation criteria ranged from 0.72 to 0.95 for R, from 0.57 to 0.51 for RMSE, from 0.42 to 0.40 for MAE, and from 0.71 to 0.96 for NS. Also, the average frequency of days with dust storms on a seasonal scale varied from 1.06 to 7.11, allowing forecasting accuracy of all methods to increase as the FDSD index mounted. In SARIMA time series model, the correlation coefficient (R) between the observed and forecasted values of the FDSD index rose from 0.64 to 0.79. As for Holt-Winters, RBF, and ANFIS methods, this value varied between 0.70 and 0.87, 0.69 and 0.92, and 0.72 and 0.95, respectively. Moreover, based on the results of the observed and forecasted values, the greater the FDSD index in the studied stations (progress from Saravan to Zabol Station), the more the compatibility of observed and forecasted values in all methods (time series models and artificial intelligence methods) with Semi-constructor of the first quarter. The results from the Z test also proved the assumption that stated that zero-based on the mean equal of the time series of FDSD index’ observed and forecasted values were not rejected in none of the studied stations, according to ANFIS and RBF methods at 1% and SARIMA and Holt-Winters time series models at 5% error level.
The results showed that as the frequency of days with dust storms in Saravan and Khash stations got less, the Holt-Winters time series model showed an almost similar and better performance than the RBF method. This indicates this model’s high capability to forecast low values of FDSD index. The results also showed that the SARIMA time series model, compared to other forecasting methods, did not show a high ability to forecast FDSD index at any of the studied stations. Furthermore, despite the low frequency of days with dust storms at Iranshahr station, compared to Zahedan station, all FDSD index forecasting methods had a better performance and higher accurately than Zahedan station, based on the evaluation criteria, which can be searched due to the presence of a complete series without FDSD index termination at Iranshahr station. The results of this study can be useful for forecasting and managing the consequences of dust storms in the studied areas. On the other hand, when forecasting the FDSD index in Sistan and Baluchestan province, the optimal predictor model has been complex. For all of the stations studied, the model that used three or four steps of the predictive delay was recognized as the best predictor model. Therefore, particles leftover from previous storms could be an important cause for the impact of the last few seasons’ dust storms on the formation of new ones in the coming seasons.


انتظاری، ع. و سروستان، ر. (1396). بررسی گردوغبار و پیش‏بینی آن در شهرهای استان خوزستان با استفاده از مدل‏های سری زمانی، مطالعات علوم محیط ‏زیست، 2(4): 5۳5-5۴5.
انصاری قوجقار، م.؛ پورغلام آمیجی، م.؛ بذرافشان، ج.؛ لیاقت، ع. و عراقی‏نژاد، ش. (1399). مقایسة کارایی شبکه‏های عصبی آماری، فازی، و پرسپترونی در پیش‏بینی طوفان‌های گردوغبار در نواحی بحرانی کشور، تحقیقات آب و خاک ایران (آمادة انتشار).
جمالی‌زاده تاج‏آبادی، م. ر.؛ مقدم‌نیا، ع. ر. و پیری، ج. (1386). بررسی توانایی دو روش شبکه‏های عصبی مصنوعی و ماشین‏های بردار پشتیبان در پیش‏بینی طوفان‏های گردوخاک شهر زابل، چهارمین همایش ملی علوم و مهندسی آبخیزداری ایران، مدیریت حوزه‏های آبخیز، دانشکدة منابع طبیعی دانشگاه تهران، 1 اسفند.
حسین حمزه، ن.؛ فتاحی، ا.؛ ذوالجودی، م.؛ غفاریان، پ. و رنجبر، ع. (1395). تحلیل همدیدی و دینامیکی پدیدة گردوغبار و شبیه‏سازی آن در جنوب غرب ایران در تابستان ۱۳۸4، تحلیل فضایی مخاطرات محیطی، 3(1): ۹۱-102.
زینالی، ب. (1395). بررسی روند تغییرات فراوانی روزهای همراه با طوفان‏های گردوغباری نیمة غربی ایران، مخاطرات محیط طبیعی، 5(7): ۸۷-۱۰۰.
سبحانی، ب.؛ صفریان زنگیر، و. و فیض‏الله‌زاده، س. (1399). مدل‏سازی و پیش‏بینی گردوغبار در غرب ایران، پژوهش‏های جغرافیای طبیعی، 52(1): ۱۷-35.
سبحانی، ب.؛ صلاحی، ب. و گل‌دوست، ا. (1394). بررسی گردوغبار و ارزیابی امکان پیش‏بینی آن بر اساس روش‏های آماری و مدل ANFIS در ایستگاه زابل، جغرافیا و توسعة پایدار، 13(38): ۱۲۳-138.
سروستان، ر. و فلاح قالهری، غ. (1399). بررسی و پیش‏بینی پدیدة گردوغبار در استان خوزستان با استفاده از مدل‏های سری زمانی باکس جنکینز، مهندسی و مدیریت آبخیز.
شاکر سوره، ف. و اسدی، ا. (1398). ارتباط بین خشک‌سالی‏های هواشناسی و هیدرولوژیکی در دشت سلماس، مهندسی اکوسیستم بیابان، 8(22): ۸۹-۱۰۰.
عبدالشاه‌نژاد، م.؛ خسروی، ح.؛ نظری سامانی، ع. ک.؛ زهتابیان، غ. و علم‌بیگی، ا. (1399). تعیین چهارچوب مفهومی ریسک گردوغبار بر مبنای سنجش تاب‏آوری (بررسی موردی: جنوب غرب کشور)، پژوهش‏های راهبردی در علوم کشاورزی و منابع طبیعی، 5(1): ۳۳-44.
عراقی‏نژاد، ش. و انصاری قوجقار، م. (1396). بررسی تأثیر سرعت بیشینة باد بر روند فراوانی روزهای همراه با طوفان‏های گردوغباری (مطالعة موردی: استان لرستان)، چهارمین همایش ملی فرسایش بادی و طوفان‏های گردوغبار، انجمن علمی مدیریت و کنترل مناطق بیابانی ایران، پژوهشکدة مناطق خشک و بیابانی، دانشگاه یزد، 1۶-1۷ اسفند.
عراقی‏نژاد، ش.؛ انصاری قوجقار، م.؛ پورغلام آمیجی، م.؛ لیاقت، ع. و بذرافشان، ج. (1397). تأثیر نوسانات اقلیمی بر فراوانی طوفان‏های گردوغبار در ایران، مهندسی اکوسیستم بیابان، 7(21): ۱۳-۳۲.
فرج‌زاده، م. و علیزاده، خ. (1390). تحلیل زمانی و مکانی طوفان‏های گردوخاک در ایران، برنامه‏ریزی و آمایش فضا، 15(1): ۶۵-84.
قربانی، س. و مدرس، ر. (1398). مدل‏سازی رابطة فراوانی طوفان‏های گردوغبار با متغیرهای اقلیمی فصل تابستان در مناطق بیابانی ایران، علوم آب و خاک، 23(3): ۱۲۵-140.
گودرزی، ل. و روزبهانی، ع. (1396). بررسی کارایی مدل‏های سری زمانی آریما و هالت- وینترز در پیش‏بینی دما و بارش ماهانه (مطالعة موردی: ایستگاه لتیان)، علوم و مهندسی آبیاری، 40(3): ۱۳۷-149.
مهرابی، ش.؛ سلطانی، س. و جعفری، ر. (1394). بررسی رابطه بین پارامترهای اقلیمی و وقوع ریزگردها (مطالعة موردی: استان خوزستان)، علوم آب و خاک، 19(71): ۶۹-۸۰.
یارمرادی، ز.؛ نصیری، ب.؛ کرم‏پور م. و محمی، غ. ح. (1397). تحلیل روند فراوانی روزهای گردوغباری در نیمة شرقی ایران در ارتباط با نوسانات اقلیمی، مهندسی اکوسیستم بیابان، 7(18): ۱-۱۴.
Aboagye-Sarfo, P.; Mai, Q.; Sanfilippo, F. M.; Preen, D. B.; Stewart, L. M. and Fatovich, D. M. (2015). A comparison of multivariate and univariate time series approaches to modelling and forecasting emergency department demand in Western Australia. Journal of biomedical informatics, 57: 62-73.
Ahmed, N. K.; Atiya, A. F.; Gayar, N. E. and El-Shishiny, H. (2010). An empirical comparison of machine learning models for time series forecasting. Econometric Reviews, 29(5-6): 594-621.
Aigang, L.; Tianming, W.; Shichang, K. and Deqian, P. (2009). On the relationship between global warming and dust storm variation in China. In 2009 International Conference on Environmental Science and Information Application Technology (Vol. 2, pp. 59-62). IEEE.
Aliyari, M.; Teshnehlab, M. and Khaki Sedigh, A. (2008). Short-term forecast of air pollution by neural networks, delayed memory line, gamma and ANFIS with PSO-based educational methods. Control journal, 2(1): 1-19.
Amgalan, G.; Liu, G. R.; Lin, T. H. and Kuo, T. H. (2017). Correlation between dust events in Mongolia and surface wind and precipitation, Terr. Journal of Atmospheric & Ocean Science, 28 (1): 23-32.
Asplin, B. R.; Flottemesch, T. J. and Gordon, B. D. (2006). Developing models for patient flow and daily surge capacity research. Academic Emergency Medicine, 13(11): 1109-1113.
Chen, S.; Cowan, C. F. N. and Grant, P. M. (1991). Orthogonal Least Squares Learning Algorithm for Radial Basis Function Networks. IEEE Transactions on Neural Networks, 2(2): 302-309.
Cochrane, J. H. (2005). Time series for macroeconomics and finance. Manuscript, University of Chicago, 1-136.
Goudie, A. (2014). Review Desert dust and human health disorders. Journal of Environment International, 63(3): 101-113.
Goudie, A. S. and Middleton, N. J. (2006). Desert dust in the global system. Springer Science & Business Media.
Hahnenberger, M. and Nicoll, K. (2014). Geomorphic and land cover identification of dust sources in the eastern Great Basin of Utah, USA. Geomorphology, 204: 657-672.
Herweijer, C.; Seager, R.; Cook, E. R. and Emile-Geay, J. (2007). North American droughts of the last millennium from a gridded network of tree-ring data. Journal of Climate, 20(7): 1353-1376.
Hyndman, R. J. and Khandakar, Y. (2008). Automatic time series forecasting: the forecast package for R. Journal of Statistical Software, 27(3): 1-22.
Jang, J. S. (1993). ANFIS: adaptive-network-based fuzzy inference system. IEEE transactions on systems, man, and cybernetics, 23(3): 665-685.
O’Loingsigh, T.; McTainsh, G. H.; Tews, E. K.; Strong, C. L.; Leys, J. F.; Shinkfield, P. and Tapper, N. J. (2014). The Dust Storm Index (DSI): a method for monitoring broadscale wind erosion using meteorological records. Aeolian Research, 12: 29-40.
Rashki, A.; Kaskaoutis, D. G.; Goudie, A. S. and Kahn, R. A. (2013). Dryness of ephemeral lakes and consequences for dust activity: the case of the Hamoun drainage basin, southeastern Iran. Science of the Total Environment, 463: 552-564.
Singh, A. and Mishra, G. C. (2015). Application of Box-Jenkins method and Artificial Neural Network procedure for time series forecasting of prices. Statistics in Transition new series, 1(16): 83-96.
Tanarhte, M.; Hadjinicolaou, P. and Lelieveld, J. (2012). Intercomparison of temperature and precipitation data sets based on observations in the Mediterranean and the Middle East. Journal of Geophysical Research: Atmospheres, 117(D12).
Xu, X.; Levy, J. K.; Zhaohui, L. and Hong, C. (2006). An investigation of sand–dust storm events and land surface characteristics in China using NOAA NDVI data. Global and Planetary Change, 52 (1-4): 182-196.
Volume 52, Issue 4
January 2021
Pages 567-587
  • Receive Date: 16 June 2020
  • Revise Date: 22 November 2020
  • Accept Date: 22 November 2020
  • First Publish Date: 21 December 2020