نشریه علمی پژوهشی مهندسی آبیاری و آب ایران

نشریه علمی پژوهشی مهندسی آبیاری و آب ایران

کاربرد الگوریتم های یادگیری ماشین در پیش‌بینی مساحت آبی خلیج گرگان با بهره‌گیری از داده‌های هیدرولوژیکی و اقلیمی

نوع مقاله : مقاله پژوهشی

نویسندگان
1 دکتری هواشناسی کشاورزی، گروه مهندسی آب، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ساری، ایران
2 دانشیارگروه مهندسی آب دانشگاه علوم کشاورزی و منابع طبیعی ساری
10.22125/iwe.2025.495508.1844
چکیده
این مطالعه به پیش‌بینی تغییرات مساحت آبی خلیج گرگان با استفاده از داده‌های هیدرولوژیکی، ماهواره‌ای و اقلیمی شامل دما، بارش، دبی، تراز آب و مساحت آبی (MNDWI) دریای خزر در بازه زمانی 2000 تا 2023 پرداخت. به‌منظور مدل‌سازی این تغییرات، روش‌های پیشرفته یادگیری ماشین شامل XGBoost، شبکه عصبی RBFN، جنگل تصادفی و رگرسیون خطی استفاده شد. ارزیابی روابط میان متغیرها با استفاده از ضریب همبستگی و تحلیل رگرسیونی خطی انجام شد. شاخص‌های ارزیابی مدل شامل RMSE، MAE، MAPE، MBE و R² بوده و پنج سال به طور تصادفی داده‌های واقعی با داده‌های پیش‌بینی مقایسه شد. بر اساس نتایج، تغییرات تراز آبی دریای خزر بیشترین همبستگی را با مساحت آبی خلیج گرگان داشت (ضریب همبستگی 90/0 و معنی داری 001/0). ارتباط مساحت دریای خزر با خشک شدن خلیج گرگان ضریب همبستگی 66/0 و ضریب تعیین 43/0، و دبی ورودی با ضریب پیرسون 63/0 و ضریب تعیین 40/0 بود. بارش و دما با ضریب همبستگی 43/0 و 34/0- کمترین تأثیر را داشته است. نتایج ارزیابی مدل‌ها نشان داد که مدل XGBoost با ضریب تعیین 93/0 و خطای میانگین درصدی مطلق 9/4%، ریشه میانگین مربعات خطا 9/16 و میانگین مطلق خطا 3/15 بهترین عملکرد را داشت. در نهایت، پنج سال به‌طور تصادفی از جمله سال‌های 2000، 2008، 2011، 2016 و 2018 برای پیش‌بینی مساحت آبی خلیج گرگان توسط مدل انتخاب شد. نتایج نشان داد که تمامی مدل‌ها توانستند نوسانات داده‌ها را به طور مناسب شبیه‌سازی کنند، اما مدل XGBoost بهترین عملکرد را داشت.
کلیدواژه‌ها
موضوعات

عنوان مقاله English

Application of Machine Learning Algorithms in Predicting the Water Area of Gorgan Bay Using Hydrological and Climatic Data

نویسندگان English

Alireza Yousefi Kebriya 1
Mehdi Nadi 2
1 Ph.D. of Agricultural Meteorology, Department of Water Engineering. Sari Agricultural Sciences and Natural Resources University, Sari, Iran.
2 Associate Professor of Water engineering Department, Sari Agricultural Sciences and Natural Resources, Sari, Iran.
چکیده English

This study aimed to predict changes in the water area of Gorgan Bay using hydrological, satellite, and climatic data, including temperature, precipitation, discharge, water level, and the water area (MNDWI) of the Caspian Sea from 2000 to 2023. Advanced machine learning methods, including XGBoost, Radial Basis Function Networks (RBFN), Random Forest, and Linear Regression, were employed to model these changes. The relationships among the variables were assessed using correlation coefficients and linear regression analysis. Model evaluation metrics included RMSE, MAE, MAPE, MBE, and R², and actual data from five randomly selected years were compared with predicted values. The results revealed that changes in the water level of the Caspian Sea exhibited the highest correlation with the water area of Gorgan Bay (correlation coefficient 0.90 and significance level 0.001). Precipitation and temperature had the least impact, with correlation coefficients of 0.43 for precipitation and -0.34 for temperature. Evaluation of the predictive models showed that the XGBoost model had the best performance, with an R² of 0.93 and a mean absolute percentage error (MAPE) of 4.9%, root mean square error (RMSE) of 16.9, and mean absolute error (MAE) of 15.3. Finally, five years, including 2000, 2008, 2011, 2016, and 2018, were randomly selected to predict the water area of Gorgan Bay. The results indicated that all models adequately simulated data fluctuations, but the XGBoost model performed the best, accurately predicting severe fluctuations in the water area.

کلیدواژه‌ها English

Caspian Sea Water Level
Remote Sensing
Machine Learning
Statistical Modeling
and Water Surface Area Changes
 
Al-Selwi, S.M., M.F. Hassan, S.J. Abdulkadir, A. Muneer, E.H. Sumiea, A. Alqushaibi and M.G. Ragab. 2024. RNN-LSTM: From applications to modeling techniques and beyond—Systematic review. Journal of King Saud University - Computer and Information Sciences, 36(5): 102068. https://doi.org/10.1016/j.jksuci.2024.102068
Aslam, R.W., H. Shu, I. Naz, A. Quddoos, A. Yaseen, K. Gulshad and S.S. Alarifi. 2024. Machine learning-based wetland vulnerability assessment in the Sindh Province Ramsar site using remote sensing data. Remote Sensing, 16(5): 928. https://doi.org/10.3390/rs16050928
Cui, Q., M.E. Ammar, M. Iravani, J. Kariyeva and M. Faramarzi. 2021. Regional wetland water storage changes: The influence of future climate on geographically isolated wetlands. Ecological Indicators, 120: 106941. https://doi.org/10.1016/j.ecolind.2020.106941
Esri. 2018. Sentinel-2, 10m Multispectral, Multitemporal, 13-band images with visual renderings and indices. ArcGIS. https://www.arcgis.com/home/item.html?id=fd61b9e0c69c4e14bebd50a9a968348c
Ganaie, M.A., M. Hu, A.K. Malik, M. Tanveer and P.N. Suganthan. 2022. Ensemble deep learning: A review. Engineering Applications of Artificial Intelligence, 115: 105151. https://doi.org/10.1016/j.engappai.2022.105151
Gautama, V., G. Gaurava, P. Murugana and M. Annadurai. 2015. Assessment of surface water dynamics in Bangalore using WRI, NDWI, MNDWI, supervised classification and K-T transformation. International Conference on Water Resources, Coastal and Ocean Engineering, 4: 739–746. DOI: 10.1016/j.aqpro.2015.02.095
Gholizadeh, S., R. Dezvareh and A. Kiani. 2024. Long-term monitoring of changes in the waterbody of Gorgan Bay using the combined method of remote sensing indicators and numerical modeling. Amphibious Science and Technology, 5(1): 59–75. https://doi.org/10.22034/JAMST.2024.544346.1133
Jayathilake, T., M.B. Gunathilake, E.M. Wimalasiri and U. Rathnayake. 2023. Wetland water-level prediction in the context of machine-learning techniques: Where do we stand? Environments, 10(5): 75. https://doi.org/10.3390/environments10050075
Kazempour, Z., M. Danesh-Yazdi, K. Asadifakhr and M. Raie. 2023. Spatiotemporal dynamics of chlorophyll-a in the Gorgan Bay and Miankaleh Peninsula biosphere reserve: Call for action. Remote Sensing Applications: Society and Environment, 30: 100946. https://doi.org/10.1016/j.rsase.2023.100946
Li, L., M. Herrera, A. Mukherjee, G. Zheng, C. Chen, M. Dhada, H. Brice, A. Parekh and A.K. Parlikad. 2025. Predictive alarm models for improving radio access network robustness. Expert Systems with Applications, 259: 125312. https://doi.org/10.1016/j.eswa.2024.125312
Li, S., F. Chen, K. Song, G. Liu, H. Tao, S. Xu, X. Wang, Q. Wang and G. Mu. 2022. Mapping the trophic state index of eastern lakes in China using an empirical model and Sentinel-2 imagery data. Journal of Hydrology, 608: 127613. https://doi.org/10.1016/j.jhydrol.2022.127613 
Lorente, A., T. Borsdorff, A. Butz, O. Hasekamp, J. aan de Brugh, A. Schneider, L. Wu, F. Hase, R. Kivi, D. Wunch, D.F. Pollard, K. Shiomi, N.M. Deutscher, V.A. Velazco, C.M. Roehl, P.O. Wennberg, T. Warneke and J. Landgraf. 2021. Methane retrieved from TROPOMI: Improvement of the data product and validation of the first 2 years of measurements. Atmospheric Measurement Techniques, 14: 665–684. https://doi.org/10.5194/amt-14-665-2021 
Luymes, N. and P. Chow-Fraser. 2021. Detection of potential vernal pools on the Canadian Shield (Ontario) using object-based image analysis in combination with machine learning. Canadian Journal of Remote Sensing, 47(4): 519-534. https://doi.org/10.1080/07038992.2021.1900717 
Nadi, M. and A. Yousefi Kebriya. 2024. A Method for Correction of Tropical Rainfall Measuring Mission Satellite Temperature Network in Mazandaran Province. Iranica Journal of Energy and Environment (IJEE), 15(1): 100-110. https://doi.org/10.5829/ijee.2024.15.01.10 
Nadi, M. and A. Yousefi Kebriya. 2024. Evaluation and modification of TRMM temperature and precipitation products in Mazandaran. Journal of Climate Research, 1402(55): 147-160. DOI:10.21203/rs.3.rs-1521038/v1 
NOAA (National Oceanic and Atmospheric Administration). 2020. NOAA ESRL global monitoring laboratory: SURFRAD aerosol optical depth. https://gml.noaa.gov/grad/surfrad/aod/, accessed in 2020. 
Ouma, Y.O., D.B. Moalafhi, G. Anderson, B. Nkwae, P. Odirile, B.P. Parida and J. Qi. 2022. Dam water level prediction using vector autoregression, random forest regression, and MLP-ANN models based on land-use and climate factors. Sustainability, 14(22): 14934. https://doi.org/10.3390/su142214934 
Pirali Zafraei, A.R., S.A. Hedayati, S. Pourmanafi, O. Bireghdar Keshkuli and R. Ghorbani. 2020. Investigation of the efficiency of support vector machine in predicting changes in water quality parameters (Case study: Choghakhor International Wetland). Journal of Aquatic Ecology, 10(1): 23-34. https://doi.org/10.1001.1.23222751.1399.10.1.3.9 
Rane, N.L., M. Paramesha, S.P. Choudhary and J. Rane. 2024. Artificial intelligence, machine learning, and deep learning for advanced business strategies: A review. Partners Universal International Innovation Journal (PUIIJ), 02(03): 147-171. https://doi.org/10.5281/zenodo.12208298 
Ranjbar, M.H., M. Jandaghi Alaee and M. Nazarali. 2019. A modeling study of the impact of increasing water exchange rate on water quality of a semi-enclosed bay. Ecological Engineering, 136: 177-184. https://doi.org/10.1016/j.ecoleng.2019.05.024 
Rezaei, R., A. Jafarian, F. Mattern, U.K. Shukla, V. Senapathi and M. Bernecker. 2019. The sedimentology and development of a modern sandspit (Miankaleh Peninsula) and a lacustrine lagoon (Gorgan Bay), Caspian Sea, Iran. Marine Geology, 415: 105974. https://doi.org/10.1016/j.margeo.2019.105974 
Riley, J.W. and C.C. Stillwell. 2023. Predicting inundation dynamics and hydroperiods of small, isolated wetlands using a machine learning approach. Wetlands, 43: 63. https://doi.org/10.1007/s13157-023-01706-2 
Roodbari Shahmiri, S., M. Adjami and H. Khoshravan. 2017. Prediction of Gorgan Bay Inlet Performance and Morphological Stability. Uqyānūs/Shināsī, 8(31): 53–65. https://doi.org/10.29252/joc.8.31.53 
Salamat, A., M. Ardestani and B. Malekmohammadi. 2023. Modeling groundwater potential using machine learning models. Watershed Management Research, 36(4): 114-132. https://doi.org/10.22092/wmrj.2023.360675.1506 
Sharbaty, S. 2020. Investigating the rivers’ role in the Gorgan Bay possible future after separation from the Caspian Sea. Environmental Researches, 12(23): 117-125. https://doi.org/20.1001.1.20089597.1400.12.23.10.0 
Siadatmousavi, S.M. and A. Eftekhari. 2024. 3D Hydrodynamic Numerical Modeling of Gorgan Bay. International Journal of Coastal, Offshore and Environmental Engineering (IJCOE). doi: 10.22034/ijcoe.2024.357431.1008 
Stein, E.D., E.M. Gee, J.B. Adams, K. Irving and L. Van Niekerk. 2021. Advancing the science of environmental flow management for protection of temporarily closed estuaries and coastal lagoons. Water, 13(5): 595. https://doi.org/10.3390/w13050595 
Torahi, A., M. FiroziNejad and A. Abdolkhani. 2017. Assessment of SVM and MLC algorithms on land use/land cover mapping of riparian forest using OLI sensor (Case study: Riparian Forest of Maroon, Behbahan). Iranian Journal of Remote Sensing and GIS, 9(1): 49-62. https://gisj.sbu.ac.ir/article_96239.html?lang=fa 
Yousefi Kebria, A., M. Nadi and M. Jamei. 2021. Investigation of Statistical and Geostatistical Methods in Preparing the Rainfall Map of Mazandaran Province. Journal of Watershed Management Research, 12(23): 212-223. doi: 10.52547/jwmr.12.23.212 
Yousefi Kebriya, A., M. Nadi and M. Jamei. 2022. Combining interpolation methods and precipitation products of TRMM satellite to increase the accuracy of rainfall maps in Mazandaran province. Water and Soil Conservation, 28(3): 49-70. doi: 10.22069/JWSC.2022.19286.3477 
Yousefi Kebriya, A., M. Nadi, E. Ghanbariparmehr and S. Zhongchang. 2024. Modeling and Forecasting Dust Pollution Using Satellite Data and Machine Learning Techniques: A Case Study of Ahvaz. Journal of Agricultural Meteorology. doi: 10.22125/agmj.2024.478677.1174 
Zakaria, M.N.A., A.N. Ahmed, M.A. Malek, A.H. Birima, M.M.H. Khan, M. Sherif and A. Elshafie. 2023. Exploring machine learning algorithms for accurate water level forecasting in Muda River, Malaysia. Heliyon, 9(7): e17689. https://doi.org/10.1016/j.heliyon.2023.e17689 
Zheng, L., H. Wang, C. Liu, S. Zhang, A. Ding, E. Xie, J. Li and S. Wang. 2021. Prediction of harmful algal blooms in large water bodies using the combined EFDC and LSTM models. Journal of Environmental Management, 295: 113060. https://doi.org/10.1016/j.jenvman.2021.113060