Investigation of Sea Level Changes due to Climate Parameters Using Decision Tree Algorithm, Makran Coast, the Northern Oman Sea

Document Type : Full length article

Authors

1 PhD Candidate in Physical Geography, Faculty of Geographical Sciences and Planning, University of Isfahan, Isfahan, Iran

2 Associate Professor of Physical Geography, Faculty of Geographical Sciences and Planning, University of Isfahan, Isfahan, Iran

3 Assistant Professor of Physical Geography, Faculty of National Defense, University of National Defense, Tehran, Iran

4 Professor of Strategic Management, Faculty of National Defense, University of National Defense, Tehran, Iran

Abstract

Introduction    
The relationship between form and process is very important in geomorphology. By changing in the process, the forms will be changed and new processes will be created in reponse to the new forms. Sea level changes mainly include tidal variations and changes due to atmospheric factors. Tidal flows are also affected by coastal washing during their daily advancement and retreat on tidal slopes and tidal zones. The formation of many coastal geomorphologic forms is the result of their involvement. Climatic factors cause short time fluctuations and tidal cycles and long term fluctuations in medium level of sea. Sea level fluctuations influence important aspects of coastal climate, economic planning, agricultural issues, environmental problems and all other affairs related to sailing and marine constructions.
Torabi Azad and Honarmand (2016) performed a concise investigation about sea level changes in Bandar Abbas and Booshehr Stations in a period of 11 years (2000 to 2010) and analyzed and computed barometric effects, wind force and temperature on the sea level mean. The results showed that sea level mean in these stations has incremental trend by 5 cm and 4 cm respectively in the mentioned seaports.
Srivastava (2016) investigated the combined use of quantitative forecasting methods for sea level rise using exponential smoothing state space models (ESMs) and an Autoregressive Integrated Moving Average (ARIMA) model with sea level data over 17 years (1994–2010). The results of this present study suggest that the rate of Arabian Sea level rise is high, and if this is not taken into consideration, many coastal areas may be affected by climate-change-induced habitat loss in future.
Akbari et al (2017) applied 3D FVCOM Model in order to investigate and analyze important tidal components in a vast area including Persian Gulf, Hormuz Strait, Oman Sea and Arab sea. The results of this research showed that there is four kinds of tides in Persian Gulf including Daily, semi-Daily, daily compounded and semi-daily compounded tides. On the other regions, there is just semi-daily compounded tide. The purpose of this research is to investigate the effects of climate change parameters (temperature, pressure, and wind rate) on the sea level fluctuations in an annual, seasonal and monthly intervals and 20-year period in northern coasts of Oman Sea.
 Matarials and methods
The study area of this research is stretched from Jask port (with longitude of 570 46' E and latitude of 250 40' N) to Gowatre Bay in the terminal point of southeast Iran and at Pakistan border (with longitude of 570 46' E and latitude 250 10' N).
The sea level changes have been obtained from tide gauges of IOC (Intergovernmental Oceanographic Commission) in the stations of hydrography of Jask and Chabhar ports during 1997 to 2016. The tide gauges for the mentioned stations presented 1440 datum. In fact, they registered sea level in every minutes. In order to compute the data based on monthly averages, the tidal effects should be deleted and computed into level fragment that means sea level minus tidal effect. According to the presented information in meteorological organization since 1997 to 2016, we used pressure, temperature and wind data in research stations as monthly means and the monthly, seasonal and annual diagrams.  
In this research, Meta heurestic-Algorithm (Decision Tree Algorithm) and CARD regression tree decomposition algorithm (Classification and regression tree) is used as a type of regression decision tree for prediction purposes. Different elements have been used in simulation using decision tree model. These elements have been introduced as independent variables to the model and simulations have been made to predict the target variable. In order to verify the relationship between the final decision trees based on the statistical index, graphical graphs and correlation coefficients were obtained from the field operation method, visual inspection, ground monitoring and verification of control points.
Results and discussion
The model has been executed with three independent variables including temperature, pressure and wind in 240 data rows. It should be noted that we have used these 72 rows in the training phase and 168 rows in the test phase. The decision tree model in the Jask area has three parameters of wind pressure and wind speed, and the tree is based on these two parameters that the model did not use the temperature parameter in the decision tree. It was not selected as an effective parameter. In Chabahar region, all three parameters are used in the model. The above-mentioned model has a very high performance in predicting values. In most of the 12-month intervals, the model performed its predictions close to real values; in other words, the tree created using the data has a good prediction process and can simulate the changes well. According to the above figure, the predictions were evaluated. The results indicate that this model can be predicted with high accuracy in 95% confidence level for the region. Since the temperature parameter has not been able to predict the response variable in the decision tree, the model has been eliminated, and the final equation of Jask and Chabahar is as follows.
MSL(Jask) =13.197+5.619T(1.102)-11.092P(0.195)+7.208W(0.71)
MSL(Chabahar)=  4.520+1.529 T (1.089)-1.596P(0.87)+2.776 W(0.316)
Conclusion
The fluctuations of MSL are among the general methods of analysis. Therefore, accurate prediction can provide conditions for assessing the status. The purpose of this study was to investigate the effects of data pre-processing on the performance of nonlinear decision tree model in predicting MSL in Jask and Chabahar. The results of this study in all simulations show that pressure and wind parameters are more effective in the final model. This indicates the importance of these parameters in predicting future MSL. The close relationship between wind speed and water level changes is evident with the strong positive correlation coefficient of the Jask station compared with the Chabahar station in the annual windfall of both regions. The relationship between the final models is derived from the decision tree algorithm in MSL prediction using available data. Investigating the related geomorphologic forms in the study area, the tidal range fluctuations in the Chabahar region are ranged from 1 to 1.5 meters. Therefore, in a closer examination of the processes governing the environments around the coastline, it is necessary to study the status of the tidal region and the influential climatic parameters.

Keywords

Main Subjects


آزرم‏سا، ع.؛ شفیعی، س. و کامیابی‏گل، ر. (1387). تغییرات ماهانة میانگین تراز سطح آب در خلیج فارس، دریای عمان، و شمال دریای عرب در 1994، مجلة فیزیک زمین و فضا، 34(2): 83-96.
آزموده اردلان، ع. و طوریان، م. (2010). مدل‏سازی جزرومد در دریای عمان و خلیج‏فارس با استفاده از داده‏های ارتفاع‏سنجی ماهواره‏ای و تایدگیج‏های ساحلی، مجلة فیزیک زمین و فضا، 36: 15-25.
ترابی ‏آزاد، م. و هنرمند، م. (1395). بررسی تغییرات تراز دریا در اثر پارامترهای هواشناختی با استفاده از مدل‏های آماری در سواحل شمالی خلیج فارس، مجلة پژوهش علوم و فنون دریایی، 11(1): 53-65.
حسن‏زاده، ا و علیزاده، ح. (1382). تراز دریا و تغییرات آب و هوا در سواحل خلیج فارس، سومین کنفرانس منطقه‏ای و اولین کنفرانس ملی تغییر اقلیم، اصفهان .
رضایی، ا. (1387). مطالعة نوسانات تراز آب دریا با استفاده از داده‏های ماهواره‏ای و جزرومدسنجی در سواحل شمالی دریای عمان (چابهار و جاسک)، پایان‏نامة کارشناسی ارشد، رشتة فیزیک دریا، دانشگاه آزاد اسلامی واحد تهران شمال.
رهنماراد، ج. و صاحب‏زاده، ب. (1389). زمین‏شناسی و ژئومورفولوژی جنوب ‏شرق ایران برای بازدیدهای صحرایی، زاهدان، انتشارات دانشگاه آزاد اسلامی واحد زاهدان.
صفاری، م. (1384). گردش سطحی دریای عمان با استفاده از ارتفاع‏سنجی ماهوار‏ه‏ای، پایان‏نامة کارشناسی ارشد، دانشگاه اصفهان.
صفرقلی، ا.؛ محمدی، ا.؛ نجارتبار، م.؛ حاج‏محمدی، ا. و سیدکریمی، م. (1394). آمارنامة دریایی ایران، چ2، تهران: انتشارات ستاد توسعة فناوری و صنایع دانش‏بنیان دریایی.
گورابی، ا. و امامی، ک. (1396). تأثیرات نوزمین‏ساخت بر تغییرات مورفولوژیک حوضه‏های زهکشی سواحل مکران، جنوب شرق ایران، مجلة پژوهش‏های ژئومورفولوژی کمّی، 6(1): 74-89.
مشایخ‏پور، م.؛ عمادی، س‏ر. و ترابی ‏آزاد، م. (1396). بررسی تغییرات فصلی دامنة مؤلفه‏های جزرومدی در سواحل شمالی خلیج‏فارس و دریای عمان، دوفصلنامة علمی- پژوهشی هیدروفیزیک، 2(2): 67-77.
مهدیزاده، م. و کسبی، م. (1393). پیش‏بینی ارتفاع امواج ناشی از مد طوفان در سواحل ایرانی دریای عمان، مجلة علوم و فنون دریایی، 13(1): 41-50.
نظریان، م. (1381). تعیین روند تغییرات دوسالانة سطح تراز دریا با استفاده از دو روش آلتی‏متری ماهواره‏ای و جزرومدسنجی در ناحیة دریای عمان- بندر چابهار، چاپ در یازدهمین کنفرانس ژئوفیزیک ایران، تهران.
نوحه‏گر، ا.؛ حسین‏زاده، م‏م. و حیدرزاده، م. (1389). تأثیر عناصر اقلیمی محلی بر نوسانات کوتاه‏مدت تراز دریا (مطالعة موردی: سواحل شمالی تنگة هرمز- بندرعباس)، نشریة پژوهش‏های اقلیم‏شناسی، 1(1 و 2): 77-88.
نوحه‏گر، ا. و حسین‏زاده، م. (1390). دینامیک دریا و عوامل مؤثر بر نوسانات تراز دریا در تحول قاعدة دلتاهای شمال تنگة هرمز، مجلة جغرافیا و برنامه‏ریزی محیطی، 22(3): 125-142.
نوحه‏گر، ا. و یمانی، م. (1385). ژئومورفولوژی ساحل شرقی تنگة هرمز با تأکید بر فرسایش بادی، هرمزگان، انتشارات دانشگاه هرمزگان.
یمانی، م. (1378). اثر حرکات آب دریای عمان در تشکیل و تکامل تالاب‏های جزرومدی، مجلة پژوهش‏های جغرافیایی، 37: 19-34.
یمانی، م. و محمدنژاد، و. (1392). ژئومورفولوژی ساحلی، چ2، تهران: مؤسسة انتشارات دانشگاه تهران.
Akbari, P.; Sadrinasab, M.; Chegini, V. and Siadatmousavi, M. (2017). Tidal Constituents in the Persian Gulf, Gulf of Oman and Arabian Sea, a Numerical Study, Indian Journal of Geo-Marine Sciences, 45(8): 1010-1016.
Ardalan, A.A. and Toorian, M.J. (2010). A new tidal model for the Persian Gulf and Oman Sea based on satellite altimetry and coastal tidal gauge observations, Journal of the Earth and Space Physics, 36(3): 15-25 (In Persian)
Azarmsa, A.; Shafiee, S. and Kamyabi Gol, R. (2008). Sea level mean monthly variations in the Persian Gulf, Oman Sea and the North of the Arabian Sea, in 1994, Journal of the Earth & Space Physics, 34(2): 83-96 (In Persian).
British Admiralty Org (1982). The Persian Gulf Pilot and its Approaches, Twelfth Edition.
Gurabi, A. and Emami, K. (2017). Neotectonics influences on morphological variations of Makran costal basins, SE Iran, 6(1): 74-89 (In Persian).
Hassanzadeh, A.  and Alizadeh , H. (2003). Sea Level and Climate Change on the Gulf Coastal, Third Regional Conference and First National Conference on Climate Change, Isfahan (In Persian).
IOC. (1985). Manual on sea-level measurement and interpretation, Vol. 1 - Basic procedures, Intergovernmental Oceanographic Commission Manuals and Guides, No. 14. IOC, Paris.
Mahdizadeh, M.M. and Kasbi, M.N. (2014). Estimation of Storm Surge Dominated Wave Height in Iranian Coastlines of Oman Sea, Journal of Marine Science and Technology, 13(1): 41-50 (In Persian).
Mahongo, S.B. (2009). The changing global climate and its implication on sea level trends in Tanzania and the Western Indian Ocean Region, Journal of Marine Science, 8(2): 147-159.
Mashayekhpour, M.; Emadi, S.R. and Torabi Azad, M. (2017). Study of seasonal variations of tidal components in the northern coasts of Persian Gulf and Oman Sea, Journal of Two Hydrological Research Series, 2(2): 67-77 (In Persian).
National Cartographic Center of Iran (NCC) P.O. Box 13185 1684 Maraj Ave. Azadi Sq. Tehran IRAN.
Nazarian, M. (2001). Determination of the biennial variation of sea level levels using two satellite and satellite telescopes in the Oman Sea area - Chabahar Port, Published at the Eleventh Iranian Geophysical Conference, Tehran (In Persian).
Noahegar, A.; Hosseinzadeh, M. and Heidarzadeh, M. (2010). Impact of local climatic factors on short-term fluctuations of the equilibrium. Case study: North Coast of Strait of Hormoz-Bandar Abbas, Clinical Research Journal, 1(1-2): 77-88 (In Persian).
Noahegar, A. and Yamani, M. (2010). Geomorphology of the East Coast of Hormoz Strait with Emphasis on Wind Erosion, Hormozgan University Press, Hormozgan (In Persian).
Nohegar, A. and Hosseinzadeh, M.M. (2011). Sea Dynamics and the Factors Affecting Sea Level Fluctuations the Evolution of the Deltas Base in Northern Strait of Hormuz, Journal of Geography and Environmental Planning, 43(3): 125-142 (In Persian).
Quinlan, J.R. (1992). Learning with continuous classes, In: Proc.AI 92 (Fifth Australian Joint Conf. onArtifical Intelligence) (ed. By A.Adams & L. Sterling), pp. 343-348.
RahnamaRad, G. and Sahebzadeh, B. (2010). Geology and geomorphology of south east Iran for field visits, First edition, Islamic Azad University, Zahedan, Zahedan (In Persian).
Rezaei, A. (2008). Study of sea level fluctuation fluctuations using satellite and tidal data in the northern coasts of the Oman Sea (Chabahar and Jask), Master's thesis, Professor Dr. Kamran Lari, PhD in the field of marine physics, Islamic Azad University, North Tehran Branch (In Persian).
Safargholi, A.; Mohammadi, A.; Najartbar, M.; Haj Mohammadi, A. and Sayed Karimi, M. (2015). Marine Statistics of Iran, Second Edition, Publication of Chief of Technology Development and Marine Knowledge Industry, Tehran (In Persian).
Safari, M. (2005). Oman Sea Surface Surface Using Satellite Surface Altitude, Master's Thesis, Isfahan University (In Persian).
Srivastava, K.P. (2016). Forecasting Arabian Sea level rise using exponential smoothing state space models and ARIMA from TOPEX and Jason satellite radar altimeter data, Meteorological Applications Meteorol, 23: 633-639.
Sultan, S.A.R.; Ahmad, F.; Elghribi, N.M. and  Al subhi, A.M. (1995). An analysis of Persian Gulf monthly mean sea level, Continental Shelf Research, 15(11/12): 1471-1482.
Torabi Azad, M. and Honarmand, M. (2015). Investigation of sea level changes due to meteorological parameters using statistical models in the north coast of Persian Gulf, Journal of Marine Science and Technology, 11(1): 53-65 (In Persian).
Wang, Y. and Witten, I.H. (1997). Inducing model trees for continuous classes, In V. Someren, Maarten, & G. Widmer(Eds.), Poster Papers: 9th European Conference on Machine Learning, pp. 128-137.
Wunsch, C.; Hansen, D.V. and Zetler, B.D. (1969). Fluctuations of the Florida Current inferred from sea level records, Deep-Sea Research, 16: 447-470.
www.inio.ac.ir
Yamani, M. (1999). The effect of Oman Sea water motions on the formation and development of tidal wetlands, Journal of Geographical Research, 37: 19-34 (In Persian).
Yamani, M. and MohammadNejad, V. (2013). Coastal Geomorphology, Second Edition, Tehran University Press, Tehran (In Persian).