با همکاری انجمن هیدرولیک ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری ، گروه علوم و مهندسی آب، دانشگاه بیرجند، بیرجند، ایران

2 دانشجوی دکتری، گرایش مهندسی آب و سازه های هیدرولیکی، دانشکده‌ مهندسی عمران، دانشگاه تهران، تهران، ایران

3 دانش‌آموخته کارشناسی ارشد دانشگاه تهران و کارشناس GIS شرکت گاز استان خراسان جنوبی، بیرجند، ایران.

10.22077/jaaq.2024.7282.1062

چکیده

پیش‌بینی پتانسیل آب‌های زیرزمینی جهت توسعه و برنامه‌ریزی سیستماتیک منابع آب بسیار حیاتی است. هدف اصلی این تحقیق، توسعه مدل‌های یادگیری ماشینی از جمله جنگل تصادفی (RF)، درخت تصمیم (DT) و ماشین بردار پشتیبان (SVM) برای پیش‌بینی مناطق پتانسیلی آب زیرزمینی در دشت بیرجند است. بنابراین، برای اجرای این مطالعه، داده‌های ژئوهیدرولوژیکی مربوط به 37 چاه آب زیرزمینی (شامل تعداد و موقعیت چاه‌ها و سطح آب زیرزمینی) و 17 معیار هیدرولوژی، توپوگرافی، زمین‌شناسی و محیطی مورد استفاده قرار گرفت. روش انتخاب ویژگی از طریق کمترین مربعات ماشین بردار پشتیبان جهت تعیین معیارهای مؤثر برای بهبود عملکرد الگوریتم‌های یادگیری ماشین به کار گرفته شد. در نهایت، نقشه‌های پیش‌بینی پتانسیل آب زیرزمینی با استفاده از مدل‌های DT، RF و SVM تهیه شدند و عملکرد این مدل‌ها با استفاده از سطح زیر منحنی (AUC) و سایر شاخص‌های آماری مورد ارزیابی قرار گرفت. نتایج نشان داد که مدل DT (AUC=0.89) توانایی پیش‌بینی بسیار بالایی برای پتانسیل آب زیرزمینی در منطقه مورد مطالعه دارد و معیار ارتفاع به عنوان مهم‌ترین عامل در پیش‌بینی پتانسیل آب زیرزمینی در این منطقه شناخته شد. نتایج این مطالعه می‌تواند به عنوان راهنمایی برای تصمیم‌گیری و برنامه‌ریزی مناسب در استفاده بهینه از منابع آب زیرزمینی مورد استفاده قرار گیرد.

کلیدواژه‌ها

موضوعات

عنوان مقاله [English]

Assessment of machine learning models in GIS for predicting groundwater in semi-arid regions of eastern Iran

نویسندگان [English]

  • Mobin Eftekhari 1
  • Ali Haji Elyasi 2
  • Seyed Ahmad Eslaminezhad 3

1 Ph.D Student, Water Engineering Department, University of Birjand, Birjand, Iran

2 Ph.D. Student, Department of Civil Engineering, College of Engineering, University of Tehran, Tehran, Iran

3 Master's graduate of Tehran university and GIS expert of Gas Company, of South Khorasan Province, Birjand, Iran

چکیده [English]

Predicting groundwater potential is crucial for systematic development and planning of water resources. The main objective of this study is to develop machine learning models including Random Forest (RF), Decision Tree (DT), and Support Vector Machine (SVM) for predicting potential groundwater areas in the Birjand plain. Therefore, for the implementation of this study, geohydrological data related to 37 groundwater wells (including the number and location of wells and groundwater levels) and 17 hydrological, topographical, geological, and environmental criteria were used. Feature selection was performed using Support Vector Machine's least squares method to determine effective criteria for improving the performance of machine learning algorithms. Ultimately, predictive maps of groundwater potential were prepared using DT, RF, and SVM models, and the performance of these models was evaluated using the Area under the Curve (AUC) and other statistical indicators. The results showed that the DT model (AUC=0.89) has very high predictive capability for groundwater potential in the study area, and elevation was identified as the most important factor in predicting groundwater potential in this area. The findings of this study can serve as a guide for decision-making and appropriate planning in the optimal use of groundwater resources.

کلیدواژه‌ها [English]

  • Birjand Plain
  • Predictive Maps
  • Random Forest
  • Decision Tree
  • Support Vector Machine
Abbaspour, K. C., Faramarzi, M., Ghasemi, S. S., & Yang, H. (2009). Assessing the impact of climate change on water resources in Iran. Water resources research, 45(10).
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.
Bhavsar, H., & Panchal, M. H. (2012). A review on support vector machine for data classification. International Journal of Advanced Research in Computer Engineering & Technology (IJARCET), 1(10), 185-189.
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.
Deepika, B., Avinash, K., & Jayappa, K. S. (2013). Integration of hydrological factors and demarcation of groundwater prospect zones: insights from remote sensing and GIS techniques. Environmental earth sciences, 70, 1319-1338.
Dong, H., Yang, L., & Wang, X. (2021). Robust semi-supervised support vector machines with Laplace kernel-induced correntropy loss functions. Applied Intelligence, 51, 819-833.
Eftekhari, M., Madadi, K., & Akbari, M. (2019). Monitoring the fluctuations of the Birjand Plain aquifer using the GRACE satellite images and the GIS spatial analyses. Watershed Management Research Journal, 32(4), 51-65.
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.
Ferreira, C. S. S., Walsh, R. P. D., Steenhuis, T. S., Shakesby, R. A., Nunes, J. P. N., Coelho, C. O. A., & Ferreira, A. J. D. (2015). Spatiotemporal variability of hydrologic soil properties and the implications for overland flow and land management in a peri-urban Mediterranean catchment. Journal of Hydrology, 525, 249-263.
Foster, S., Chilton, J., Nijsten, G. J., & Richts, A. (2013). Groundwater—a global focus on the ‘local resource’. Current opinion in environmental sustainability, 5(6), 685-695.
Genuer, R., Poggi, J. M., Genuer, R., & Poggi, J. M. (2020). Random forests (pp. 33-55). Springer International Publishing.
Guido, J. J., Winters, P. C., & Rains, A. B. (2006). Logistic regression basics. MSc University of Rochester Medical Center, Rochester, NY, 21.
Hilario, M., Kalousis, A., Pellegrini, C., & Müller, M. (2006). Processing and classification of protein mass spectra. Mass spectrometry reviews, 25(3), 409-449.
Hussein, A. A., Govindu, V., & Nigusse, A. G. M. (2017). Evaluation of groundwater potential using geospatial techniques. Applied Water Science, 7, 2447-2461.
Li, H., Zhao, X., Gao, X., Ren, K., & Wu, P. (2018). Effects of water collection and mulching combinations on water infiltration and consumption in a semiarid rainfed orchard. Journal of Hydrology, 558, 432-441.
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.
Miralles, P., Church, T. L., & Harris, A. T. (2012). Toxicity, uptake, and translocation of engineered nanomaterials in vascular plants. Environmental science & technology, 46(17), 9224-9239.
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.
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.
Sanaeinejad et al. (2014), Wheat yield estimation using Landsat images and field observation: A case study in Mashhad. J. of Plant Production, Vol. 20 (4), 2014. 
Sansone, M., Fusco, R., Pepino, A., & Sansone, C. (2013). Electrocardiogram pattern recognition and analysis based on artificial neural networks and support vector machines: a review. Journal of healthcare engineering, 4, 465-504.
Tashayo, B., Honarbakhsh, A., Akbari, M., & Eftekhari, M. (2020). Land suitability assessment for maize farming using a GIS-AHP method for a semi-arid region, Iran. Journal of the Saudi Society of Agricultural Sciences, 19(5), 332-338.
Uuemaa, E., Ahi, S., Montibeller, B., Muru, M., & Kmoch, A. (2020). Vertical accuracy of freely available global digital elevation models (ASTER, AW3D30, MERIT, TanDEM-X, SRTM, and NASADEM). Remote Sensing, 12(21), 3482.
Xiong, L., Tang, G., Yan, S., Zhu, S., & Sun, Y. (2014). Landform‐oriented flow‐routing algorithm for the dual‐structure loess terrain based on digital elevation models. Hydrological Processes, 28(4), 1756-1766.
Yaman, A., & Cengiz, M. A. (2021). The Effects of Kernel Functions and Optimal Hyperparameter Selection on Support Vector Machines. Journal of New Theory, (34), 64-71.
Yenehun, A., Nigate, F., Belay, A. S., Desta, M. T., Van Camp, M., & Walraevens, K. (2020). Groundwater recharge and water table response to changing conditions for aquifers at different physiography: The case of a semi-humid river catchment, northwestern highlands of Ethiopia. Science of The Total Environment, 748, 142243.
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.