تحقیقات کاربردی علوم جغرافیایی

تحقیقات کاربردی علوم جغرافیایی

برآورد مقادیر مفقود شاخص جهانی امنیت آب با بهره‌گیری از الگوریتم‌های یادگیری ماشین و تحلیل عوامل محیطی، مکانی و انسانی

نویسندگان
1 گروه جغرافیا، دانشگاه فردوسی مشهد، مشهد، ایران.
2 گروه پژوهشی امنیت آب، برنامه تنوع زیستی و منابع طبیعی، موسسه بین‌المللی تحلیل سیستم‌های کاربردی یاسا ، اتریش .
3 گروه جغرافیا طبیعی، دانشکده علوم جغرافیایی، دانشگاه خوارزمی، تهران، ایران
چکیده
بحران جهانی آب، با کمبود داده‌های مکانی دقیق در شاخص‌های فشار آبی مانند Baseline Water Stress (BWS)، چالش‌های جدی در سیاست‌گذاری و مدیریت منابع ایجاد کرده است. این پژوهش، با بهره‌گیری از الگوریتم XGBoost – به عنوان یکی از کارآمدترین روش‌های یادگیری ماشین برای مدل‌های رگرسیون – مقادیر گمشده BWS را در مقیاس جهانی تخمین می‌زند. متغیرهای کلیدی شامل رطوبت خاک، عوامل اقلیمی (بارش، دما، تبخیر-تعرق)، کاربری اراضی و ارتفاع، بر اساس داده‌های Aqueduct Water Risk Atlas 4.0 و منابع سنجش از دور انتخاب شده‌اند. مدل، با پیش‌پردازش جامع داده‌ها و تنظیم بهینه پارامترها، حدود ۷۱٪ واریانس داده‌های واقعی را توضیح می دهد(71/0= R2) با خطای متوسط مطلق (72/0= MAE) و ریشه میانگین مربعات خطا (14/1= RMSE) در مقیاس 5-0 که عملکرد رقابتی نسبت به مطالعات پیشین نشان می دهد. تحلیل اهمیت ویژگی‌ها حاکی از برتری رطوبت خاک (35.41٪) به عنوان شاخص یکپارچه هیدرولوژیکی، اقلیم (24.58٪) به عنوان موتور چرخه آب، کاربری اراضی (18.30٪) و جمعیت (16.04٪) به عنوان عوامل انسانی، و ارتفاع (5.67٪) به عنوان متغیر توپوگرافی است. نقشه تکمیل‌شده BWS، الگوهای ناهمگون فشار آبی را برجسته می‌سازد: کانون‌های بحرانی در خاورمیانه، شمال آفریقا و جنوب آسیا، و امنیت بالاتر در مناطق استوایی و معتدل. این مدل، ابزاری عملی برای سیاست‌گذاران در شناسایی مناطق پرریسک، توسعه سیستم‌های هشدار زودهنگام و برنامه‌ریزی پایدار منابع آب ارائه می‌دهد. محدودیت‌های واریانس باقیمانده (۲۹٪) بر لزوم ادغام داده‌های اقتصادی-اجتماعی و کالیبراسیون محلی تأکید دارد و گامی محوری در مقابله با بحران آب جهانی به شمار می‌رود.
کلیدواژه‌ها

عنوان مقاله English

Estimating missing values of the Global Water Security Index using machine learning algorithms and analyzing environmental, spatial, and human factors

نویسندگان English

Masoud Minaei 1
Sylvia Tramberend 2
Mohammad Kamangar 1
Ali Reza Karbalaee 3
Emilio Politti 2
1 Department of Geography, Ferdowsi University of Mashhad, Mashhad, Iran
2 Water Security Research Group, Biodiversity and Natural Resources Program, International Institute for Applied Systems Analysis (IIASA), Schlossplatz 1, A-2361 Laxenburg, Austria
3 Department of Climatology, Faculty of Geographical Sciences, Kharazmi University, Tehran, Iran
چکیده English

“The global water crisis is exacerbated by significant spatial data gaps in key water stress indicators such as Baseline Water Stress (BWS), posing serious challenges for policy-making and water resource management. This study leverages the XGBoost algorithm one of the most efficient machine learning methods for regression modeling to estimate missing BWS values at the global scale. Key predictor variables include soil moisture, climatic factors (precipitation, temperature, and evapotranspiration), land use/land cover, and elevation, derived from the Aqueduct Water Risk Atlas 4.0 and remote sensing datasets. Through comprehensive data preprocessing and hyperparameter optimization, the model explains approximately 71% of the variance in observed BWS values (R² = 0.711), achieving a Mean Absolute Error (MAE) of 0.727 and a Root Mean Square Error (RMSE) of 1.143 on the standardized 0–5 BWS scale—demonstrating competitive performance compared to prior studies (R² range: 0.60–0.75). Feature importance analysis reveals soil moisture as the dominant hydrological integrator (35.41%), followed by climate variables as the primary driver of the hydrological cycle (24.58%), land use/land cover (18.30%) and population density as key anthropogenic factors (16.04%), and elevation as a topographic modulator (5.67%). The reconstructed global BWS map highlights pronounced spatial heterogeneity in water stress: critical hotspots emerge across the Middle East, North Africa, and South Asia, while higher water security is observed in tropical and temperate regions. This model provides a practical tool for policymakers to identify high-risk areas, develop early-warning systems, and support sustainable water planning. The unexplained variance (29%) underscores the need to integrate socioeconomic data and implement local-scale calibration representing a pivotal step toward addressing the global water crisis.

کلیدواژه‌ها English

Water stress
XGBoost
Soil moisture
Climate Change
Water resources management
Remote Sensing
Ahmed U, et al. (2022). "A Machine Learning-Based Water Potability Prediction Model by Using Explainable Artificial Intelligence." Frontiers in Public Health. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9514946/pmc.ncbi.nlm.nih
Alvarez, P. J., Chan, C. K., Elimelech, M., Halas, N. J., & Villagrán, D. (2018). Emerging opportunities for nanotechnology to enhance water security. Nature nanotechnology, 13(8), 634-641.
Arrojo Agudo, P. (2008). La crisis global del agua en el Planeta Agua. 168, 50-52. https://dialnet.unirioja.es/servlet/articulo?codigo=2967011
Asakaa, J. O., Argomedo, D. W., & Jones, N. P. (2024). Climate change risks to water security: Exploring the interplay between climate change, water theft, and water (in)security. Water Policy. https://doi.org/10.2166/wp.2024.213
Boretti, A., & Rosa, L. (2019). Reassessing the projections of the World Water Development Report. NPJ Clean Water, 2(1). https://doi.org/10.1038/s41545-019-0039-9
Chen, T., & Guestrin, C. (2016). XGBoost: A scalable tree boosting system (arXiv preprint arXiv:1603.02754). arXiv. https://doi.org/10.48550/arXiv.1603.02754.
Connor, R. (2015). The United Nations world water development report 2015: water for a sustainable world (Vol. 1). UNESCO publishing.
Damkjaer, S., & Taylor, R. (2017). The measurement of water scarcity: Defining a meaningful indicator. Ambio, 46(5), 513-531. https://doi.org/10.1007/s13280-017-0912-z
Gain, A. K., Giupponi, C., & Wada, Y. (2016). Measuring global water security towards sustainable development goals. Environmental Research Letters, 11(12), 124015.
Gerlak, A. K., House-Peters, L., Varady, R. G., Albrecht, T., Zúñiga-Terán, A., de Grenade, R. R., ... & Scott, C. A. (2018). Water security: A review of place-based research. Environmental science & policy, 82, 79-89.
González-Zeas, D., García-Vila, M., Estrela, T., & Andreu, J. (2019). Impacts of climate change on water stress in Mediterranean River Basins. Hydrology and Earth System Sciences, 23(6), 2615-2635.
Hanif Chen, T., He, T., Benesty, M., Khotilovich, V., Tang, Y., Cho, H., ... & Zhou, T. (2015). XGBoost: Extreme gradient boosting. R package version 0.4-2, 1(4), 1-4.
Howlett, M. P., & Cuenca, J. S. (2017). The use of indicators in environmental policy appraisal: lessons from the design and evolution of water security policy measures. Journal of Environmental Policy & Planning, 19(2), 229-243. https://doi.org/10.1080/1523908X.2016.1207507
https://doi.org/10.1016/j.envsci.2018.01.009
https://doi.org/10.1016/j.scitotenv.2023.161763
https://doi.org/10.1038/s41565-018-0203-2
https://doi.org/10.1088/1748-9326/11/12/124015
Kisi, O., Parmar, K.S., & Karimi, O. (2020). Application of machine learning algorithms in modeling long-term water quality index. Environmental Science and Pollution Research, 27(26), 32619-32629.
Li, N., et al. (2022). "Water ecological security assessment and spatial autocorrelation analysis in the Songhua River Basin: Based on the PSR model." Scientific Reports. https://www.nature.com/articles/s41598-022-07656-9nature
Li, X., Su, X., & Wei, Y. (2019). Multistage integrated water security assessment in a typical region of Northwestern China. Journal of Cleaner Production, 220, 732-744. https://doi.org/10.1016/j.jclepro.2019.02.033
Nie, R. X., Tian, Z. P., Wang, J. Q., Zhang, H. Y., & Wang, T. L. (2018). Water security sustainability evaluation: Applying a multistage decision support framework in industrial region. Journal of cleaner production, 196, 1681-1704. https://doi.org/10.1016/j.jclepro.2018.06.144
Peng, Q., He, W., Kong, Y., Shen, J., Yuan, L., & Ramsey, T. S. (2024). Spatio-temporal analysis of water sustainability of cities in the Yangtze River Economic Belt based on the perspectives of quantity-quality-benefit. Ecological Indicators, 160, 111909. https://doi.org/10.1016/j.ecolind.2024.111909
Racheeti, P. B. (2024). Water crisis escalation: global challenges and urgent imperatives-review. International Journal of Advanced Research, 12(02), 703-710. https://doi.org/10.21474/ijar01/18348
Saberi Kouadri, et al. (2025). "Advanced machine learning models for robust prediction of water quality index and water quality classification." Journal of Hydroinformatics. https://doi.org/10.2166/hydro.2025.290
Satoh, Y., et al. (2022). Global water scarcity assessment incorporating water quality and environmental flow requirements. Water Resources Research, 58(2), e2021WR030531. https://doi.org/10.1029/2020WR028570
Srinivasan, V., Lambin, E. F., Gorelick, S. M., Thompson, B. H., & Rozelle, S. (2012). The nature and causes of the global water crisis: Syndromes from a meta-analysis of coupled human-water studies. Water Resources Research, 48(10). https://doi.org/10.1029/2011WR011087
Sun, J., & Gong, D. (2025). "Machine learning approaches for predicting water quality towards sustainable development." Hydrology Research. https://doi.org/10.2166/nh.2025.042
Tigkas, D., Vangelis, H., & Tsakiris, G. (2015). DrinC: A software for drought analysis based on drought indices. Earth Science Informatics, 8(3), 697-709. https://doi.org/10.1007/s12145-014-0178-y
Tong, X., Xiang, Z., You, L., Zhang, J., & Gin, K. Y. H. (2025). Modelling Approach to Understanding the Nexus of Emerging Contaminants, Climate Change, and Water Security. Current Opinion in Environmental Science & Health, 100650. https://doi.org/10.1016/j.coesh.2025.100650
Viñals, E., Maneja, R., Rufí-Salís, M., Martí, M., & Puy, N. (2023). Reviewing social-ecological resilience for agroforestry systems under climate change conditions. Science of the total environment, 869, 161763.
Water security (pp. 40-42). (2011). Organization for Economic Cooperation and Development. https://doi.org/10.1787/9789264115958-15-en
Yuan, L., He, W., Degefu, D. M., Liao, Z., Wu, X., An, M., ... & Ramsey, T. S. (2020). Transboundary water sharing problem; a theoretical analysis using evolutionary game and system dynamics. Journal of Hydrology, 582, 124521. https://doi.org/10.1016/j.jhydrol.2019.124521
Yuan, L., Li, R., He, W., Wu, X., Kong, Y., Degefu, D. M., & Ramsey, T. S. (2022). Coordination of the industrial-ecological economy in the Yangtze River Economic Belt, China. Frontiers in Environmental Science, 10, 882221. https://doi.org/10.3389/fenvs.2022.882221
Zhang Y, et al. (2024). "Assessment and forecasting of water ecological security and obstacle diagnosis." Frontiers in Environmental Science. https://www.ncbi.nlm.nih.gov/pmc/articles/PMC11461892/pmc.ncbi.nlm.nih