پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 158 |
| تعداد شماره‌ها | 6,232 |
| تعداد مقالات | 67,797 |
| تعداد مشاهده مقاله | 115,275,274 |
| تعداد دریافت فایل اصل مقاله | 90,020,502 |
تحلیل حساسیت کانون‌های مخاطره‌آمیز مستعد گردوغبار در دوره‌های مرطوب و خشک حوضه دجله و فرات: الگوریتم فرا ابتکاری و یادگیری ماشین | ||
| مدیریت مخاطرات محیطی | ||
| دوره 10، شماره 4، دی 1402، صفحه 355-370 اصل مقاله (1.17 M) | ||
| نوع مقاله: پژوهشی کاربردی | ||
| شناسه دیجیتال (DOI): 10.22059/jhsci.2024.373445.821 | ||
| نویسندگان | ||
| ازهر ابراهیم الطائی1؛ علی اصغر آل شیخ* 2؛ علی درویشی بلورانی3 | ||
| 1گروه مهندسی GIS، دانشگاه صنعتی خواجه نصیرالدین طوسی | ||
| 2گروه GIS ، دانشکده مهندسی نقشه برداری، دانشگاه صنعتی خواجه نصیرالدین طوسی، تهران، ایران | ||
| 3گروه سنجش‌ازدور و GIS، دانشکده جغرافیا، دانشگاه تهران | ||
| چکیده | ||
| طوفان‌های گردوغبار یکی از شدیدترین نوع آلودگی هوا هستند و تهدیدات جدی را برای سلامت، محیط‌زیست و انسان به همراه دارند. برای مقابله با این پدیده، درک مکانیسم‌های تولید گردوغبار بسیار حیاتی است. این امر با استفاده از یادگیری ماشین در تحلیل حساسیت کانون‌های گردوغبار و تعیین سطح مخاطره‌آمیز بودن آن‌ها به دست می‌آید. اگرچه فعالیت‌های گردوغبار ارتباط بسیار بالایی با تغییر مداوم مکانی و زمانی پارامترهای جوی و محیطی دارد، بااین‌حال مطالعات معدودی به تحلیل حساسیت کانون‌های گردوغبار با در نظر گرفتن نوسانات اقلیمی مانند دوره‌های مرطوب و خشک پرداخته‌اند. همچنین، درحالی‌که بهینه‌سازی فرا ابتکاری پارامترها برای بهبود عملکرد یادگیری ماشین بسیار مهم است، بسیاری از مطالعات از آن صرف‌نظر کرده‌اند. برای پر کردن خلاءهای پژوهشی مرتبط با این موضوع، هدف از این مطالعه ارائه یک چارچوب برای تحلیل حساسیت کانون‌های مخاطره‌آمیز مستعد گردوغبار در دوره‌های خشک و مرطوب (بر اساس تغییرات بدنه‌های آبی) با استفاده از یک مدل جنگل تصادفی (RF) بهبود یافته با بهینه‌سازی مبتنی بر آموزش و یادگیری (TLBO) و بهینه‌سازی مبتنی بر روانشناسی دانش‌آموز (SPBO) می‌باشد. برای دستیابی به این هدف، این مطالعه 10392 کانون گردوغبار شناسایی‌شده را همراه با عوامل مؤثر محیطی بین سال‌های 2000 تا 2020 در حوضه مشترک فرامرزی دجله و فرات، که ازجمله مهم‌ترین کانون‌های گردوغبار در خاورمیانه و در سطح جهانی است، تحلیل کرد. نتایج نشان داد که RF-TLBO با متوسط خطای مطلق میانگین (MAE) 0.146، متوسط خطای جذر میانگین مربعات (RMSE) 0.194 و متوسط ضریب ویلموت (WI) 0.761 در مقایسه با متوسط MAE برابر 0.148، متوسط RMSE برابر 0.195 و متوسط WI برابر 0.757 کمی بهتر از RF-SPBO عمل کرد. TLBO تنظیم مدل RF را با تعداد درختان کمتر و نیز حداکثر عمق کمتر و به‌صورت مدلی ساده‌تر انجام داد. بر همین اساس ما از RF-TLBO استفاده کردیم و نواحی کانونی مستعد گردوغبار را در طول دوره‌های خشک با سطح بالاتری از مخاطره‌آمیز بودن نسبت به دوره‌های مرطوب شناسایی کردیم. این مشاهده ارتباط معنی‌داری بین دوره‌های مرطوب و خشک و مستعد بودن برای ایجاد طوفان‌های مخاطره‌آمیز را تأیید می‌کند. سطح بالای مخاطره‌آمیز بودن کانون‌های نزدیک منابع آبی و باتلاق‌ها نشان‌دهنده تأثیر قابل‌توجه تغییرات پهنه‌های آبی بر تولید منابع گردوغبار مخاطره‌آمیز است. نتایج شاخص Gini همچنین نشان می‌دهد که پوشش گیاهی، ارتفاع، سرعت باد و بافت خاک تأثیر بیشتری بر مخاطره‌آمیز بودن کانون‌های مستعد تولید گردوغبار دارند. | ||
| کلیدواژه‌ها | ||
| کانون‌های گردوغبار؛ جنگل تصادفی؛ روش‌های فرا ابتکاری؛ حوضه دجله و فرات؛ دوره‌های مرطوب و خشک | ||
| عنوان مقاله [English] | ||
| Hazardous Dust Source Susceptibility Mapping in Wet and Dry Periods of the Tigris-Euphrates Basin: A Meta-Heuristics and Machine Learning | ||
| نویسندگان [English] | ||
| Azher Ibrahim Al-Taei1؛ Ali Asghar Alesheikh2؛ Ali Darvishi Boloorani3 | ||
| 1PhD Candidate in GIS, Department of GIS, Faculty of Geodesy and Geomatics Engineering, K. N. Toosi University of Technology, Tehran, Iran | ||
| 2Professor in GIS, Center of Excellence for Geospatial Information Technology, Faculty of Geomatics Eng. , K. N. Toosi University of Technology, Tehran, Iran | ||
| 3Associate Professor of Geoinformatics, Department of Remote Sensing and GIS, University of Tehran, Tehran, Iran | ||
| چکیده [English] | ||
| Dust storms are a severe form of air pollution that poses significant threats to the environment and human health. To deal with this phenomenon, it is crucial to comprehend the mechanisms accountable for dust generation. This can be achieved by utilizing machine learning in dust source susceptibility mapping. Although dust activities vary spatiotemporally due to the constantly changing atmosphere, few papers have addressed dust source susceptibility mapping considering Earth system frameworks such as wet and dry periods. Also, while optimizing hyperparameters is crucial for improving machine learning performance, many studies have neglected this aspect in this particular application. To address this research gap, the objective of this study was to create a framework for mapping the susceptibility of hazardous hotspot dust sources (HDS) during wet and dry periods (based on the changes in water bodies) using a fine-tuned random forest model with teaching learning-based optimization (TLBO) and student psychology based optimization (SPBO) optimizers. To achieve this, the study analyzed 10,392 identified HDS, along with various environmental influential factors between 2000 and 2020 in the transnational shared Tigris-Euphrates Basin, which is a significant source of dust in the Middle East and globally. The results showed that RF-TLBO performed slightly better than RF-SPBO, with an average mean absolute error (MAE) of 0.146, average root mean squared error (RMSE) of 0.194, and average Willmott Index (WI) of 0.761, compared to RF-SPBO's average MAE of 0.148, average RMSE of 0.195, and average WI of 0.757. The TLBO tuned RF with a lower number of trees and a lower maximum depth value, making it a simpler model. We utilized RF-TLBO and observed more areas that are more susceptible to hazardous dust sources during dry periods, confirming the meaningful relationship between wet and dry periods and hazardous dust susceptibility. Higher susceptibilities were found near water bodies and marshlands, indicating the significant impact of fluctuating water bodies on the generation of hazardous dust sources. The Gini index results also show that vegetation cover, elevation, wind speed, and soil texture have a high impact on land susceptibility to be a hazardous dust source. | ||
| کلیدواژه‌ها [English] | ||
| Hotspot dust sources, Random forest, Meta-heuristics methods, Tigris-Euphrates Basin, Wet and Dry periods | ||
| مراجع | ||
|
[1] Achakulwisut, P., Anenberg, S. C., Neumann, J. E., et al. Effects of increasing aridity on ambient dust and public health in the US Southwest under climate change. GeoHealth, 3(5), 127-144. (2019)
[2] Aeronautics, N., & Laboratory, S. A. J. P. (2020). Nasadem merged dem global 1 arc second v001 [data set]. NASA EOSDIS Land Processes DAAC.
[3] Al-Abadi, A. M., Al-Temmeme, A. A., & Al-Ghanimy, M. A. (2016). A GIS-based combining of frequency ratio and index of entropy approaches for mapping groundwater availability zones at Badra–Al Al-Gharbi–Teeb areas, Iraq. Sustainable Water Resources Management, 2, 265-283.
[4] Al-Taei, A. I., Alesheikh, A. A., & Darvishi Boloorani, A. (2023). Land Use/Land Cover Change Analysis Using Multi-Temporal Remote Sensing Data: A Case Study of Tigris and Euphrates Rivers Basin. Land, 12(5), 1101.
[5] Al Ameri, I. D., Briant, R. M., & Engels, S. (2019). Drought severity and increased dust storm frequency in the Middle East: a case study from the Tigris–Euphrates alluvial plain, central Iraq. Weather, 74(12), 416-426.
[6] Alsubhi, Y., Qureshi, S., & Siddiqui, M. H. (2023). A New Risk-Based Method in Decision Making to Create Dust Sources Maps: A Case Study of Saudi Arabia. Remote Sensing, 15(21), 5193.
[7] Aniya, M. (1985). Landslide-susceptibility mapping in the Amahata river basin, Japan. Annals of the Association of American Geographers, 75(1), 102-114.
[8] Bank, W. (2019). Sand and Dust Storms in the Middle East and North Africa Region: Sources, Costs, and Solutions: World Bank.
[9] Beyranvand, A., Azizi, G., Alizadeh, O., & Darvishi Boloorani, A. (2023). Dust in Western Iran: the emergence of new sources in response to shrinking water bodies. Scientific reports, 13(1), 16158.
[10] Boloorani, A. D., Ranjbareslamloo, S., Mirzaie, S., Bahrami, H. A., Mirzapour, F., & Tehrani, N. A. (2020). Spectral behavior of Persian oak under compound stress of water deficit and dust storm. International journal of Applied earth Observation and Geoinformation, 88, 102082.
[11] Boloorani, A. D., Samany, N. N., Papi, R., & Soleimani, M. (2022). Dust source susceptibility mapping in Tigris and Euphrates basin using remotely sensed imagery. Catena, 209, 105795.
[12] Boloorani, A. D., Soleimani, M., Papi, R., et al. (2024). Assessing the role of drought in dust storm formation in the Tigris and Euphrates basin. Science of The Total Environment, 171193.
[13] Boroughani, M., Mirchooli, F., Hadavifar, M., & Fiedler, S. (2023). Mapping land degradation risk due to land susceptibility to dust emission and water erosion. Soil, 9(2), 411-423.
[14] Branco, P., Torgo, L., & Ribeiro, R. P. (2017). SMOGN: a pre-processing approach for imbalanced regression. Paper presented at the First international workshop on learning with imbalanced domains: Theory and applications.
[15] Briceño-Zuluaga, F., Castagna, A., Rutllant, J. A., et al. (2017). Paracas dust storms: Sources, trajectories and associated meteorological conditions. Atmospheric Environment, 165, 99-110.
[16] Darvishi Boloorani, A., Kazemi, Y., Sadeghi, A., Shorabeh, S. N., & Argany, M. (2020). Identification of dust sources using long term satellite and climatic data: A case study of Tigris and Euphrates basin. Atmospheric Environment, 224, 117299.
[17] Darvishi Boloorani, A., Papi, R., Soleimani, M., et al. (2023). Visual interpretation of satellite imagery for hotspot dust sources identification. Remote Sensing Applications: Society and Environment, 29, 100888.
[18] Darvishi Boloorani, A., Papi, R., Soleimani, M., Karami, L., Amiri, F., & Samany, N. N. (2021). Water bodies changes in Tigris and Euphrates basin has impacted dust storms phenomena. Aeolian Research, 50, 100698.
[19] Das, B., Mukherjee, V., & Das, D. (2020). Student psychology based optimization algorithm: A new population based optimization algorithm for solving optimization problems. Advances in Engineering software, 146, 102804.
[20] Ding, Q., Liu, X., & Zhang, X. (2014). Impacts of water level fluctuations on substrate environments of lakeshore zone of the lakes in the middle and lower reaches of the Yangtze River. Journal of Lake Science, 26(3), 340-348.
[21] Eleftheriou, A., Mouzourides, P., Biskos, G., Yiallouros, P., Kumar, P., & Neophytou, M. K.-A. (2023). The challenge of adopting mitigation and adaptation measures for the impacts of sand and dust storms in Eastern Mediterranean Region: a critical review. Mitigation and Adaptation Strategies for Global Change, 28(6), 33.
[22] Farhangi, F., Sadegh-Niaraki, A., Razavi-Termeh, S. V., & Nahvi, A. (2023). Driver drowsiness modeling based on spatial factors and electroencephalography using machine learning methods: A simulator study. Transportation Research Part F: Traffic Psychology and Behaviour, 98, 123-140.
[23] Feng, Y., Long, H., Yang, F., Yang, F., Cheng, H., & Zhang, G. (2023). Warmth Favored Dust Activities on the Northeastern Qinghai‐Tibet Plateau. Geophysical research letters, 50(11), e2023GL103781.
[24] Furman, H. K. H. (2003). Dust storms in the Middle East: sources of origin and their temporal characteristics. Indoor and Built Environment, 12(6), 419-426.
[25] Gholami, H., Mohamadifar, A., Sorooshian, A., & Jansen, J. D. (2020). Machine-learning algorithms for predicting land susceptibility to dust emissions: The case of the Jazmurian Basin, Iran. Atmospheric pollution research, 11(8), 1303-1315.
[26] Hamidi, M. (2020). The key role of water resources management in the Middle East dust events. Catena, 187, 104337.
[27] Hengl, T. (2018). Soil texture classes (USDA system) for 6 soil depths (0, 10, 30, 60, 100 and 200 cm) at 250 m (Version v02)[Data set]. Zenodo.
[28] Jafari, R., Amiri, M., Asgari, F., & Tarkesh, M. (2022). Dust source susceptibility mapping based on remote sensing and machine learning techniques. Ecological Informatics, 72, 101872.
[29] Jish Prakash, P., Stenchikov, G., Kalenderski, S., Osipov, S., & Bangalath, H. (2015). The impact of dust storms on the Arabian Peninsula and the Red Sea. Atmospheric Chemistry and Physics, 15(1), 199-222.
[30] Karunasingha, D. S. K. (2022). Root mean square error or mean absolute error? Use their ratio as well. Information Sciences, 585, 609-629.
[31] Khaniabadi, Y. O., Daryanoosh, S. M., Amrane, A., et al. (2017). Impact of Middle Eastern Dust storms on human health. Atmospheric pollution research, 8(4), 606-613.
[32] Li, J., Garshick, E., Huang, S., & Koutrakis, P. (2021). Impacts of El Niño-Southern Oscillation on surface dust levels across the world during 1982–2019. Science of The Total Environment, 769, 144566.
[33] Li, J., Li, C., & Zhang, S. (2022). Application of Six Metaheuristic Optimization Algorithms and Random Forest in the uniaxial compressive strength of rock prediction. Applied Soft Computing, 131, 109729.
[34] Liu, R., Li, G., Wei, L., et al. (2022). Spatial prediction of groundwater potentiality using machine learning methods with Grey Wolf and Sparrow Search Algorithms. Journal of Hydrology, 610, 127977.
[35] Liu, Y., Wang, G., Hu, Z., et al. (2020). Dust storm susceptibility on different land surface types in arid and semiarid regions of northern China. Atmospheric Research, 243, 105031.
[36] McNally, A. (2018). FLDAS Noah Land Surface Model L4 Global Monthly 0.1× 0.1 degree (MERRA-2 and CHIRPS), Greenbelt, MD, USA, Goddard Earth Sciences Data and Information Services Center (GES DISC).
[37] Mengmeng, Z., & Yian, L. (2018). Signal sorting using teaching-learning-based optimization and random forest. Paper presented at the 2018 17th International Symposium on Distributed Computing and Applications for Business Engineering and Science (DCABES).
[38] Moniz, N., Branco, P., & Torgo, L. (2017). Evaluation of ensemble methods in imbalanced regression tasks. Paper presented at the First International Workshop on Learning with Imbalanced Domains: Theory and Applications.
[39] Munkhtsetseg, E., Shinoda, M., Gillies, J. A., Kimura, R., King, J., & Nikolich, G. (2016). Relationships between soil moisture and dust emissions in a bare sandy soil of Mongolia. Particuology, 28, 131-137.
[40] Naghibi, A., Hashemi, H., Zhao, P., et al. (2024). Spatiotemporal variability of dust storm source susceptibility during wet and dry periods: The Tigris-Euphrates River Basin. Atmospheric pollution research, 15(1), 101953.
[41] Neelamani, S., & Al-Dousari, A. (2016). A study on the annual fallout of the dust and the associated elements into the Kuwait Bay, Kuwait. Arabian Journal of Geosciences, 9, 1-11.
[42] Okin, G. S. (2022). Where and how often does rain prevent dust emission? Geophysical research letters, 49(4), e2021GL095501.
[43] Parajuli, S. P., Yang, Z. L., & Kocurek, G. (2014). Mapping erodibility in dust source regions based on geomorphology, meteorology, and remote sensing. Journal of Geophysical Research: Earth Surface, 119(9), 1977-1994.
[44] Park, S., Hamm, S.-Y., Jeon, H.-T., & Kim, J. (2017). Evaluation of logistic regression and multivariate adaptive regression spline models for groundwater potential mapping using R and GIS. Sustainability, 9(7), 1157.
[45] Peng, Y. (2022). Application of Educational Psychology Based on Improved SPBO Optimization Algorithm in English Learning. Frontiers in Psychology, 13, 949568.
[46] Pourhashemi, S., Asadi, M. A. Z., Boroughani, M., & Azadi, H. (2023). Mapping of dust source susceptibility by remote sensing and machine learning techniques (case study: Iran-Iraq border). Environmental Science and Pollution Research, 30(10), 27965-27979.
[47] Rao, R. V., & Patel, V. (2013). An improved teaching-learning-based optimization algorithm for solving unconstrained optimization problems. Scientia Iranica, 20(3), 710-720.
[48] Rao, R. V., Savsani, V. J., & Vakharia, D. (2011). Teaching–learning-based optimization: a novel method for constrained mechanical design optimization problems. Computer-aided design, 43(3), 303-315.
[49] Razavi-Termeh, S. V., Sadeghi-Niaraki, A., & Choi, S.-M. (2019). Groundwater potential mapping using an integrated ensemble of three bivariate statistical models with random forest and logistic model tree models. Water, 11(8), 1596.
[50] Razavi-Termeh, S. V., Sadeghi-Niaraki, A., Seo, M., & Choi, S.-M. (2023). Application of genetic algorithm in optimization parallel ensemble-based machine learning algorithms to flood susceptibility mapping using radar satellite imagery. Science of The Total Environment, 873, 162285.
[51] Sarzaeim, P., Bozorg-Haddad, O., & Chu, X. (2018). Teaching-learning-based optimization (TLBO) algorithm. Advanced optimization by nature-inspired algorithms, 51-58.
[52] Shao, Y. (2008). Physics and modelling of wind erosion: Springer.
[53] Shogrkhodaei, S. Z., Razavi-Termeh, S. V., & Fathnia, A. (2021). Spatio-temporal modeling of PM2. 5 risk mapping using three machine learning algorithms. Environmental Pollution, 289, 117859.
[54] Speer, M. S. (2013). Dust storm frequency and impact over Eastern Australia determined by state of Pacific climate system. Weather and Climate Extremes, 2, 16-21.
[55] Strong, J. D., Vecchi, G. A., & Ginoux, P. (2015). The response of the tropical Atlantic and West African climate to Saharan dust in a fully coupled GCM. Journal of Climate, 28(18), 7071-7092.
[56] UNCCD. (2022). Sand and dust storms compendium: Information and guidance on assessing and addressing the risks: United Nations Convention to Combat Desertification.
[57] Wang, N., Chen, J., Zhang, Y., Xu, Y., & Yu, W. (2023). The Spatiotemporal Characteristics and Driving Factors of Dust Emissions in East Asia (2000–2021). Remote Sensing, 15(2), 410.
[58] Wang, W., Samat, A., Abuduwaili, J., De Maeyer, P., & Van de Voorde, T. (2023). Machine learning-based prediction of sand and dust storm sources in arid Central Asia. International Journal of Digital Earth, 16(1), 1530-1550.
[59] Willmott, C. J., Ackleson, S. G., Davis, R. E., et al. (1985). Statistics for the evaluation and comparison of models. Journal of Geophysical Research: Oceans, 90(C5), 8995-9005.
[60] WMO. (1995). Manual on Codes – International Codes. WMO Report No.306, Geneva, Switzerland.
[61] Wu, C., Lin, Z., Shao, Y., Liu, X., & Li, Y. (2022). Drivers of recent decline in dust activity over East Asia. Nature Communications, 13(1), 7105.
[62] Wu, D., Wang, S., Liu, Q., Abualigah, L., & Jia, H. (2022). An improved teaching-learning-based optimization algorithm with reinforcement learning strategy for solving optimization problems. Computational Intelligence and Neuroscience, 2022.
[63] Xu, C., Guan, Q., Lin, J., et al. (2020). Spatiotemporal variations and driving factors of dust storm events in northern China based on high-temporal-resolution analysis of meteorological data (1960–2007). Environmental Pollution, 260, 114084.
[64] Xue, R., & Wu, Z. (2019). A survey of application and classification on teaching-learning-based optimization algorithm. IEEE Access, 8, 1062-1079.
[65] Yadav, R., & Kaur, M. (2024). Teaching learning based optimization-a review on background and development. AIP Conference Proceedings, 2986(1).
[66] Zhang, J., Huang, Y., Wang, Y., & Ma, G. (2020). Multi-objective optimization of concrete mixture proportions using machine learning and metaheuristic algorithms. Construction and Building Materials, 253, 119208.
[67] Zhao, C., Dabu, X., & Li, Y. (2004). Relationship between climatic factors and dust storm frequency in Inner Mongolia of China. Geophysical research letters, 31(1).
[68] Zucca, C., Middleton, N., Kang, U., & Liniger, H. (2021). Shrinking water bodies as hotspots of sand and dust storms: The role of land degradation and sustainable soil and water management. Catena, 207, 105669.
| ||
|
آمار تعداد مشاهده مقاله: 78 تعداد دریافت فایل اصل مقاله: 228 |
||