نشریه محیط زیست طبیعی

ارزیابی روش‌های یادگیری ماشین در پیش‌بینی نوسانات تراز سطح آب سواحل جنوبی دریای خزر با استفاده از ماهوارة GRACE و GRACE-FO

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه علوم و مهندسی آب، دانشکدة کشاورزی، دانشگاه بیرجند، بیرجند، ایران.

2 گروه مهندسی آب و سازه‌های هیدرولیکی، دانشکدة کشاورزی، دانشکده‌ مهندسی عمران، دانشگاه تهران، تهران، ایران.

10.22059/jne.2024.379065.2691

چکیده

نوسانات تراز آب دریا تأثیرات مخربی بر شهرهای ساحلی و محیط‌زیست و اقلیم آنها دارد. بنابراین شناسایی تغییرات و نوسانات تراز سطح آب‌ها دریا و پیش‌بینی آن می‌تواند به تصمیم‌گیری‌ها و مدیریت صحیح رخدادها و مشکلات ناشی از آن کمک کند. در این‌ مطالعه به‌ مدل‌سازی سری زمانی تراز سطح آب سواحل جنوبی دریای خزر با استفاده از داده‌های ماهوارة  GRACEو GRACE-FO بکارگیری مدل‌های مبتنی بر یادگیری ماشین نظیر درخت تصمیم (DT)، جنگل تصادفی (RF) و رگرسیون تطبیقی چند متغیرة اسپلاین (MARS) پرداخته ‌شده است. بدین‌‌منظور از داده‌های ماهوارة GRACE و GRACE-FO طی‌ سال‌های 2003 تا 2023 استفاده شد. نتایج‌ به‌دست‌آمده از سری زمانی به‌دست‌آمده از سنجش‌ازدور در مقایسه با داده‌های ایستگاه نوسان‌سنجی بندر انزلی مورد همبستگی قرار گرفتند و در ادامه‌ با استفاده از مدل‌های یادگیری ماشین، تراز سطح آب مورد شبیه‌سازی و پیش‌بینی قرار گرفت. نتایج نشان داد که مدل JPL با 0/788 = R2بیانگر ارتباط مناسب داده‌های ماهواره‌ای با داده‌های زمینی است. همچنین مقادیر R2 سه مدل DT، MARS وRF  به‌ترتیب 0/545، 0/853 و 0/671 و NSE  به‌ترتیب 0/64، 0/89 و 0/76 به‌دست‌ آمد که نشان‌دهندة عملکرد مناسب‌ مدل MARS نسبت به سایرین در شبیه‌سازی است. ازاین‌رو در پیش‌بینی تراز سطح آب تا سال 2040 از این مدل استفاده شد که معیارهای ارزیابی آن حاکی از که‌ کارایی‌ بالای مدل MARS است. پیش‌بینی‌ها نشان داد که در سال 2040 در بدترین شرایط تراز سطح آب دریا تا 120 سانتی‌متر کاهش خواهد یافت که این اتفاق منجر به خسارات محیط‌زیستی و خسارت به صنایع دریایی و بنادر شهرهای ساحلی خواهد شد. نتایج این مطالعه می‌تواند به‌عنوان ابزاری کارآمد در مدیریت منابع آب و برنامه‌ریزی‌های بلندمدت در مناطق ساحلی دریای خزر مورد استفاده قرار گیرد. همچنین، این یافته‌ها می‌تواند در ارزیابی ریسک‌های محیط‌زیستی و اقتصادی ناشی از تغییرات سطح آب دریا و اتخاذ استراتژی‌های مناسب کمک شایانی نماید.

کلیدواژه‌ها

عنوان مقاله [English]

Evaluation of machine learning methods for predicting water level fluctuations in the southern coasts of the Caspian Sea using GRACE and GRACE-FO satellites

نویسندگان [English]

  • Mobin Eftekhari 1
  • Mehdi Dastorani 1
  • Ali Haji Elyasi 2

1 Department of Water Engineering, Faculty of Agriculture, University of Birjand, Birjand, Iran.

2 School of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran.

چکیده [English]

Sea level fluctuations have destructive effects on coastal cities, their environment, and climate. Therefore, identifying changes and fluctuations in sea levels and predicting them can aid in decision-making and proper management of resulting events and problems. This study focuses on modeling the time series of water level in the southern coasts of the Caspian Sea using GRACE and GRACE-FO satellite data, employing machine learning-based models such as Decision Tree (DT), Random Forest (RF), and Multivariate Adaptive Regression Splines (MARS). For this purpose, GRACE and GRACE-FO satellite data from 2003 to 2023 were used. The results obtained from the remote sensing time series were correlated with data from the Anzali Port tide gauge station. Subsequently, water levels were simulated and predicted using machine learning models. Results showed that the JPL model with R2= 0.788 indicates an appropriate relationship between satellite data and ground data. Additionally, R2 values for the three models DT, MARS, and RF were 0.545, 0.853, and 0.671, respectively, and NSE values were 0.64, 0.89, and 0.76 respectively, demonstrating the superior performance of the MARS model in simulation compared to others. Therefore, this model was used to predict water levels up to 2040, with evaluation criteria indicating the high efficiency of the MARS model. Predictions showed that in the worst-case scenario, sea level will decrease by 120 centimeters by 2040, leading to environmental damage and harm to marine industries and ports in coastal cities. The results of this study can be used as an effective tool in water resource management and long-term planning in the Caspian Sea coastal areas. Furthermore, these findings can greatly assist in assessing environmental and economic risks resulting from sea level changes and adopting appropriate strategies.

کلیدواژه‌ها [English]

  • Caspian Sea
  • Gravimetry satellite
  • Machine learning
  • Multivariate adaptive Prediction
  • Regression splines
Alizadeh Katk Lahijani, H., 2003. Impact of Caspian Sea Water Level Fluctuation on Coastal Ecosystems [Specialized Roundtable Report]. Faculty of Natural Resources and Marine Science, Tarbiat Modares University, Iran. 156 p. (In Persian)
Ardalan, A.A., Jafari, A., 2006. Assessment of 13 years of sea level variations at the Caspian Sea using satellite altimetry observations. Journal of the Earth & Space Physics 33(2), 20-31.
Babagholi Mat Kelaei, J., 2018. Study and prediction of Caspian surface fluctuations. In 12th International Energy Conference. National Energy Committee of the Islamic Republic of Iran, University of Tehran, Iran. (In Persian)
Bani Hashemi, S.M., Khoroshan, H., Rohani Zadeh, S., 2012. Investigation of changes in the southern coast of the Caspian Sea due to sea level fluctuations and human factors using remote sensing data. In Third International Conference on Tree Climate and Anthropology in Natural Ecosystems, Sari, Iran. (In Persian)
Banihashemi, S.M., Hosseini, S.A., 2018. Evaluation of the effect of climate change on Caspian Sea level fluctuations. In 5th National Conference on Climate Change and Tree Chronology in Caspian Ecosystems. Research Institute of Caspian Ecosystems of Sari University of Agricultural Sciences and Natural Resources, Iran. (In Persian)
Barros, R.C., Basgalupp, M.P., De Carvalho, A.C., Freitas, A.A., 2011. A survey of evolutionary algorithms for decision-tree induction. IEEE Transactions on Systems, Man, and Cybernetics, Part C (Applications and Reviews) 42(3), 291-312.
Charbuty, B., Abdulazeez, A., 2021. Classification based on decision tree algorithm for machine learning. Journal of Applied Science and Technology Trends 2(01), 20-28.
Chen, J.L., Pekker, T., Wilson, C.R., Tapley, B.D., Kostianoy, A.G., Cretaux, J.F., Safarov, E.S., 2017. Long‐term Caspian Sea level change. Geophysical Research Letters 44(14), 6993-7001.
Dehbashi, M., Azarmsa, S.A., Vafakhah, M., 2017. Analysis and prediction of Caspian Sea level fluctuations using time series stochastic models. Journal of Marine Engineering 25, 23-33. (In Persian)
Eeslami, Z., Ghanghermeh, A., 2022. Forecast of water levels in the Caspian Sea based on the sixth IPCC report. Physical Geography Research 54(2), 257-272. (In Persian)
Eslaminezhad, S. A., Eftekhari, M., Azma, A., Kiyanfar, R., Akbari, M., 2022. Assessment of flood susceptibility prediction based on optimized tree-based machine learning models. Journal of Water and Climate Change 13(6), 2353-2385.
Friedman, J.H., 1991. Multivariate adaptive regression splines. The Annals of Statistics 19(1), 1-67.
Genuer, R., Poggi, J.M., 2020. Random forests. In Random Forests (pp. 33-55). Springer International Publishing.
Ghanghermeh, A., Malek, J., 2005. Peaceful Coexistence with Caspian Sea Fluctuations for Sustainable Development of Iranian Shores (Case Study: South East Coast). Physical Geography Research 54, 1-11. (In Persian)
Hilario, M., Kalousis, A., Pellegrini, C., Müller, M., 2006. Processing and classification of protein mass spectra. Mass Spectrometry Reviews 25(3), 409-449.
Honarbakhsh, A., Azma, A., Nikseresht, F., Mousazadeh, M., Eftekhari, M., Ostovari, Y., 2019. Hydro-chemical assessment and GIS-mapping of groundwater quality parameters in semi-arid regions. Journal of Water Supply: Research and Technology—Aqua 68(7), 509-522.
Hoseini, S. M., Soltanpour, M., 2020. Long-term prediction of Caspian Sea level under CMIP6 scenarios using artificial neural networks. Coastal Engineering Proceedings (36v), 5-5.
Knoben, W.J., Freer, J.E., Woods, R.A., 2019. Inherent benchmark or not? Comparing Nash–Sutcliffe and Kling–Gupta efficiency scores. Hydrology and Earth System Sciences 23(10), 4323-4331.
Koriche, S.A., Singarayer, J.S., Cloke, H.L., 2021. The fate of the Caspian Sea under projected climate change and water extraction during the 21st century. Environmental Research Letters 16(9), 094024.
Kosarev, A.N., Kostianoy, A.G., Zonn, I.S., 2009. Kara-Bogaz-Gol Bay: Physical and Chemical Evolution. Aquatic Geochemistry 15(1), 223-236.
Kuhn, M., Johnson, K., 2013. Applied predictive modeling. Springer.
Lebedev, S.A., Kostianoy, A.G., 2008. Integrated Use of Satellite Altimetry in the Investigation of the Meteorological, Hydrological, and Hydrodynamic Regime of the Caspian Sea. Terrestrial, Atmospheric and Oceanic Sciences 19, 71-82.
Louppe, G., 2014. Understanding random forests: From theory to practice. arXiv preprint arXiv:1407.7502.
Matin, S. S., Farahzadi, L., Makaremi, S., Chelgani, S. C., & Sattari, G. H., 2018. Variable selection and prediction of uniaxial compressive strength and modulus of elasticity by random forest. Applied Soft Computing 70, 980-987.
Milborrow, S., 2016. Multiview active shape models with SIFT descriptors.
Moriasi, D. N., Gitau, M. W., Pai, N., Daggupati, P., 2015. Hydrologic and Water Quality Models: Performance Measures and Evaluation Criteria. Transactions of the ASABE 58(6), 1763–1785.
Patel, H.H., Prajapati, P., 2018. Study and analysis of decision tree-based classification algorithms. International Journal of Computer Sciences and Engineering 6(10), 74-78.
Poursharif, H., 2006. Determination of sea-level topography in the Persian Gulf and Oman Sea by integrating altimetric data using ERS and T / P altimetric models [Master's thesis]. K.N. Toosi University of Technology, Iran. (In Persian)
Rai, K., Devi, M.S., Guleria, A., 2016. Decision tree-based algorithm for intrusion detection. International Journal of Advanced Networking and Applications 7(4), 2828.
Salehpour, J., Khaledian, M.R., Ashrafzadeh, A., 2017. Simulation of Caspian Sea Water Level Fluctuations Using Diagen Planning, Bayesian Decision Network and Artificial Neural Network. In Second National Conference on Soft Computing. University of Guilan, Iran. (In Persian)
Shouval, R., Bondi, O., Mishan, H., Shimoni, A., Unger, R., Nagler, A., 2014. Application of machine learning algorithms for clinical predictive modeling: a data-mining approach in SCT. Bone Marrow Transplantation 49(3), 332-337.
Tapley, B.D., Bettadpur, S., Watkins, M., Reigber, C., 2004. The gravity recovery and climate experiment: Mission overview and early results. Geophysical Research Letters 31(9).
Wahr, J., Molenaar, M., Bryan, F., 1998. Time variability of the Earth's gravity field: Hydrological and oceanic effects and their possible detection using GRACE. Journal of Geophysical Research: Solid Earth 103(B12), 30205-30229.
Wang, J., Lu, S., Wang, S.H., Zhang, Y.D., 2022. A review on extreme learning machine. Multimedia Tools and Applications 81(29), 41611-41660.
Yosefi Roshan, M., 2013. Fluctuation of Caspian Sea Water Level and Functionality (Shoreline, Babolsar County Area). Researches in Earth Sciences 4, 1-16. (In Persian)
Zhu, F., Tang, M., Xie, L., Zhu, H., 2018. A classification algorithm of CART decision tree based on MapReduce attribute weights. International Journal of Performability Engineering 14(1), 17.
Ziegler, A., König, I.R., 2014. Mining data with random forests: current options for real‐world applications. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery 4(1), 55-63.
نشریه محیط زیست طبیعی
دوره 77، شماره 3
آذر 1403
صفحه 453-466