کاربرد شبکة عصبی در مدل‌سازی اثر عوامل محیطی بر انبوهی پوشش گیاهی در منطقة حفاظت‌شدة البرز مرکزی

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه محیط ‌زیست، دانشکده منابع طبیعی، دانشگاه تهران، کرج، ایران.

2 گروه ارزیابی و مخاطرات محیط ‌زیست، پژوهشکده محیط‌زیست و توسعه پایدار، سازمان حفاظت محیط‌ زیست کشور، تهران، ایران.

3 گروه جنگلداری و اقتصاد جنگل، دانشکده منابع طبیعی، دانشگاه تهران، کرج، ایران.

10.22059/jne.2023.353731.2514

چکیده

پوشش گیاهی در حفظ تعادل اکوسیستم‌ها نقش مهمی ایفا می‌کند و به‌عنوان یک شاخص با اهمیت در ارزیابی اکوسیستم‌های خشکی به‌شمار می‌آید. انبوهی پوشش گیاهی به‌عنوان یکی از خصوصیات مهم برای ارزیابی رستنی‌ها مورد بررسی قرار می‌گیرد. تغییرات پوشش گیاهی سبب به‌وجود آمدن بی‌نظمی در اکوسیستم شده و به‌عنوان یک محرک در تغییر ترکیب گونه‌ها و شرایط زیستگاهی عمل می‌کند. پژوهش حاضر با هدف مدل‌سازی اثر عوامل محیطی بر انبوهی پوشش گیاهی با کمک شبکة عصبی مصنوعی و تعیین اثرگذارترین متغیرهای اکولوژیک و انسانی بر انبوهی در منطقة حفاظت‌شدة البرز مرکزی تحت مدیریت استان البرز انجام شد. بدین‌منظور پس از تشکیل واحدهای همگن اکولوژیک، تعداد 101 قطعه نمونة مربعی شکل به ابعاد 2 در 2 متر، نمونة گیاهی و 101 نمونة خاک در این واحدها برداشت و آنالیزهای مربوط به خاک و پوشش گیاهی بر روی آن‌ها انجام گرفت. مدل‌سازی با استفاده از روش پرسپترون چند لایه انجام شد، داده ­های ورودی شامل متغیرهای فیزیکی و شیمیایی خاک، متغیرهای فیزیوگرافی (براساس نقشه‌های طرح مدیریت) و متغیرهای مربوط به عوامل انسانی (براساس نقشة فاصلة اقلیدسی از نقاط نمونه‌برداری) بود. با توجه به مقادیر ضریب تبیین در سه دسته دادة آموزش، اعتبارسنجی و آزمون برابر با 0/86، 0/79 و 0/81، ساختار بهینة مدل برای انبوهی پوشش گیاهی با ساختار 1-19-18 (18 متغیر ورودی، 19 نورون در لایة پنهان و یک متغیر خروجی) انتخاب شد. براساس نتایج آنالیز حساسیت، متغیرهای شیب، درصد مادة آلی و ارتفاع، اثرگذارترین متغیرها بر انبوهی پوشش گیاهی در محدودة مورد مطالعه شناسایی شد. مدل‌ ارائه‌شده در این پژوهش به‌عنوان سیستم‌ پشتیبان تصمیم‌گیری در ارزیابی اثرات فعالیت‌های انسان بر انبوهی پوشش گیاهی در مناطق تحت حفاظت کاربرد دارد و امکان پیش‌بینی میزان اثرات مذکور را بر انبوهی پوشش گیاهی در این مناطق فراهم می‌کند.

کلیدواژه‌ها

عنوان مقاله [English]

Environmental factor effects on vegetation coverage using Neural Network Modeling in central Alborz protected area

نویسندگان [English]

  • Hannaneh Sadat Sadat Mousavi 1
  • Ali Jahani 2
  • Afshin Danehkar 1
  • Vahid Etemad 3
  • Farnoush Attar Sahragard 1

1 Department of Environmental Science, Faculty of Natural Resources, University of Tehran, Karaj, Iran.

2 Department of Assessment and Environment Risks, Research Center of Environment and Sustainable Development, Iran Environmental Protection Organization, Tehran, Iran.

3 Department of Forestry and Forest Economics, Faculty of Natural Resources, University of Tehran, Karaj, Iran.

چکیده [English]

Vegetation plays an important role in maintaining the balance of ecosystems and is considered as a significant indicator in assessing the environment of terrestrial ecosystems. ‌The coverage of vegetation is considered as one of the important characteristics for the assessment of vegetation. Vegetation changes cause disorder in the ecosystem and act as a stimulus to change the composition of species and habitat conditions. The present research was conducted with the aim of modeling the effect of human activities on the coverage of vegetation with the help of artificial neural network and determining the most effective ecological and human variables on the coverage in the central Alborz protected area under the management of Alborz province. For this purpose, after the characterizing homogeneous ecological units, 101 plant square plots with dimensions of 2 x 2 meters and 101 soil samples were collected in these units. Modeling was done using multi-layer perceptron method, the input data included soil physical and chemical variables, physiographic variables (based on management plan maps) and variables related to human factors (based on the Euclidean distance map of sampling points). According to the values ​​of the coefficient of determination in the three categories of training, validation and test data equal to 0.86, 0.79 and 0.81, the optimal structure of the model for the coverage of vegetation with a structure of 1-19-18 (18 input variables, 19 neurons in the hidden layer and one output variable) was selected. Based on the results of sensitivity analysis, slope variables, percentage of organic matter and height, the most effective variables on the abundance of vegetation in the study area were identified. The model presented in this research is used as a decision support system in assessing the effects of human activities on the coverage of vegetation in protected areas and provides the possibility of predicting the extent of these effects on the coverage of vegetation in protected areas.

کلیدواژه‌ها [English]

  • Multilayer perceptron
  • Coverage
  • Artificial neural network
  • Environmental factors
Aghajani, H., Marvie Mohadjer, M.R., Jahani, A., Asef, M.R., Shirvany, A., Azaryan, M., 2014. Investigation of affective habitat factors affecting on abundance of wood macrofungi and sensitivity analysis using the artificial neural network. Iranian Journal of Forest and Poplar Research 21(4), 9-19. (In Persian)
Alborz Department of Environment (website), 2020. Introduction of Central Alborz Protected Area. Available from https://alborz.doe.ir/. (Accessed on 22 August 2020). (In Persian)
Ataei, F., Karami, M., Kaboli, M., 2012. Modeling the suitability of the brown bear's summer habitat (Ursus arctos syriacus) in South Alborz protected area. Journal of Natural Environment 65(2), 235-245. (In Persian)
Ballantyne, M., Gudes, O., Pickering, C.M., 2014. Recreational Trails Are an Important Cause of Fragmentation in Endangered Urban Forests: A Case-Study from Australia. Landscape and Urban Planning 130(1), 112-124.
Bayram Komaki, CH., Asadi Kia, R., Niknahad Gharmakher, H., 2019. Estimating the percentage of plant coverage and biomass using remote sensing indicators (Case study: Central Alborz protected area-Karaj city). Remote sensing and Geographic Information System in Natural Resources 10(1), 1-16. (In Persian)
Borana, S.L., Yadav, S.K., 2017. Prediction of land cover changes of Jodhpur City using cellular automata markov modelling techniques. International Journal of Engineering Science 17(11), 15402-15406.
Eagles, P., 2013. Research Priorities in Park Tourism. Journal of Sustainable Tourism 22(4), 528-549.
Eshaghi Rad, J., Heydari, M., Mahdavi, A., Zeini Vandzadeh, M., 2011. The effect of recreational activities on the vegetation and soil of the forest park (case study: Chaghasabz Forest Park, Ilam). Journal of Iranian Forestry, Iranian Forestry Association, 3(1), 71-80. (In Persian)
Ghaemi, Z., Moghim, E., 2016a. Studies of planning Alborz province: Department of location of vicissitude. Management and Planning Organization of Alborz Province, Shargh ayand Consulting Engineering Company, 54 p. (In Persian)
Ghaemi, Z., Moghim, E., 2016b. Studies of planning Alborz province: Department of Environmental Studies (Volume I). Management and Planning Organization of Alborz Province, Shargh ayand Consulting Engineering Company, 201 p. (In Persian)
Imani, J., Arzani, H. and Zare Chahouki, M.A., 2013. Comparing the effectiveness of density estimation methods of three pasture species Bromus tomentellus, Festuca ovina, Prangos ferullacea (Case study: Saral pastures of Kurdistan). Pasture and Watershed Journal (Iranian Natural Resources Magazine) 66(2), 179-190. (In Persian)
Jafari Haghighi, M., 2004. Soil analysis methods, sampling and important physical and chemical analyzes with emphasis on theoretical and practical principles. Nedaye zoha press, Tehran, 236 p. (In Persian)
Jahani, A., 2016. Modeling of forest canopy density confusion in environmental assessment using artificial neural network. Journal of Forest and Poplar Research 24(2), 310-322. (In Persian)
Jahani, A., 2019. Forest landscape aesthetic quality model (FLAQM): A comparative study on landscape modelling using regression analysis and artificial neural networks. Journal of Forest Science 65(2), 61-69.
Jahani, A., Goshtasb, H., Saffariha, M., 2020. Tourism impact assessment modeling of vegetation density for protected areas using data mining techniques. Journal of Land Degradation & Development 31(12), 1502-1519.
Jahani, A., Saffariha, M., 2021. Human activities impact prediction in vegetation diversity of Lar National Park in Iran using artificial neural network model. Journal of Integrated Environmental Assessment and Management 17(1), 42-52.
Jones, D.A., Hansen, A.J., Bly, K., Doherty, K., Verschuyl, J.P., Paugh, J.I., Carle, R., Story, S.J., 2009. Monitoring land use and cover around parks: a conceptual approach. Remote Sensing of Environment 113(7), 1346-1356.
Lucas‐Borja, M.E., Bastida, F., Moreno, J.L., Nicolás, C., Andres, M., Lopez, F.R., Del Cerro, A., 2011. The effects of human trampling on the microbiological properties of soil and vegetation in Mediterranean mountain areas. Journal of Land Degradation & Development 22(4), 383-394.
Maier, H.R., Jain, A., Dandy, G.C., Sudheer, K.P., 2010. Methods used for the development of neural networks for the prediction of water resource variables in river systems: Current status and future directions. Environmental Modelling & Software 25(8), 891-909.
Makhdoum, M., 2021. Fundamental of Land Use Planning. Tehran University press, Tehran, 300 p. (In Persian)
Moghaddam, M.R., 2008. Quantitative Plant Ecology. Tehran University press, Tehran, 285 p. (In Persian)
Mosaffaei, Z., Jahani, A., Zare Chahouki, M.A., Goshtasb, H., Etemad, V., 2019. Modeling vegetation destruction using Simpson's biodiversity index, (case study of Sorkheh Hesar National Park). National conference on modern studies of civil engineering, architecture and urban planning in the 21st century, Comprehensive University of Applied Sciences Organization of Municipalities Cooperation, Karaj, Iran, pp: 440-450. (In Persian)
Mosaffaei, Z., Jahani, A., Zare Chahouki, M.A., Goshtasb, H., Etemad, V., 2020. Modeling vegetation destruction in protected areas due to management plan, (case study of Sorkheh Hesar National Park). Journal of Plant Ecosystem Protection 8(16), 229-248. (In Persian)
Mosaffaei, Z., Jahani, A., Zare Chahouki, M.A., Goshtasb, H., Etemad, V., 2021. Modeling the risk of reducing the diversity and extinction of plant species in Sorkheh Hisar National Park. Journal of Spatial Analysis of Environmental Hazards 8(3), 157-170. (In Persian)
Mozaffarian, V., 2001. Studying the environmental management plan of central Alborz area. Bomabad consulting engineers, Department of Environment, Office of Management of Habitats and Regional Affairs, 359 p. (In Persian)
Nezami Balouchi, B., 2014. Investigating the seasonal food habits of the Syrian brown bear (Ursus arctos syriacus Linnaeus, 1758) in the central Alborz protected area. Journal of Taxonomy and Biosystematics 6(19), 27-36. (In Persian)
Norouzi, E., Pourebrahim, SH., Goshtasb, H., Jahani, A., 2019. Biodiversity risk zoning in Alborz Central Protected Area in the southern part (under the management of Alborz province) using the DANP technique. Quarterly Scientific Journal of Animal Environment Research 11(1), 97-104. (In Persian)
Peng, J., Liu, Z., Liu, Y., Wu, J., Han, Y., 2012. Trend analysis of vegetation dynamics in Qinghai–Tibet Plateau using Hurst Exponent. Ecological Indicators 14(1), 28-39.
Piri Sahragard, H., Zare Chahouki, M.A., Azarnivand, H., 2015. Modeling the distribution of plant species in dry and desert areas using artificial neural networks (Case study: Hoze sultan pastures of Qom province). Journal of Desert Management 3(5), 26-39. (In Persian)
Pongpattananurak, N., 2018. Impacts from tourism development and agriculture on forest degradation in Thap Lan National Park and adjacent areas. Agriculture and Natural Resources 52(3), 290-297.
Pourbabaei, H., Heydari, M., Faghir, M.B., Naghilou, M, 2012.  Biodiversity and vegetation richness assessment in understory relation to soil physicochemical properties and topography in the Sefid Mazou forest, Asalem, Gilan. Quarterly Journal of Plant and Ecosystem 8(31), 15-26.
Pourmohammad, P., 2018. Road impact assessment on soil and vegetation in protected areas (Case Study: Khojir National Park). M.Sc. thesis. Department of Environment. Collage of Environment, Iran, 111 p. (In Persian)
Pringle, M.J., Denham, R.J., Devadas, R., 2012. Identification of cropping activity in central and southern queensland, australia, with the aid of modis Mod13q1 imagery. International Journal of Applied Earth Observation and Geoinformation 19(1), 276-285.
Rannow, S. and Neubert, M., 2014. Managing protected areas in central and Eastern Europe under climate change. Springer Nature. 308 p.
Sadat Mousavi, H.S., Danehkar, A., Jahani, A., Etemad, V., Attar Sahragard, F., 2023. Modeling the effect of environmental factors on the diversity of vegetation in central Alborz protected area. Journal of Range and Watershed Management.
Shams, S.R., Jahani, A., Kalantary, S., Moeinaddini, M., Khorasani, N., 2021. The evaluation on artificial neural networks (ANN) and multiple linear regressions (MLR) models for predicting SO2 concentration. Urban Climate 37, 100837.
Sheydaei Karkaj, E., Motamedi, J., Alilou, F., Sirousi, H., 2017. The role of livestock grazing management on vegetation characteristics in Chaharbagh summer pastures of Golestan province. Pasture and Watershed Journal (Iranian Natural Resources Magazine) 69(4), 949-961. (In Persian).
Shirani sarmazeh, N., Jahani, A., Goshtasb Maygooni, H., Etemad, V., 2018. Ecological impacts assessment of recreation on quality of soil and vegetation in protected areas (case study: Qhamishloo National Park and Wildlife Refuge). Journal of Natural environment (Natural resources of Iran) 70(4), 881-891. (In Persian).
Tamrtash, R., 2012. Investigating the relationship between plant characteristics and topographical factors in the exploitation units of mountain pastures of Oz, Mazandaran. Pasture and Desert Research Scientific Journal 19(3), 469-481. (In Persian).
Tatiyan, M. R., Tamrtash, R., Ghordouyi Milan, G.H., Saeidi Garaghani., 2014. Investigating the effect of livestock grazing on vegetation changes (case study: pastures of Mako city). Quarterly Journal of Applied Research in Animal Sciences 3(12), 65-72.
Vali, A. A., Ramesht, M. H., Seif, A., Ghazavi, R., 2012. An assessment of the artificial neural networks technique to geomorphologic modeling sediment yield (case study Samandegan River system). Geography and Environmental Planning (University of Isfahan), 22, pp. 5-9. (In Persian).
Wang, Y., Mitchell, B. R., Nugranad-Marzilli, J., Bonynge, G., Zhou, Y., Shriver, G., 2009. Remote sensing of land-cover change and landscape context of the National Parks: a case study of the Northeast Temperate Network. Remote Sensing of Environment 113(7), 1453-1461.
Yaghmaei, L., Jafari, R., Soltani, S., Bashari, H. and Jahanbazi, H., 2016. The effect of human activities on the deterioration of forest and pasture vegetation using remote sensing (case study: Barez region, Chaharmahal and Bakhtiari province). The second international conference on landscape ecology, Isfahan University of Technology, Isfahan, pp: 1-11. (In Persian).
Zare Chahouki, M.A., Khalasi Ahvazi, L., Azarnivand, H., 2014. Modeling the distribution of plant species based on soil and topography factors using the logistic regression method in the pastures of East Semnan. Pasture and Watershed Journal (Iranian Natural Resources Magazine) 67(1), 45-59 (In Persian).
Zhang, H., Lei, S. L., 2012. A Structural Model of Residents’ Intention to Participate in Ecotourism: The Case of a Wetland Community. Tourism Management 33(4), 916-925.