Journals / Geosound / 2004 / Cilt: 0 - Sayı: 44-45

The artificial neural network model for estimating hydraulic conductivity of porous media

Sediment permeabilitelerinin hesaplanmasında yapay sinir ağları modeli

Journal
Geosound
Pages
45–56
Publication Date
2022-10-18
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 hydraulic conductivity results for gravel, sand and silt by using Artificial Neural Network model are in well accord with those obtained by equations.

📌 3 Key Takeaways

🎯
Objective & Hypothesis:A new equation for estimating the hydraulic conductivity of porous media is introduced by applying Artificial Neural Network methods on the data obtained from six most commonly used hydraulic conductivity equation.
📊
Key Findings & Data:Porosity (n), effective grain size $(d_{10})$ is taken as permeability variables.
💡
Conclusion & Impact:The hydraulic conductivity results for gravel, sand and silt by using Artificial Neural Network model are in well accord with those obtained by equations.
🔬Design:Modeling & Simulation
📍Scope:Comprehensive Sample
⚙️Variables:Domain Parameters

Abstract

A new equation for estimating the hydraulic conductivity of porous media is introduced by applying Artificial Neural Network methods on the data obtained from six most commonly used hydraulic conductivity equation. Porosity (n), effective grain size $(d_{10})$ is taken as permeability variables. Hydraulic conductivity data produced with those variables in each equation forms Artificial Neural Network data. Thus, a hydraulic conductivity result is introduced in Artificial Neural Network method. In Artificial Neural Network, Extended Delta Bar Delta is used as Multi- Layer Perceptrons and learning algorithm. The hydraulic conductivity results for gravel, sand and silt by using Artificial Neural Network model are in well accord with those obtained by equations.

Özet

En çok kullanılan altı adet geçirimlilik denklemlerinden üretilen veriler, yapay sinir ağlarına (YSA) uygulanarak, yeni bir geçirimlilik değeri bulunmuştur. Geçirimlilik değişkenleri olarak gözeneklilik (n) ve efektif tane çapı $(d_{10})$ alınmıştır. Her denklemde bu parametrelere bağlı olarak üretilen geçirimlilik değerleri yapay sinir ağlarının verilerini oluşturmaktadır. Böylece altı değişik denklem YSA da birleştirilerek tek bir geçirimlilik sonucu grafiksel olarak sunulmuştur. Yapay sinir ağında Çok Katmanlı Ağ Yapısı (Multi - Layer Perceptrons) ve öğrenme algoritması olarak Genişletilmiş Delta Bar Delta (GDBD) kullanılmıştır. Yapay sinir ağı modeli kullanılarak çakıl, kum ve şilt için ayrı ayrı elde edilen geçirimlilik sonuçları denklemsel geçirimlilik sonuçlarıyla oldukça iyi uyumluluk göstermektedir.

🔖

Cite This Article

KANSUN, G., GÜLTEKİN, S. S., BAYRAM, A. F. (2022). The artificial neural network model for estimating hydraulic conductivity of porous media. Geosound, Cilt: 0 - Sayı: 44-45, 45–56. https://ajindex.com/articles/524893

References (6)

  1. Barr, D.W. 2001. Coefficient of permeability determined by measurable parameters. Ground Water 39: 3: 356-361.
  2. Bear, J. 1972.
  3. Dynamics of fluids in porous media, American Elsevier. New York: USA. Carman, P.C. 1937. Fluid flow through a granular bed. Trans. Inst. Chem. Engnrs. 15:150-156.
  4. Domenico, P. A. ve Shwartz, F. W., 1990, Physical and chemical hydro geology: John Wiley & Sons, New York. Haykin, S. 1994. Neural Networks: A Comprehensive Foundation. Macmillan College Publishing Company, New York: USA. Hazen, A. 1911. Discussion: Dams on Sand Foundations. Transactions, American Society of Civil Engineers 73: 199. Kozeny, J. 1927. Über kapillare leitung des Wassers in boden. Sitzungsber Akad. Wiss.Wien. 136:271-306.
  5. Kresic, N., 1997, Quantitative solution in hydrogeology and groundwater modeling: CRC Lewis Publishers, New York, 461 p. Minai, A.A. ve Williams, R.D. 1990. Acceleration of Backpropagation Through Learning Rate and Momentum Adaptation. Int. Joint Conf. on Neural Networks 1: 676-679. NeuralWare Handbook. 1996. Neural Computing: A Technology Handbook for Professional IIIPLUS and NeuralWorks Explorer. NeuralWare, Inc., Technical Publications Group, Pittsburgh: USA. Rumelhart, D.E. ve McClelland, J. L. 1986. Parallel Distributed Processing 1. The MIT Press, Cambridge: Massachusetts. Rumelhart, D.E., Hinton, G.E. ve Williams, R.J.,1986, Learning Internal Representations by Error Propagation, Parallel Distributed Processing, Vol.1: Foundations, D.E. Rumelhart ve J.L. McClelland (Eds.), MIT Press,
  6. Cambridge, MA, pp 318 - 362. Sağıroğlu, Ş., Güney, K. and Erler, M., 1998, Neural Design of Rectangular Microstrip Antennas, Kayseri İkinci Havacılık Sempozyumu, Prof. Dr. Veysel ATLI (Eds.), 209 - 218. Vukovic, M. ve Soro, A. 1992. Determination of Hydraulik konduktivity of porous media from grain-size composition. Water Resources Publications, Littleton: Colorado.