مدل‌سازی رویشگاه بالقوه Trigonella elliptica با استفاده از متغیرهای محیطی و تکنیک‌ یادگیری ماشینی در مراتع استان یزد

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه احیاء مناطق خشک و کوهستانی، دانشکده منابع طبیعی، دانشگاه تهران، کرج، ایران

2 اداره کل منابع طبیعی و آبخیزداری استان یزد، یزد، ایران

چکیده

رویشگاه بالقوه گیاه مرتعی شنبلیله شیرازی (Trigonella elliptica) در اراضی مرتعی استان یزد با استفاده از الگوریتم جنگل تصادفی به‌عنوان یکی از مدل‌های پیشرفته یادگیری ماشینی مدل‌سازی شد. از 11 متغیر کاربری اراضی، شاخص شوری خاک، بارندگی، حداقل و حداکثر دما، تبخیر، ارتفاع، جهت و درجة شیب، فاصله تا آبراهه و شاخص خیسی توپوگرافی و همچنین موقعیت مکانی حضور شنبلیله شیرازی استفاده شد. از مجموع 103 موقعیت مکانی ثبت‌شده به‌عنوان نقاط حضور این گیاه، به‌طور تصادفی 70 درصد برای آموزش مدل و 30 درصد برای آزمون مدل توسعه داده شده استفاده شد. به‌منظور اعتبارسنجی و آزمون مدل، از مساحت زیر منحنی مشخصه عملکرد (AUC_ROC) و جهت تعیین اهمیت متغیرهای محیطی مورد استفاده در مدل‌سازی از روش جک‌نایف (Jackknife) استفاده شد. نتایج ارزیابی مدل با استفاده از منحنی ROC (AUC>0/8)، عملکرد خیلی خوب را نشان داد. همچنین آماره‌های خطا شامل صحت، دقت مدل‌سازی، مقادیر اریبی، احتمال آشکارسازی و نرخ هشدار اشتباه به‌ترتیب 0/9، 0/79، 1، 0/93 و 0/04 را نشان دادند که بیان‌گر عملکرد خوب مدل است. نتایج تعیین اهمیت متغیرها نشان داد که به‌ترتیب عامل درجة شیب، و سپس ارتفاع و شاخص خیسی توپوگرافی نسبت به بقیة عوامل در تعیین رویشگاه بالقوه شنبلیله شیرازی اهمیت بیشتری دارند. نقشة حاصل از پیش‌بینی رویشگاه بالقوه شنبلیله شیرازی می‌تواند به‌عنوان اطلاعات دقیق به‌منظور احیاء رویشگاه‌های تخریب شده این گیاه مرتعی در استان یزد مفید واقع‌شده و مورد توجه بخش اجرایی قرار گیرد.

کلیدواژه‌ها

عنوان مقاله [English]

Spatial modeling of Trigonella elliptica potential habitat using environmental variables and machine learning technique in the Rangelands of Yazd province

نویسندگان [English]

  • Ehsan Moradi 1
  • Ali Tavili 1
  • Mohsen Asadollahi 1
  • Mohammad Reza Ahmadi Roknabadi 2

1 Department of Reclamation of Arid and Mountainous Regions, Faculty of Natural Resources, University of Tehran, Karaj, Iran

2 Bureau of Natural Resources and Watershed Management, Yazd Province, Yazd, Iran

چکیده [English]

Identifying plant species distribution and potential habitats which are under degraded in the rangelands ecosystem is an essential challenge in natural resource science. Performance these studies will support rangeland conservation, restoration, and management measures. In this study, the potential habitat of Trigonella elliptica in rangeland of Yazd province was modeled using one of the advanced machine learning models (Random Forest algorithm). We used 11 variables including land use, soil salinity index, rainfall, minimum and maximum temperature, evaporation, elevation, aspect and degree of slope, distance from river, and topographic wetness index, as well as 103 presence points of T. elliptica to improve the model. 70 % of the T. elliptica presence points were randomly selected for model training and 30% of them for model testing. In order to evaluate the model and the importance of environmental variables were used the area under the receiver operator characteristic (ROC) curve and the Jackknife methods respectively. The evaluation results of the model using the ROC curve (AUC> 0.8) showed a very good performance. Error statistics including Accuracy, Precision, Bias, Probability of Detection and False Alarm Ratio showed 0.9, 0.79, 1, 0.93 and 0.04, respectively, which demonstrate the good performance of the model to prediction. In addition, the results of determining the importance of variables showed that the slope degree and following it, elevation and topographic wetness index are more important than other variables in determining the potential habitat of T. elliptica. The map obtained from the prediction of the potential habitat of T. elliptica can be very useful as accurate information in the rangeland management in order to Reclamation the destroyed habitats of this rangeland plant in Yazd province and be highly regarded by rangeland managers.

کلیدواژه‌ها [English]

  • Spatial modeling
  • Trigonella elliptica
  • Rangelands of Yazd province
  • Random Forest
Acharya, S., Srichamroen, A., Basu, S., Ooraikul, B., Basu, T., 2006. Improvement in the nutraceutical properties of fenugreek (Trigonella foenum-graecum L.). Journal of Science and Technology 28, 1-9.
Arjmandi, Z., Asadi Zarch, M.A., Hosseyni, S.Z., Ekhtesasi, M.R., 2021. Forecasting Drought in Arid Regions Using Global Climate Models: A Case Study of Yazd Province, Iran. Desert Ecosystem Engineering Journal 10(32), 97-112.
Asadi Zarch, M.A, 2017. Analyzing climate change effects on drought occurrence in Yazd province, Iran. Iranian Scientific Association of Desert Management and Control. No. 9. pp: 74-90.
Asch, J., 2021. Topographic controls of drought impact on Swedish primary forests. Student thesis series INES.
Atkinson, P.M., 2005. Sub-pixel target mapping from soft-classified, remotely sensed imagery. Photogrammetric Engineering & Remote Sensing 71(7), 839-846.
Baghestani Meybodi, N., Mirokili, S., Zarezadeh, A., 2010. Introduction of flora, biological form and geographical distribution of steppe range plants (Case study: Khoy-Newk watershed in Yazd province). Renewable Natural Resources Research 1(2), 43-58.
Bakhshi, J., Javadi, S.A., Tavili, A., Arzani, H., 2020. Study on the effects of different levels of grazing and exclosure on vegetation and soil properties in semi-arid rangelands of Iran. Acta Ecologica Sinica 40(6), 425-431.
Brinkmann, K., Patzelt, A., 2010. Rangeland Vegetation on Al Jabal Al Akhdar a Key Resource of Oasis Settlements. Oasis of Oman, pp: 42-46.
Chen, W., Zhang, S., Li, R., Shahabi, H., 2018. Performance evaluation of the GIS-based data mining techniques of best-first decision tree, random forest, and naïve Bayes tree for landslide susceptibility modeling. Science of the Total Environment 644, 1006-1018.
Choubin, B., Abdolshahnejad, M., Moradi, E., Querol, X., Mosavi, A., Shamshirband, S., Ghamisi, P., 2020. Spatial hazard assessment of the PM10 using machine learning models in Barcelona, Spain. Science of the Total Environment 701, 134474.
Choubin, B., Moradi, E., Golshan, M., Adamowski, J., Sajedi-Hosseini, F., Mosavi, A., 2019a. An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Science of the Total Environment 651, 2087-2096.
Choubin, B., Mosavi, A., Alamdarloo, E.H., Hosseini, F.S., Shamshirband, S., Dashtekian, K., Ghamisi, P., 2019b. Earth fissure hazard prediction using machine learning models. Environmental Research 179, 108770.
Cutler, D.R., Edwards Jr, T.C., Beard, K.H., Cutler, A., Hess, K. T., Gibson, J., Lawler, J.J., 2007. Random forests for classification in ecology. Ecology 88(11), 2783-2792.
De Clercq, E., Leta, S., Estrada-Peña, A., Madder, M., Adehan, S., Vanwambeke, S., 2015. Species distribution modelling for Rhipicephalus microplus (Acari: Ixodidae) in Benin, West Africa: Comparing datasets and modelling algorithms. Preventive Veterinary Medicine 118(1), 8-21.
De Smith, M.J., Goodchild, M.F., Longley, M.A., 2007. Geospatial Analysis: A Comprehensive Guide to Principles, Techniques and Software Tools. Matador Press, Leicester.
Deng, T., Chen, X., Chuvieco, E., Warner, T., Wilson, J. P., 2007. Multi-scale linkages between topographic attributes and vegetation indices in a mountainous landscape. Remote Sensing of Environment 111, 122-134.
Duan, X., Li, J., Wu, S., 2022. MaxEnt Modeling to Estimate the Impact of Climate Factors on Distribution of Pinus densiflora. Forests 13(3), 402.
Ebrahimi, M., Khosravi, H., Rigi, M., 2016. Short-term grazing exclusion from heavy livestock rangelands affects vegetation cover and soil properties in natural ecosystems of southeastern Iran. Ecological Engineering 95, 10-18.
Elith, J., Leathwick, J. R., 2009. Species distribution models: ecological explanation and prediction across space and time. Annual Review of Ecology, Evolution, and Systematics 40, 677-697.
Emadodin, I., Bork, H. R., 2012. Degradation of soils as a result of long-term human-induced transformation of the environment in Iran: an overview. Journal of Land Use Science 7(2), 203-219.
Franklin, J., 2009. Mapping species distributions: spatial inference and prediction. Cambridge University Press, New York.
Gayen, A., Pourghasemi, H. R., 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.
Goetz, J. N., Brenning, A., Petschko, H., Leopold, P., 2015. Evaluating machine learning and statistical prediction techniques for landslide susceptibility modeling. Computers & Geosciences 81, 1-11.
He, S., Wu, J., Wang, D., He, X., 2022. Predictive modeling of groundwater nitrate pollution and evaluating its main impact factors using random forest. Chemosphere 290, 133388.
Heydari Alamdarloo, E., Moradi, E., Abdolshahnejad, M., Fatahi, Y., Khosravi, H., da Silva, A. M., 2021. Analyzing WSTP trend: a new method for global warming assessment. Environmental Monitoring and Assessment 193(12), 1-15.
Hosseinzadeh, M.S., Farhadi Qomi, M., Naimi, B., Roedder, D., Kazemi, S. M., 2018. Habitat suitability and modelling the potential distribution of the Plateau Snake Skink Ophiomorus nuchalis (Sauria Scincidae) on the Iranian Plateau. North-Western Journal of Zoology.
Huettmann, F., Gottschalk, T., 2011. Simplicity, model fit, complexity and uncertainty in spatial prediction models applied over time: We are quite sure, aren’t we?. In Predictive species and habitat modeling in landscape ecology (pp. 189-208). Springer, New York, NY.
Karimiyan, A., 2005. Medicinal, aromatic, rangeland and rare plants of Kalmand Bahadoran and Bafgh protected areas in Yazd province. Journal of Environmental Science 31(37), 77-88.
Khanamani, A., Bameri Nejad, F., 2020. Locating Potential Sites for Species (Ammodendron persicum) in Southern Kerman province, Using AHP Method. Desert Ecosystem Engineering Journal 9(27), 67-78.
Khayrandish, H., Esmaeilpour, Y., Kamali, A.R., Zakeri, O., 2015. Locating suitable areas for mangrove afforestation in the Sirik habitat, Hormozgan Province. Journal of Aquatic Ecology 5(2), 112-123.
Lee, S., Kim, J. C., Jung, H. S., Lee, M. J., Lee, S., 2017. Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea. Geomatics, Natural Hazards and Risk 8(2), 1185-1203.
McCormick, K.M., Norton, R.M., Eagles, H.A., 2009. Phenotypic variation within a fenugreek (Trigonella foenum-graecum L.) germplasm collection. II. Cultivar selection based on traits associated with seed yield. Genetic Resources and Crop Evolution 56(5), 651-661.
Mehmud, S., Kalita, N., Roy, H., Sahariah, D., 2022. Species distribution modelling of Calamus floribundus Griff (Arecaceae) using Maxent in Assam. Acta Ecologica Sinica 42(2), 115-121.
Mi, C., Huettmann, F., Guo, Y., Han, X., Wen, L., 2017. Why choose Random Forest to predict rare species distribution with few samples in large undersampled areas? Three Asian crane species models provide supporting evidence. PeerJ 5, e2849.
Mohajane, M., Costache, R., Karimi, F., Pham, Q. B., Essahlaoui, A., Nguyen, H., Oudija, F., 2021. Application of remote sensing and machine learning algorithms for forest fire mapping in a Mediterranean area. Ecological Indicators 129, 107869.
Mokarram, M., Hojjati, M., Zarei, A.R., 2017. Using the attraction model in remote sensing to evaluation of topographic wetness index (TWI). Eco hydrology 4(1), 237-245.
Mokhtari, D., Ebrahimi, H., Salmani, S., 2019. Landslide risk modeling using stochastic forest algorithm (Case study: Tasuj plain catchment). Remote Sensing and GIS in Natural Resources 10 (3), 93-105.
Moradi, E., Abdolshahnejad, M., Hassangavyar, M.B., Ghoohestani, G., da Silva, A.M., Khosravi, H., Cerdà, A., 2021. Machine learning approach to predict susceptible growth regions of Moringa peregrina (Forssk). Ecological Informatics 62, 101267.
Mozaffarian, V., Mirvakili, M., Barzegari, G., 2000. Flora of Yazd. Yazd Publication Institute.
Onagh, M., 1994. Evaluation of production capacity and rangeland management using system GIS. Proceedings of the first national seminar on rangeland and rangeland management in Iran. August 25-27, p.2.
Park, N.W., 2015. Using maximum entropy modeling for landslide susceptibility mapping with multiple geoenvironmental data sets. Environmental Earth Sciences 73(3), 937-949.
Pham, Q.B., Kumar, M., Di Nunno, F., Elbeltagi, A., Granata, F., Islam, A.R.M., Anh, D.T., 2022. Groundwater level prediction using machine-learning algorithms in a drought-prone area. Neural Computing and Applications 1-23.
Pourghasemi, H. R., Kariminejad, N., Amiri, M., Edalat, M., Zarafshar, M., Blaschke, T., Cerda, A., 2020. Assessing and mapping multi-hazard risk susceptibility using a machine learning technique. Scientific Reports 10(1), 1-11.
Qarachorlu, M., Esfandiari, F., Dalal Oghli, A., 2018. Investigation of the role of geomorphological parameters in vegetation distribution using spatial regression analysis (Case study, Arasbaran watersheds: Tea, Ilgineh, Tea and Mardam-e-Tea). Geographical Space 18 (63), 225-248.
Ranjbar, M., Hajmoradi, Z., Karamian, R., 2014. Novelty in Trigonella sect. Ellipticae (Fabaceae) from Iran. Novon: A Journal for Botanical Nomenclature 23(2), 209-216.
Ranjbar, M., Karamian, R., Hajmoradi, Z., Joharchi, M.R., 2012. A revision of Trigonella sect. Ellipticae (Fabaceae) in Iran. Nordic Journal of Botany 30(1), 17-35.
Riyasat, M., Nasirzadeh, A., 2006. Evaluation of 2 perennial Trigonella (T. elliptica and T. tehranica) for forage quality improvement. Iranian Journal of Rangelands and Forests Plant Breeding and Genetic Research 14(4), 230-240.
Rodriguez, V., Ghimire, B., Rogan, J., Chica-Olmo, M., Rigol-Sánchez, J.P., 2012. An assessment of the effectiveness of a Random Forest classifier for land-cover classification. International Society for Photogrammetry and Remote Sensing 67, 9 -104
Schumann, G.P., Vernieuwe, H., De Baets, B., Verhoest, N.E.C., 2014. ROC-based calibration of flood inundation models. Hydrol. Process. 28(22), 5495–5502.
Sedghi, S., 2022. The Effect of Biomechanical Operations on Rangeland Vegetation (Case Study: Rangelands of Abarkooh, Yazd). Natural Ecosystems of Iran 12(4), 13-24.
Sharifian, S., Mortazavi, M.S., Mohebbi-Nozar, S. L., 2022. Modeling Present Distribution Commercial Fish and Shrimps Using MaxEnt. Wetlands 42(5), 1-9.
She, Y., Zhang, Z., Ma, L., Xu, W., Huang, X., Zhou, H., 2022. Vegetation attributes and soil properties of alpine grassland in different degradation stages on the Qinghai-Tibet Plateau, China: a meta-analysis. Arabian Journal of Geosciences 15(2), 1-22.
Sokolova, M., Japkowicz, N., Szpakowicz, S., 2006. Beyond accuracy, F-score and ROC: a family of discriminant measures for performance evaluation. Springer, Berlin, Heidelberg pp: 1015-1021.
Stafoggia, M., Bellander, T., Bucci, S., Davoli, M., de Hoogh, K., De'Donato, F., Gariazzo, C., Lyapustin, A., Michelozzi, P., Renzi, M., Scortichini, M., 2019. Estimation of daily PM10 and PM2. 5 concentrations in Italy, 2013–2015, using a spatiotemporal land use random-forest model. Environment international 124, 170–179.
Tadros, M.J., El-Shatnawi, M.D.K.J., Jaradat, R.Q., 2011. Growth, persistence and quality of Trigonella arabica Del. and Trigonella caelesyriaca Boiss. Grown in the semi-arid rangeland north of Jordan. Journal of Food, Agriculture & Environment 9(1), 389-393.
Talebi, A., Goudarzi, S., Pourghsemi, H., 2018. Investigation of the possibility of landslide hazard mapping using the Random Forest algorithm (Case study: Sardarabad Watershed, Lorestan Province). Journal of Natural Environmental Hazards 7(16), 45-64.
Tempa, K., Aryal, K.R., 2022. Semi-automatic classification for rapid delineation of the geohazard-prone areas using Sentinel-2 satellite imagery. SN Applied Sciences 4(5), 1-14.
Wu, C., Xiao, Q., McPherson, E.G., 2008. A method for locating potential tree-planting sites in urban areas: A case study of Los Angeles, USA. Urban Forestry & Urban Greening 7(2), 65-76.
Yadav, U., Moorthy, K., Baquer, N.Z., 2004. Effects of sodium-orthovanadate andTrigonella foenum-graecum seeds on hepatic and renal lipogenic enzymes and lipid profile during alloxan diabetes. Journal of Biosciences 29(1), 81-91.
Zhang, K., Wu, X., Niu, R., Yang, K., Zhao, L., 2017. The assessment of landslide susceptibility mapping using random forest and decision tree methods in the Three Gorges Reservoir area, China. Environmental Earth Sciences 76(11), 1-20.