Ilgaz Dağı Milli Parkı Doğal Çam Orman Arazilerinin Çölleşme Risk Değerlendirmesinde Bulanık-AHP Yaklaşımı ve Yapay Zekâ Kullanımı

Year 2023, Volume: 10 Issue: 1, 75 - 90, 14.04.2023

Orhan Dengiz , Muhammet Emin Saflı , Sena Pacci

https://doi.org/10.19159/tutad.1238402

Cited By: 1

Abstract

Bu çalışmanın amacı, çam ormanlarıyla kaplı alanların çölleşme risk değerlendirmesinde Akdeniz Avrupası için Çölleşme Gösterge Sistemi (DIS4ME) yaklaşımında ele alınan indikatörleri dikkate alarak, Ilgaz Dağı Milli Park sınırları içerisinde doğal çam orman arazilerinin çölleşme risk değerlendirmesini yapmaktır. Çölleşme risk değerlendirmesinde 8 indikatör (yağış, kuraklık, toprak bünyesi, taşlılık, bitki örtüsü-kapalılık, eğim, derinlik ve bakı) ele alınmıştır. Fakat, DIS4ME yaklaşımından farklı olarak bu çalışmada ele alınan indikatör indeks değerleri modelden birebir alınmayıp, Bulanık-Analitik Hiyerarşik Süreç (Bulanık-AHP) yaklaşımı ile daha da hassaslaştırılmıştır. Toprakların temel fiziko-kimyasal özellerini belirlemek amacıyla alandan 151 toprak örneği alınmıştır. Ilgaz Dağı Milli Park alanı içerisinde çölleşme risk değerlendirmesi yönünden alanda dağılım gösteren toprakların büyük bir çoğunluğunun çölleşme riski altında olduğu belirlenmiştir. Ayrıca, çalışmada elde edilen model sonuçları yapay sinir ağları ile tahmin edilmiştir. Elde edilen sonuçlara göre, çölleşme riskinin belirlenmesinde % 99 doğrulukla tahmin edilebilir olduğu belirlenmiştir.

Keywords

Çölleşme, bulanık-AHS, yapay zeka, Ilgaz Dağı Mili Parkı

Fuzzy-AHP Approach and Artificial Intelligence Use in The Desertification Risk Assessment of Natural Pine Forest Lands of Ilgaz Mountain National Park in Türkiye

Abstract

The aim of this study is to conduct a desertification risk assessment of natural pine forest lands within the boundaries of Ilgaz Mountain National Park, taking into account the indicators considered in the Desertification Indicator System for Mediterranean Europe (DIS4ME) approach to the desertification risk assessment of areas covered with pine forests. Eight indicators (rainfall, drought, soil texture, stoniness, vegetation cover, slope, depth and aspect) were considered in the desertification risk assessment. However, unlike the DIS4ME approach, the indicator index values considered in this study were not taken directly from the model and were more refined with the Fuzzy-Analytic Hierarchical Process (Fuzzy-AHP) approach. To determine the basic physico-chemical properties of the soils, 151 soil samples were taken from the study area. In terms of desertification risk assessment of soils within the Ilgaz Mountain National Park area, it has been determined that most of the area is under desertification risk. In addition, the model results obtained in the study were estimated with artificial neural networks (ANN). According to the results obtained, it has been determined that the risk of desertification can be estimated with 99% accuracy in determining.

Keywords

Desertification, fuzzy-AHP, artificial intelligence, Ilgaz Mountain National Park

References

• Abdel-Kader, M.G., Dugdale, D., 2001. Evaluating investments in advanced manufacturing technology: A fuzzy set theory approach. The British Accounting Review, 33(4): 455-489.
• Akbari, M., Memarian, H., Neamatollahi, E., Jafari Shalamzari, M., Alizadeh Noughani, M., Zakeri, D., 2021. Prioritizing policies and strategies for desertification risk management using MCDM-DPSIR approach in northeastern Iran. Environment, Development and Sustainability, 23: 2503-2523.
• Aksoy, B.R., 2016. MEDALUS modeli ile arazi degradasyonu ve çölleşme riskinin belirlenmesi örnek çalışma: İnebolu Havzası. Yüksek Lisans Tezi, Ondokuz Mayıs Üniversitesi Fen Bilimleri Enstitüsü, Samsun.
• Anonim, 2009. Ilgaz Dağı Milli Parkı Uzun Devreli Gelişme Planı. Çevre ve Orman Bakanlığı, Doğa Koruma ve Milli Parklar Genel Müdürlüğü, Milli Parklar Dairesi Başkanlığı, Ankara.
• Anonymous, 1992. Procedures for Collecting Soil Samples and Methods of Analysis for Soil Survey. Soil Survey Invest. Rep. I, U.S. Government Print Office, Washington DC, USA.
• Anonymous, 2004. Desertification Indicator System for Mediterranean Europe (DIS4ME). European Commission, Contract EVK2-CT-2001-00109, (http://www.kcl.ac.uk/projects/desertlinks/), (Accessed: 23.12.2022).
• Bellman, R.E., Zadeh, L.A., 1970. Decision-making in a fuzzy environment. Management Science, 17(4): B-141.
• Blake, G.R., Hartge, K.H., 1986. Bulk density. In: A. Klute (Ed.), Methods of Soil Analysis, Part 1: Physical and Mineralogical Methods, American Society of Agronomy, Inc. Soil Science Society of America, pp. 363-375.
• Bouyoucos, G.J., 1962. Hydrometer method improved for making particle size analyses of soils 1. Agronomy Journal, 54(5): 464-465.
• Celilov, C., Dengiz, O., 2019. Erozyon duyarlılık parametrelerinin farklı enterpolasyon yöntemleriyle konumsal dağılımlarının belirlenmesi: Türkiye, Ilgaz Milli Park toprakları. Türkiye Tarımsal Araştırmalar Dergisi, 6(3): 242-256.
• Chang, D.Y., 1996. Applications of the extent analysis method on fuzzy AHP. European Journal of Operational Research, 95(3): 649-655.
• Dağdeviren, M., 2007. Bulanık analitik hiyerarşi prosesi ile personel seçimi ve bir uygulama. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 22(4): 791-799.
• Dağdeviren, M., Akay, D., Kurt, M., 2004. İş değerlendirme sürecinde analitik hiyerarşi prosesi ve uygulaması. Gazi Üniversitesi Mühendislik Mimarlık Fakültesi Dergisi, 19(2): 131-138.
• Dastorani, M., 2022. Application of fuzzy-AHP method for desertification assessment in Sabzevar area of Iran. Natural Hazards, 112(1): 187-205.
• Dede, V., Demirağ Turan, İ., Dengiz, O., Serin, S., Pacci, S., 2022. Effects of periglacial landforms on soil erosion sensitivity factors and predicted by artificial ıntelligence approach in mount Cin, NE Turkey. Eurasian Soil Science, 55(12): 1857-1870.
• Deng, H., 1999. Multicriteria analysis with fuzzy pairwise comparison. International Journal of Approximate Reasoning, 21(3): 215-231.
• El Alfy, Z., Elhadary, R., Elashry, A., 2010. Integrating GIS and MCDM to deal with landfill site selection. International Journal of Engineering & Technology, 10(6): 32-42.
• Gao, J., Wang, H., 2019. Temporal analysis on quantitative attribution of karst soil erosion:A case study of a peak-cluster depression basin in Southwest China. Catena, 172: 369-377.
• Haykin, S., 1999. Neural networks: A guided tour. In: N.K. Sinha and M.M. Gupta (Eds.), Soft Computing and Intelligent Systems: Theory and Applications, Academic Press, USA, pp. 71-80.
• Imbrenda, V., Coluzzi, R., Di Stefano, V., Egidi, G., Salvati, L., Samela, C., Lanfredi, M., 2022. Modeling spatio-temporal divergence in land vulnerability to desertification with local regressions. Sustainability, 14(17): 10906.
• Jackson, M.L., 1958. Soil Chemical Analysis. Verlag: Prentice Hall, Inc., Englewood Cliffs, NJ.
• Jafari, R., Abedi, M., 2021. Remote sensing-based biological and nonbiological indices for evaluating desertification in Iran: Image versus field indices. Land Degradation & Development, 32(9): 2805-2822.
• Jafari Shalamzari, M., Zhang, W., Gholami, A., Zhang, Z., 2019. Runoff harvesting site suitability analysis for wildlife in sub-desert regions. Water, 11(9): 1944.
• Kargın, M., 2010. Bulanık analitik hiyerarşi süreci ve ideal çözüme yakınlığa göre sıralama yapma yöntemleri ile tekstil sektöründe finansal performans ölçümü. Celal Bayar Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 8(1): 195-216.
• Kosmas, C., Ferrara, A., Briassouli, H., Imeson, A., 1999. Methodology for mapping environmentally sensitive areas (ESAs) to desertification. In: C. Kosmas, M. Kirkby and N. Geeson (Eds.), The Medalus Project: Mediterranean Desertification and Land Use, Manual on Key Indicators of Desertification and Mapping Environmentally Sensitive Areas to Desertification, EUR, 18882, pp. 31-47.
• Kuang, Q., Yuan, Q.Z., Han, J.C., Leng, R., Wang, Y.S., Zhu, K.H., Lin, S., Ren, P., 2020. A remote sensing monitoring method for alpine grasslands desertification in the eastern Qinghai-Tibetan Plateau. Journal of Mountain Science, 17(6): 1423-1437.
• Liou, T.S., Wang, M.J.J., 1992. Ranking fuzzy numbers with integral value. Fuzzy Sets and Systems, 50(3): 247-255.
• Malczewski, J., Rinner, C., 2015. Development of GIS-MCDA. In: J. Malczewski and C. Rinner (Eds.), Multicriteria Decision Analysis in Geographic Information Science, New York: Springer, pp. 55-77.
• McLean, E.O., 1982. Soil pH and lime requirement. In: A.L. Page, R.H. Miller and D.R. Keeney (Eds.), Methods of Soil Analysis, Part 2: Chemical and Microbiological Properties, (2nd Edition), Agronomy, pp. 199-223.
• Mutlu, N., 2015. Yarı kurak bir bölgede çölleşmenin izlenmesini sağlayacak göstergelerinin belirlenmesi ve haritalanması. Doktora Tezi, Gazi Osmanpaşa Üniversitesi Fen Bilimleri Enstitüsü, Tokat.
• Odabas, M.S., Kayhan, G., Ergun, E., Senyer, N., 2016. Using artificial neural network and multiple linear regression for predicting the chlorophyll concentration index of Saint John’s Wort Leaves. Communications in Soil Science and Plant Analysis, 47(2): 237-245.
• Pacci, S., Kaya, N.S., Turan, İ.D., Odabas, M.S., Dengiz, O., 2022. Comparative approach for soil quality index based on spatial multi-criteria analysis and artificial neural network. Arabian Journal of Geosciences, 15(1): 1-15.
• Pala, O., 2016. Bulanık analitik hiyerarşi prosesi ve meslek seçiminde uygulanması. Dokuz Eylül Üniversitesi Sosyal Bilimler Enstitüsü Dergisi, 18(3): 427-445.
• Pishyar, S., Khosravi, H., Tavili, A., Malekian, A., Sabourirad, S., 2020. A combined AHP-and TOPSIS-based approach in the assessment of desertification disaster risk. Environmental Modeling & Assessment, 25(2): 219-229.
• Rhoades, J.D., 1993. Electrical conductivity methods for measuring and mapping soil salinity. Advances in Agronomy, 49: 201-251.
• Saaty, T.L., 1977. A scaling method for priorities in hierarchical structures. Journal of Mathematical Psychology, 15(3): 234-281.
• Salman, M.S., Kukrer, O., Hocanin, A., 2017. Recursive inverse algorithm: Mean-square-error analysis. Digital Signal Processing, 66: 10-17.
• Silva, J., Moura, G., Lopes, P.M.O., França-e-Silva Ê, Ortiz P., Silva, D., Silva, M., Guedes, R., 2020. Spatial-temporal monitoring of the risk of environmental degradation and desertification by remote sensing in a Brazilian semiarid region. Revista Brasileira de Geografia Física, 13(2): 544-563.
• Turan, İ.D., Dengiz, O., Özkan, B., 2019. Spatial assessment and mapping of soil quality index for desertification in the semi-arid terrestrial ecosystem using MCDM in interval type-2 fuzzy environment. Computers and Electronics in Agriculture, 164: 104933.
• Türkeş, M., 2012. Türkiye’de gözlenen ve öngörülen iklim değişikliği, kuraklık ve çölleşme. Ankara Üniversitesi Çevrebilimleri Dergisi, 4(2): 1-32.
• Türkeş, M., Öztaş, T., Tercan, E., Erpul, E., Karagöz, A., Dengiz, O., Doğan, O., Şahin, K., Avcıoğlu, B., 2020. Desertification vulnerability and risk assessment for Turkey via ananalytical hierarchy process model. Land Degradation and Development, 31(2): 205-214.
• Uzuner, C., Dengiz, O., 2020. Desertification risk assessment in Turkey based on environmentally sensitive areas. Ecological Indicators, 114: 106295.
• Van Laarhoven, P.J.M., Pedrycz, W., 1983. A fuzzy extension of Saaty's priority theory. Fuzzy Sets and Systems, 11(1-3): 229-241.
• Van Wambeke, A.R., 2000. The Newhall Simulation Model for Estimating Soil Moisture & Temperature Regimes. Department of Crop and Soil Sciences, U.S. Departmanet of Agriculture, Ithaca, N.Y. Washington, DC.
• Wang, X., Chen, F., Hasi, E., Li, J., 2008. Desertification in China: an assessment. Earth-Science Reviews, 88(4): 188-206.
• Warren, A., 2002. Land degradation is contextual. Land Degradation & Development, 13(6): 449-459.
• Wijitkosum, S., 2016. The impact of land use and spatial changes on desertification risk in degraded areas in Thailand. Sustainable Environment Research, 26(2): 84-92.
• Wilding, L.P., 1985. Spatial variability: it’s documentation, accommodation and implication to soil surveys. In: D.R. Nielsen and J. Bouma (Eds.), Soil Spatial Variability, Pudoc, Wageningen, The Netherlands, p. 166-194.
• Zakerinejad, R., Masoudi, M., 2019. Quantitative mapping of desertification risk using the modified MEDALUS model: a case study in the Mazayejan Plain, Southwest Iran. Acta Universitatis Carolinae Geographica, 54(2): 232-239.