Journals / lnternational Journal of Geography and Geography Education / 2022 / Sayı: 47

Determination of erosion susceptibilities of soils formed on the periglacial landforms of mount Ilgar and its estimation using artificial neural network (ANN)

Ilgar Dağı periglasyal şekilleri üzerinde oluşmuş toprakların erozyon duyarlılıklarının belirlenmesi ve yapay sinir ağı (YSA) ile tahmin edilmesi

Pages
258–279
Publication Date
2022-09-30
DOI
—
🏛️Bibliographic metadata and full text access for this article are provided via DergiPark.
DergiPark Record ↗
✨

AI Summary & Key Takeaways

AI Insight
⚡ TL;DR(Too Long; Didn't Read)

The results show that the high organic matter content of the soils causes the crust formation in the soils, thus keeping the physical degradation at very low levels; it was observed that the high sand content caused the SSI and DO values to be high.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:Periglacial landforms are formations that develop depending on the climatic conditions of the past period and show alteration under today's climatic conditions.
📊
Key Findings & Data:Mount Ilgar (2918 m a.s.l.), located on the Lesser Caucasus (4090 m a.s.l.) in Northeastern Anatolia, is among the important points where the landforms are distributed.
💡
Conclusion & Impact:The results show that the high organic matter content of the soils causes the crust formation in the soils, thus keeping the physical degradation at very low levels; it was observed that the high sand content caused the SSI and DO values to be high.
🔬Design:Research Article
📍Scope:25 sample
⚙️Variables:Periglasyal şekiller · erodobilite · yapay sinir ağı (YSA)

Abstract

Periglacial landforms are formations that develop depending on the climatic conditions of the past period and show alteration under today's climatic conditions. These landforms are distributed in the high mountain areas of the low latitudes as well as the high latitudes of the Earth. Mount Ilgar (2918 m a.s.l.), located on the Lesser Caucasus (4090 m a.s.l.) in Northeastern Anatolia, is among the important points where the landforms are distributed. The geology of Mount Ilgar, which has the appearance of a typical volcanic cone, is composed of Upper Miocene and Lower Pliocene aged basalt, tuff and agglomerate, while Pleistocene aged andesites form the summits. Periglacial landforms consisting of non sorted steps, mud circles and stony earth circles are observed on the slopes of parasite cones called Öküzkoku and Mısıkan of Mount Ilgar. In this study, it was aimed to (1) determine the physico-chemical properties of soils developed on the periglacial landforms of Mount Ilgar and (2) estimate various erosion susceptibility parameters (Structural stability index-SSI, dispersion ratio-DR and crust formation-CF). For this purpose, the physico-chemical properties of the soils were determined by analyzing 25 sample data, collected from the field. Erosion susceptibility parameters (SSI, DR, CF) were estimated by artificial neural network (ANN) by using the soil properties as input. The results show that the high organic matter content of the soils causes the crust formation in the soils, thus keeping the physical degradation at very low levels; it was observed that the high sand content caused the SSI and DO values to be high. In addition, the highest erodibility factor estimated by ANN was CF with 82%.

Özet

Periglasyal şekiller, geçmiş dönem iklim koşullarına bağlı olarak gelişen ve günümüz iklim koşulları altındada devinim gösteren oluşumlardır. Bu şekiller, Dünya’nın yüksek enlemlerinin yanı sıra alçak enlemlerinin yüksek dağlık alanlarında da yayılış göstermektedir. Kuzeydoğu Anadolu’da, Küçük Kafkaslar (4090 m) üzerinde yer alan Ilgar Dağı (2918 m) da söz konusu periglasyal şekillerin dağılış gösterdiği önemli noktalar arasındadır. Tipik bir volkan konisi görünümünde olan Ilgar Dağı’nın jeolojisini,temelde Üst Miosen ve Alt Pliosen yaşlı bazalt, tüf ve aglomera oluştururken, zirveler bölümünü ise Pleistosen yaşlı andezitler meydana getirmektedir. Ilgar Dağı’nın Öküzkoku ve Mısıkanadlı parazit konilerinin yamaçlarında girland, çember ve taş kümelerinden oluşan periglasyal şekiller görülmektedir. Bu çalışmada, (1) Ilgar Dağı periglasyal şekilleri üzerinde gelişen toprakların fiziko-kimyasal özelliklerinin belirlenmesi ve (2) bazı erozyon duyarlılık parametrelerinin (Strüktür stabilite indeksi-SSI, dispersiyon oranı-DO ve kabuk oluşumu-CF) tahmin edilmesi amaçlanmıştır. Bu amaçla sahadan alınan 25 adet örneklem verisi analiz edilerek toprakların fiziko-kimyasal özellikleri saptanmıştır. Söz konusu toprak özellikleri girdi olarak kullanılarak, erozyon duyarlılık parametreleri (CF, DO, SSI) yapay sinir ağı (YSA) ile tahmin edilmiştir. Bulgular, toprakların organik madde içeriklerinin yüksek olması, topraklarda kabuk oluşumuna dolayısıyla da fiziksel bozunumun oldukça düşük düzeylerde kalmasına neden olurken; kum oranının yüksek olmasının ise SSI ve DO değerinin de yüksek olmasına neden olduğu görülmüştür. Ayrıca YSA ile tahmin edilen yüksek erodobilite faktörü % 82 ile CF olmuştur.

🔖

Cite This Article

DEDE, V., DENGİZ, O., TURAN, İ. D., ZORLU, K., PACCİ, S., SERİN, S. (2022). Determination of erosion susceptibilities of soils formed on the periglacial landforms of mount Ilgar and its estimation using artificial neural network (ANN). lnternational Journal of Geography and Geography Education, Sayı: 47, 258–279. https://ajindex.com/articles/719606

📄 Full Text PDF Viewer

📄

PDF görüntüleyici hazırlanıyor...

References (10)

  1. Abbot, J., & Marohasy, J. (2012). Application of artificial neural Networks to rainfall forecasting in Queensland, Australia. Adv.Atmos. Sci., 29, 717-730. https://doi.org/10.1007/s00376-012-1259-9
  2. Acheampong, A. O., & Boateng, E. B. (2019). Modelling carbon emissions intensity: Application of artificial neural network. J. Clean. Prod., 225, 833-856. https://doi.org/10.1016/j.jclepro.2019.03.352
  3. Alaboz, P., Dengiz, O., Demir, S., & Şenol, H. (2021). Digital mapping of soil erodibility factors based on decision tree using geostatistical approaches in terrestrial ecosystem. Catena, 207-105634. https://doi.org/10.1016/j.catena.2021.105634
  4. Alexakis, D. D., Tapoglou, E., & Vozinaki, A.E.K. (2019). Integrated use of satellite remote sensing, artificial neural networks, fileds pectroscopy, and GIS in estimating crucial soil parameters in terms of soil erosion. Remote Sens., 11(9), 1106. https://doi.org/ 10.3390/rs11091106 Almeida, C. M., Gleriani, J. M., & Castejon, E. F. (2008). Using neural networks and cellular automata for modelling intra-urban land use dynamics. Int. J. Geogr. Inf. Sci., 22(9), 943–963. https://doi.org/10.1080/13658810701731168
  5. Aşkın, T., Türkmen F., & Tarakçıoğlu, C. (2016). Ordu ili merkez ilçe topraklarında erozyon riskinin jeoistatistiksel tekniklerle değerlendirilmesi. Toprak Bilimi ve Bitki Besleme Dergisi, 4(2) 69-75.
  6. Bajracharya, R. M., Elliot, W. J., & Lal, R. (1992). Interrill erodibility of some Ohio soils based on field rainfall simulation. Soil Science Society of America Journal, 56, 267-272.
  7. Barthes, B., & Roose, E. (2002). Aggregate stability as an indicator of soil susceptibility to runoff and erosion; validation at several levels. Catena, 47(2), 133-149. https://doi.org/10.1016/S0341-8162(01)00180-1
  8. Bennett, H. H. (1955). Elements of soil conservation. (2.ed.) New York, McGraw-Hill, 358p. Bilgili, M. (2011). The use of artificial neural networks for forecasting the monthly mean soil temperatures in Adana. Turkey. Turkish J. Agric. For., 35, 83-93. https://doi.org/10.3906/tar-1001-593
  9. Bissonnais, Y., Bruand, A., & Jamagne, M. (2007). Laboratory experimental study of soil crusting: Relations between aggregate breakdown mechanisms and crust structure. Catena, 16, 377- 392. Blake, G. R., & Hartge, K. H. (1986). Bulk density. In A. Klute (Eds.), Methods of soil analysis: Part 1 Physical and mineralogical methods, (pp. 363-375).
  10. SSSA Book Series. Bose, B. K. (1994). Expert-system, fuzzy-logic, and neural-network applications in po