پیوندهای مفید
اخبار و اعلانات
آمار
| تعداد نشریات | 161 |
| تعداد شماره‌ها | 6,476 |
| تعداد مقالات | 70,001 |
| تعداد مشاهده مقاله | 122,880,186 |
| تعداد دریافت فایل اصل مقاله | 96,074,687 |
ارزیابی جامع ریسک شوری آبخوان سرخون با بهره‌گیری از ترکیب مدل‌های یادگیری ماشین | ||
| اکوهیدرولوژی | ||
| مقاله 12، دوره 7، شماره 1، فروردین 1399، صفحه 147-163 اصل مقاله (1.65 M) | ||
| نوع مقاله: پژوهشی | ||
| شناسه دیجیتال (DOI): 10.22059/ije.2020.287185.1197 | ||
| نویسندگان | ||
| فریبرز محمدی* 1؛ علیرضا نفرزادگان2؛ محمد کاظمی3 | ||
| 1استادیار، گروه علوم و مهندسی آب، مجتمع آموزش عالی میناب، دانشگاه هرمزگان، بندرعباس | ||
| 2استادیار، گروه مهندسی منابع طبیعی، دانشکدۀ کشاورزی و منابع طبیعی، دانشگاه هرمزگان، بندرعباس | ||
| 3استادیار، مرکز مطالعات و تحقیقات (پژوهشکده) هرمز، دانشگاه هرمزگان، بندرعباس | ||
| چکیده | ||
| ارزیابی ریسک شوری آبخوان بهخصوص در مناطق نزدیک ساحل اهمیت زیادی دارد. در پژوهش حاضر تلاش شد از طریق ترکیب مدل پتانسیل آسیبپذیری آبخوان و الگوریتمهای یادگیری ماشین، چارچوب جامعی برای ارزیابی ریسک شوری در آبخوان سرخون واقع در استان هرمزگان ایجاد شود. در مرحلۀ نخست لایههای ورودی مورد نیاز برای تولید نقشۀ پتانسیل آسیبپذیری آبخوان براساس مدل دراستیک تهیه و ترکیب شد. سپس، با استفاده از سه الگوریتم یادگیری ماشین شامل جنگل تصادفی، افزایش گرادیان اکسترمم (XGBoost) و درختان رگرسیون جمعشدۀ بیزی (BART) و با استفاده از 12 فاکتور تأثیرگذار روی آب زیرزمینی از جمله رطوبت توپوگرافیک، خاک، پوشش گیاهی و عوامل دیگر، نقشۀ احتمال خطر شور شدن تهیه شد. قبل از مدلسازی آزمون همخطی روی دادهها انجام شد و مشاهده شد که همخطی در بین پارامترهای ورودی مدلها وجود ندارد. ارزیابی کارایی مدلسازی با منحنی ویژگی عملگر نسبی ROC)) نشان داد هر سه الگوریتم دقت بسیار خوب و سطح زیرمنحنی AUC)) بیش از 90 درصد دارند. بنابراین، هر سه مدل بر اساس میزان سطح زیرمنحنی خود ترکیب شدند تا یک نقشۀ واحد برای احتمال وقوع خطر شوری به دست آید. در انتها، نقشۀ ریسک شوری براساس مقادیر آسیبپذیری، شوری و احتمال وقوع خطر تهیه شد. نقشۀ ریسک بهدستآمده نشان داد قسمتهای شرقی آبخوان ریسک شوری بسیار زیاد دارد که علت این امر تمرکز زیاد زمینهای کشاورزی در این بخش دشت است. نتایج پژوهش حاضر نشان داد دستیابی به یک نقشۀ قابل اتکا برای ارزیابی ریسک شوری آبخوان به وسیلۀ ترکیب مدل‌های یادگیری ماشین و مدل‌های آسیبپذیری آبخوان امکانپذیر است. | ||
| کلیدواژه‌ها | ||
| آب زیرزمینی؛ خطر شوری؛ جنگل تصادفی؛ شاخص دراستیک؛ پتانسیل آسیبپذیری | ||
| عنوان مقاله [English] | ||
| Comprehensive Risk Assessment of Sarkhoon Aquifer Salinization Using a Combination of Machine Learning Models | ||
| نویسندگان [English] | ||
| Fariborz Mohammadi1؛ Ali Nafarzadegan2؛ Mohamad Kazemi3 | ||
| 1Assistant Professor, Department of Water Sciences & Engineering, Minab Higher Education Center, University of Hormozgan, Bandar Abbas, Iran | ||
| 2Assistant Professor, Department of Natural Resources Engineering, Faculty of Agriculture and Natural Resources, University of Hormozgan, Bandar Abbas, Iran | ||
| 3Assistant Professor, Hormoz Study and Research Center, University of Hormozgan, Bandar Abbas, Iran | ||
| چکیده [English] | ||
| Risk assessment of aquifer salinization is of great importance especially in regions near the coast. In this study, it was attempted to develop a comprehensive framework for salinity risk assessment for Sarkhoon aquifer, Hormozgan province by combining the aquifer vulnerability potential model and machine learning algorithms. In the first step, the input layers required for the generation of the aquifer vulnerability potential map were prepared based on DRASTIC model and combined. Then, the map of salinization hazard occurrence probability was obtained by using three machine learning models of Random Forest, Extreme Gradient Boosting (XGBoost), and Bayesian Additive Regression Trees (BART) by considering 12 factors affecting groundwater including topographic wetness, soil, vegetation and other factors. Prior to modeling, a collinearity test was performed on the data and it was observed that there was no collinearity between the models’ input parameters. Evaluation of the modeling performance with the receiver operating characteristic (ROC) curve indicated that all three algorithms had very good accuracies with area under curve (AUC) values higher than 90%. Thus, all three models were combined based on their AUC values to produce a united map for the probability of salinization hazard occurrence. Finally, the map of salinization risk was generated based on the values for the vulnerability, salinity and hazard occurrence probability. The obtained risk map showed that the eastern part of the aquifer has very high salinization risk which is due to the high concentration of agricultural land in this part of the plain. The results of this study revealed that achieving a reliable map for assessing aquifer salinization risk is possible by combining machine learning models. | ||
| کلیدواژه‌ها [English] | ||
| Groundwater, Salinization hazard, Random Forest, DRASTIC index, Vulnerability potential | ||
| مراجع | ||
|
[1]. Abd-Elhamid HF, Javadi AA. A cost-effective method to control seawater intrusion in coastal aquifers. Water resources management. 2011 Sep 1; 25(11):2755-80. [2]. Kaliraj S, Chandrasekar N, Peter TS, Selvakumar S, Magesh NS. Mapping of coastal aquifer vulnerable zone in the south west coast of Kanyakumari, South India, using GIS-based DRASTIC model. Environmental monitoring and assessment. 2015 Jan 1; 187(1):4073. [3]. Kazakis N, Pavlou A, Vargemezis G, Voudouris KS, Soulios G, Pliakas F, Tsokas G. Seawater intrusion mapping using electrical resistivity tomography and hydrochemical data. An application in the coastal area of eastern Thermaikos Gulf, Greece. Science of the Total Environment. 2016 Feb 1; 543:373-87. [4]. Anders R, Mendez GO, Futa K, Danskin WR. A geochemical approach to determine sources and movement of saline groundwater in a coastal aquifer. Groundwater 52, 756–768. [5]. Han DM, Song XF, Currell MJ, Yang JL, Xiao GQ. Chemical and isotopic constraints on evolution of groundwater salinization in the coastal plain aquifer of Laizhou Bay, China. Journal of Hydrology. 2014 Jan 16; 508:12-27. [6]. Stigter TY, Ribeiro L, Dill AC. Evaluation of an intrinsic and a specific vulnerability assessment method in comparison with groundwater salinisation and nitrate contamination levels in two agricultural regions in the south of Portugal. Hydrogeology Journal. 2006 Jan 1; 14(1-2):79-99. [7]. Johnson TD, Belitz K. Assigning land use to supply wells for the statistical characterization of regional groundwater quality: correlating urban land use and VOC occurrence. Journal of Hydrology. 2009 May 30; 370(1-4):100-8. [8]. McLay CD, Dragten R, Sparling G, Selvarajah N. Predicting groundwater nitrate concentrations in a region of mixed agricultural land use: a comparison of three approaches. Environmental Pollution. 2001 Dec 1; 115(2):191-204. [9]. van Beynen PE, Niedzielski MA, Bialkowska-Jelinska E, Alsharif K, Matusick J. Comparative study of specific groundwater vulnerability of a karst aquifer in central Florida. Applied Geography. 2012 Mar 1; 32(2):868-77. [10]. Aller L, Lehr JH, Petty R. DRASTIC: a standardized system to evaluate ground water pollution potential using hydrogeologic settings. National water well Association Worthington, Ohio 43085. Truman Bennett. Bennett and Williams. Inc. Columbus, Ohio. 1987; 43229. [11]. Foster SS. Fundamental Concepts in Aquifer Vulnerability, Pollution Risk and Protection Strategy: International Conference, 1987, Noordwijk Aan Zee, the Netherlands Vulnerability of Soil and Groundwater to Pollutants The Hague, Netherlands Organization for Applied Scientific Research. Netherlands Organization for Applied Scientific Research; 1987. [12]. Zhou J, Li G, Liu F, Wang Y, Guo X. DRAV model and its application in assessing groundwater vulnerability in arid area: a case study of pore phreatic water in Tarim Basin, Xinjiang, Northwest China. Environmental Earth Sciences. 2010 May 1; 60(5):1055-63. [13]. Nobre RC, Rotunno Filho OC, Mansur WJ, Nobre MM, Cosenza CA. Groundwater vulnerability and risk mapping using GIS, modeling and a fuzzy logic tool. Journal of Contaminant Hydrology. 2007 Dec 7; 94(3-4):277-92. [14]. Iqbal J, Gorai AK, Tirkey P, Pathak G. Approaches to groundwater vulnerability to pollution: a literature review. Asian Journal of Water, Environment and Pollution. 2012 Jan 1; 9(1):105-15. [15]. Anane M, Abidi B, Lachaal F, Limam A, Jellali S. GIS-based DRASTIC, Pesticide DRASTIC and the Susceptibility Index (SI): comparative study for evaluation of pollution potential in the Nabeul-Hammamet shallow aquifer, Tunisia. Hydrogeology Journal. 2013 May 1; 21(3):715-31. [16]. Nohegar, A., Riahi, F. The Comparison of Fuzzy Drastic Model and Conventional Drastic Model to Determine the Most Appropriate Indicator of Groundwater Vulnerability, Case Study: Sarkhoon Plain Aquifer. Journal of Environmental Studies, 2014; 40(3):711-722. (In Persian) [17]. Nakhaei M, Amiri V, Rahimi shahr Babaki M. Evaluating of the potential pollution and sensitivity analysis of groundwater in the aquifer Khatoonabad using DRASTIC model based on GIS. Advanced Applied Geology Journal. 2013; 3(8): 1-10. (In Persian) [18]. Matzeu A, Secci R, Uras G. Methodological approach to assessment of groundwater contamination risk in an agricultural area. Agricultural water management. 2017 Apr 1; 184:46-58. [19]. Choubin B, Malekian A. Combined gamma and M-test-based ANN and ARIMA models for groundwater fluctuation forecasting in semiarid regions. Environmental Earth Sciences. 2017 Aug 1; 76(15):538. [20]. Ghorbani Nejad S, Falah F, Daneshfar M, Haghizadeh A, Rahmati O. Delineation of groundwater potential zones using remote sensing and GIS-based data-driven models. Geocarto international. 2017 Feb 1; 32(2):167-87. [21]. Luoma S, Okkonen J, Korkka-Niemi K. Comparison of the AVI, modified SINTACS and GALDIT vulnerability methods under future climate-change scenarios for a shallow low-lying coastal aquifer in southern Finland. Hydrogeology Journal. 2017 Feb 1; 25(1):203-22. [22]. Barzegar R, Moghaddam AA, Deo R, Fijani E, Tziritis E. Mapping Groundwater Contamination Risk of Multiple Aquifers Using Multi-Model Ensemble of Machine Learning Algorithms. Science of The Total Environment. 2018 Apr 15; 621:697-712. [23]. Regional Water Company of Hormozgan. Reclamation and balancing plan for groundwater resources of Sarkhoon plain. 2018 Jan 2. [24]. Rahman A. A GIS based DRASTIC model for assessing groundwater vulnerability in shallow aquifer in Aligarh, India. Applied geography. 2008 Jan 1; 28(1):32-53. [25]. Neshat A, Pradhan B, Pirasteh S, Shafri HZ. Estimating groundwater vulnerability to pollution using a modified DRASTIC model in the Kerman agricultural area, Iran. Environmental earth sciences. 2014 Apr 1; 71(7):3119-31. [26]. Aller L, Lehr JH, Petty R. DRASTIC: a standardized system to evaluate ground water pollution potential using hydrogeologic settings. National water well Association Worthington, Ohio 43085. Truman Bennett. Bennett and Williams. Inc. Columbus, Ohio. 1987; 43229. [27]. Regional Water Company of Hormozgan, Updating water resources balance sheet for study areas of Bandar Abbas - Sedij river basin. Sangab Zagros Consulting Engineers. 2016 Feb 4. [28]. Wilcox LV. Classification and use of irrigation waters. 1955 [29]. Wilcox, L. V. The quality of water for irrigation use United States Department of Agriculture, Economic Research Service. 1948; Washington, D.C.: U.S. Dept. of Agriculture. [30]. Arabameri A, Rezaei K, Cerda A, Lombardo L, Rodrigo-Comino J. GIS-based groundwater potential mapping in Shahroud plain, Iran. A comparison among statistical (bivariate and multivariate), data mining and MCDM approaches. Science of The Total Environment. 2019 Mar 25; 658:160-77. [31]. Sajedi-Hosseini F, Malekian A, Choubin B, Rahmati O, Cipullo S, Coulon F, Pradhan B. A novel machine learning-based approach for the risk assessment of nitrate groundwater contamination. Science of The Total Environment. 2018 Dec 10; 644:954-62. [32]. Constantin M, Bednarik M, Jurchescu MC, Vlaicu M. Landslide susceptibility assessment using the bivariate statistical analysis and the index of entropy in the Sibiciu Basin (Romania). Environmental Earth Sciences. 2011 May 1; 63(2):397-406. [33]. Jothibasu A, Anbazhagan S. Modeling groundwater probability index in Ponnaiyar River basin of South India using analytic hierarchy process. Modeling Earth Systems and Environment. 2016 Sep 1; 2(3):109. [34]. Ercanoglu M, Gokceoglu C. Assessment of landslide susceptibility for a landslide-prone area (north of Yenice, NW Turkey) by fuzzy approach. Environmental geology. 2002 Feb 1; 41(6):720-30. [35]. Al-Abadi AM, Al-Temmeme AA, Al-Ghanimy MA. 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. 2016 Sep 1; 2(3):265-83. [36]. Naghibi SA, Pourghasemi HR, Pourtaghi ZS, Rezaei A. Groundwater qanat potential mapping using frequency ratio and Shannon’s entropy models in the Moghan watershed, Iran. Earth Science Informatics. 2015 Mar 1; 8(1):171-86. [37]. Patriche CV, Căpăţână V, Stoica DL. Aspects Regarding soil erosion spatial modeling using the USLE/RUSLE within GIS, Geographia Tehnica, Nr. 2. [38]. Moore ID, Grayson RB, Ladson AR. Digital terrain modelling: a review of hydrological, geomorphological, and biological applications. Hydrological processes. 1991 Jan;5(1):3-0. [39]. Chen T, Guestrin C. XGBoost: A Scalable Tree Boosting System. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining 2016 Aug 13 (pp. 785-794). ACM. [40]. Fan J, Wang X, Wu L, Zhou H, Zhang F, Yu X, Lu X, Xiang Y. Comparison of Support Vector Machine and Extreme Gradient Boosting for predicting daily global solar radiation using temperature and precipitation in humid subtropical climates: A case study in China. Energy conversion and management. 2018 May 15; 164:102-11. [41]. Nicodemus KK. Letter to the Editor: On the stability and ranking of predictors from random forest variable importance measures. Briefings in bioinformatics. 2011 Apr 15; 12(4):369-73. [42]. Feng D, Svetnik V, Liaw A, Pratola M, Sheridan RP. Building Quantitative Structure-Activity Relationship Models Using Bayesian Additive Regression Trees. Journal of chemical information and modeling. 2019 May 6. [43]. Voudouris K, Kazakis N, Polemio M, Kareklas K. Assessment of intrinsic vulnerability using DRASTIC model and GIS in Kiti aquifer, Cyprus. European water. 2010. [44]. Dewan A. Floods in a megacity: geospatial techniques in assessing hazards, risk and vulnerability. Dordrecht: Springer; 2013 Mar 1. [45]. Mousavi SM, Golkarian A, Naghibi SA, Kalantar B, Pradhan B. GIS-based groundwater spring potential mapping using data mining boosted regression tree and probabilistic frequency ratio models in Iran. AIMS Geosci. 2017 Mar 2;3(1):91-115. | ||
|
آمار تعداد مشاهده مقاله: 548 تعداد دریافت فایل اصل مقاله: 495 |
||