شناخت توزیع مکانی احتمال رخ‌داد فرسایش خندقی با مدل بیشینه‌ی آنتروپی

نوع مقاله : پژوهشی

نویسندگان

1 دانشجوی دکترای گروه احیای مناطق خشک و کوهستانی، دانشکده‌ی منابع طبیعی، دانشگاه تهران، کرج، ایران

2 دانشیار گروه احیای مناطق خشک و کوهستانی، دانشکده‌ی منابع طبیعی، دانشگاه تهران، کرج، ایران

3 استاد گروه احیای مناطق خشک و کوهستانی، دانشکده‌ی منابع طبیعی، دانشگاه تهران، کرج، ایران

4 استادیار گروه احیای مناطق خشک و کوهستانی، دانشکده‌ی منابع طبیعی، دانشگاه تهران، کرج، ایران

5 بخش تحقیقات حفاظت خاک و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی استان فارس، سازمان تحقیقات آموزش و ترویج کشاورزی، شیراز، ایران

چکیده

فرسایش خندقی (آبکندی) یکی از مهم‌ترین نوع‌های فرسایش آبی است که به­ دلیل تأثیرهای درون‌منطقه‌یی و برون‌منطقه‌یی، نقش زیادی در ویرانی و نابودی توان تولید سرزمین دارد. تهیه‌ی نقشه‌ی مکانی احتمال رخ‌داد فرسایش خندقی برای مدیریت مناسب­تر کاربری زمین با هدف کاهش تخریب زمین در منطقه‌های آماده‌ی رخ‌داد خندق کارآیی زیادی دارد. پراکنش این فرسایش در ایران و گستردگی عامل‌ها و فرآیندهای مؤثر بر ایجاد آن، مانعی بزرگ در ایجادکردن مدلی فراگیر برای پیش­بینی رخ‌داد آن در مقیاس بزرگ‌ است. هدف از این تحقیق تهیه‌کردن نقشه‌ی احتمال رخ‌داد فرسایش خندقی با مدل یادگیری ماشینی بیشینه‌ی آنتروپی در استان فارس است. در این پژوهش از متغیرهای مرتبط با ویژگی­های زمینی و به­ ویژه خاک بهره‌گیری شد. سطح زیر منحنیِ ویژگیِ عاملِ گیرنده بیش از 90% به‌دست آمد، که نشان می­دهد مدل به‌خوبی توانست فرسایش خندقی را با داده­ ها ارزیابی کند. برپایه‌ی یافته‌های آزمون جک­نایف، متغیرهای احتمال روی‌داد افق R، عمق خاک، درصد قطعه‌های درشت­دانه، پی‌اچ در محلول کلرید پتاسیم، و درصد ذره‌های لای بیش‌ترین تأثیر را در مدل­سازی فرسایش خندقی داشت. نقشه‌ی توزیع مکانی احتمال رخ‌داد خندق، نقشه‌ی حساسیت زمین‌ها به فرسایش خندقی است. بر پایه‌ی یافته ­ها بیش‌ترین حساسیت به فرسایش خندقی در جنوب استان فارس است. نقشه‌ی تهیه‌شده در این تحقیق می­تواند نقشه‌ی پایه برای آمایش سرزمین، مدیران و مهندسان شهرسازی، راه­سازی، منابع طبیعی و کشاورزی باشد.

کلیدواژه‌ها


عنوان مقاله [English]

Determining the Spatial Distribution of Gully Erosion Probability Using the MaxEnt Model

نویسندگان [English]

  • Teimur Teimurian 1
  • Aliakbar Nazari Samani 2
  • Sadat Feiznia 3
  • khaled Ahmadaali 4
  • Seyed Masoud Soleimanpour 5
1 Ph.D. Candidate, Natural Resources Faculty, University of Tehran, Karaj, Iran
2 Associate Professor, Natural Resources Faculty, University of Tehran, Karaj, Iran
3 Professor, Natural Resources Faculty, University of Tehran, Karaj, Iran
4 Assistant Professor, Natural Resources Faculty, University of Tehran, Karaj, Iran
5 Soil Conservation and Watershed Management Research Department, Fars Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Shiraz, Iran
چکیده [English]

Gully erosion is one of the most important types of water erosion, which has a great role in the destruction of land production capacity due to intra-regional and extra-regional effects. Preparing a spatial map of the possibility of gully erosion for better management of land use with the aim of reducing land degradation in areas prone to gully occurrence is very efficient. The distribution of this erosion in Iran and the extent of factors and processes affecting its creation have been a major obstacle in creating a comprehensive model for predicting its occurrence on a large scale. The purpose of this study is to prepare a map of the probability of gully erosion using the machine learning model of maximum entropy in Fars province. In this research, it has been tried to use variables related to terrestrial characteristics, especially soil. According to the results, the area under the ROC curve is above 90%, which shows that the model has been able to evaluate the gully erosion in the study area using the studied data. According to the results of the Jaknaev test, the variables of R horizon probability, soil depth, percentage of coarse grains, pH, and silt particles have the greatest impact on modeling moat erosion in the study area. The spatial distribution map of the occurrence of the gully is a map of land susceptibility to gully erosion. Based on the findings, the highest sensitivity to gully erosion is related to the south of Fars province. The map prepared in this research can be used as a basic map for land management, managers and engineers of urban planning, road construction, natural resources, and agriculture.

کلیدواژه‌ها [English]

  • Fars Province
  • gully erosion
  • maximum entropy
Abedini M. 2009. Quantitative study of hydro geomorphological issues of Likuan Chay Catchment with emphasis on soil erosion and sedimentation (southeast of Ardabil Province). Geography and Development, 7 (15):71–88. (In Persian).
Afshari H. 2016. Investigation of topographic threshold for gully erosion in cold semi-arid climate of Zanjan Province. Thesis of Master Science. Faculty of Natural Resources and Earth Sciences. University of Kashan, 109 p. (In Persian).
Ansari MR, Soleimani F, Ahmadi AR. 2020. Evaluation zonation of sensitive areas to gully erosion using fuzzy logic (Case study: Ghaleh Gorg Watershed- Shushtar). Journal of Water and Soil, 34 (5): 1033­­–1045. (In Persian).
Arabameri A, Chen W, Loche M, Zhao X, Li Y, Lombardo L, Bui DT. 2020. Comparison of machine learning models for gully erosion susceptibility mapping. Geoscience Frontiers, 11(5): 1609–1620.
Arabameri A, Asadi Nalivan O, Saha S, Roy J, Pradhan B, Tiefenbacher JP, Thi Ngo PT. 2020. Novel ensemble approaches of machine learning techniques in modeling the gully erosion susceptibility. Remote Sensing, 12(11): 1–30.
Asgari Saraskanroud S. 2017. Analysis off effective factors in the formation and spread of gully erosion. Geographical Space. 17 (58): 285–301. (In Persian).
Azareh A, Rahmati O, Rafiei-Sardooi E, Sankey JB, Lee S, Shahabi H, Ahmad BB. 2019. Modelling gully-erosion susceptibility in a semi-arid region, Iran: Investigation of applicability of certainty factor and maximum entropy models. Science of the Total Environment, 655: 684–696.
Boos DD, Brownie C. 2004. Comparing variances and other measures of dispersion. Statistical Science, 19(4): 571-578.
Chen T, Niu RQ, Li PX, Zhang LP, Du B. 2011. Regional soil erosion risk mapping using RUSLE, GIS, and remote sensing: Acase study in Miyun Watershed, North China. Environmental Earth Sciences, 63(3): 533–541.
De Sousa LM, Heuvelink GBM, Batjes NH, Kempen B. 2018. Soil Grids: Using big data solutions and machine learning algorithms for global soil mapping. In Scientific Symposium FAIR Data Sciences for Green Life Sciences, pp. 1-1.
De Sousa LM, Poggio L, Dawes G, Kempen B, Van Den Bosch R. 2020. Computational infrastructure of Soil Grids 2.0. In International Symposium on Environmental Software Systems, Springer, Cham. pp. 24–31.
Dube F, Nhapi I, Murwira A, Gumindoga W, Goldin J, Mashauri DA. 2014. Potential of weight of evidence modelling for gully erosion hazard assessment in Mbire District–Zimbabwe. Physics and Chemistry of the Earth, Parts A/B/C, 67-69: 145–152.
Hoseinzadeh MM, Esmaeili R, Jouri MH, Pourkalhor S. 2017. Morphometric analysis of gullies relation to physical and chemical properties of soil in Kojoor area of Nowshahr (Mazanderan Province). Rang and Watershed, 69 (1):27–38. (In Persian).
Feiznia S, Teimurian T, Rahmati O. 2018. Modeling of natural hazards (concepts and application of data-mining techniques). Gorgan University of Agricultural Sciences and Natural Resources, 278 p. (In Persian).
Gayen A, Pourghasemi HR, Saha S, Keesstra S, Bai S. 2019. Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms. Science of the Total Environment, 668: 124–138.
Ghodosi J, Davari M. 2005. The effect of physical and chemical properties of soil on the occurrence of gully erosion and morphology of gullies. Conference on Erosion and Sedimentation. Tehran, 7 p. (In Persian).
Gomez Gutierrez A, Schnabel S, Felicísimo AM. 2009. Modelling the occurrence of gullies in rangelands of southwest Spain. Earth Surface Processes and Landforms: The Journal of the British Geomorphological Research Group, 34(14): 1894–1902.
Jafari gorzin B, Kavyan A. 2009. Evaluation of gully erosion in Sorkhabad Watershed of Mazanderan using RS and GIS. Watershed Management Science & Engineering, 3 (7): 55–58. (In Persian).
Lei X, Chen W, Avand M, Janizadeh S, Kariminejad N, Shahabi H, Mosavi A. 2020. GIS-based machine learning algorithms for gully erosion susceptibility mapping in a semi-arid region of Iran. Remote Sensing, 12(15). 2478: 1–25.
Kariminejad N, Hosseinalizadeh M, Pourghasemi HR, Bernatek-Jakiel A, Campetella G, Ownegh M. 2019. Evaluation of factors affecting gully headcut location using summary statistics and the maximum entropy model: Golestan Province, NE Iran. Science of the Total Environment, 677: 281–298.
Mehregan N. 2017. Studying of soils, clay mineralogy diversity, and physicochemical characteristics of some badland with gully erosion. Thesis of Master Science. Ramin Agricultural and Natural Resources University of Khuzestan, 167 p. (In Persian).
Nazari S, Rostamnia M, Ayoubi SH, Rahmani A, Mousavi SR. 2020. The efficiency of different feature selection methods in digital mapping of subgroup and soil family classes with data mining algorithms. Water and Soil, 34 (4): 973–987. (In Persian).
Pourghasemi HR, Sadhasivam N, Kariminejad N, Collins AL. 2020. Gully erosion spatial modelling: Role of machine learning algorithms in selection of the best controlling factors and modelling process. Geoscience Frontiers, 11(6): 2207–2219.
Rahmati O, Tahmasebipour N, Haghizadeh A, Pourghasemi HR, Feizizadeh B. 2017. Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion. Geomorphology, 298: 118–137.
Rahmati O, Tahmasebipour N, Haghizadeh A, Pourghasemi H, Feizizadeh, B. 2019. Assessing the effectiveness of the maximum entropy model to gully erosion susceptibility prediction in the Kashkan-Poldokhtar Watershed. Watershed Engineering and Management, 10 (4): 727–738.
Saber Chenari K. 2017. Gully erosion potential hazard zoning using (Dempster-Shafer, Regression, Frequency Ratio and Risk Factor) statistical methods in the Gharnaveh Watershed, Golestan Province. Ph.D. Dissertation. Gorgan University of Agricultural Sciences and Natural Resources, 176 p. (In Persian).
Servati MR, Ghodousi J, Dadkhah M. 2008. Factors effecting initiation and advancement of gully erosion in losses. Pajouhesh-va-Sazandegi in Natural Resources, 21 (1): 20–33. (In Persian).
Shit PK, Bhunia GS, Maiti R. 2014. Morphology and development of selected Badlands in South Bengal (India). Indian Journal of Geography and Environment, 13: 161–171.
Soil Grids. 2020. www.soilgrids.org
Soleimanpour SM, Soufi M, Ahmadi H. 2010. Investigation of the effect of surface soil properties on the longitudinal expansion of gullies in different climates of Fars Province. Watershed Management Science & Eengineering, 7 (22):75–78. (In Persian).
Soleimani F, Soufi M, Arsham A. 2017. Determination of effective factors in gullies development in Modares Watershed of Shushtar. Journal of Water and Soil, 31 (5): 1432–1446. (In Persian).
Soufi M. 2004. Investigation of morphoclimatic characteristics of ditches in Fars Province. Final Report of the Research Project. Soil Conservation and Watershed Management Research Institute. 130 p. (In Persian).
Yamani M, Zamanzadeh SM, Ahmadi M. 2013. Influence of physical and chemical properties of soil on formation and development of gully erosion (Case study: Kahoor Plain in Fars Province). Quantitative Geomorphological Research, 2(2): 135–156. (In Persian).
Yousefvand S. 2010. Determining effective factors on gully development (Case study: Sifabad Basin of Aleshtar, Lorestan Province). Thesis of Master Science. Faculty of Natural Resources. University of Agriculture and Natural Resources of Sari, 148 p. (In Persian).
Zakerinejad R. 2020. Evaluation of DEMs to the modeling of the potential of gully erosion using Maxent model (Case study: Semirom Catchment in the south of Isfahan Province, Iran). Journal of RS and GIS for Natural Resources, 11 (3):106–122.