Rizvi ZH, Akhtar SJ, Husain SMB, Khan M, Haider H, Naqvi S, Tirth V, Wuttke F. Neural Network Approaches for Computation of Soil Thermal Conductivity. Mathematics. 2022; 10(21):3957. https://doi.org/10.3390/math10213957
Neural network approaches for computation of soil thermal conductivity
|Author:||Rizvi, Zarghaam Haider1; Akhtar, Syed Jawad2; Husain, Syed Mohammad Baqir3;|
1Geomechanics & Geotechnics, Kiel University, 24118 Kiel, Germany
2Center for Ubiquitous Computing, University of Oulu, 90014 Oulu, Finland
3Faculty of Computer Science, Dalhousie University, Halifax, NS B3H 4R2, Canada
4Department of Computer Engineering, Aligarh Muslim University, Aligarh 202002, India
5Department of Information Technology, Krishna Institute of Engineering and Technology, Ghaziabad 201206, India
6Department of Computer Science, University of Southern California, Los Angeles, CA 90089, USA
7Mechanical Engineering Department, College of Engineering, King Khalid University, Abha 61421, Saudi Arabia
|Online Access:||PDF Full Text (PDF, 1.7 MB)|
|Persistent link:|| http://urn.fi/urn:nbn:fi-fe2023070479564
Multidisciplinary Digital Publishing Institute,
|Publish Date:|| 2023-07-04
The effective thermal conductivity (ETC) of soil is an essential parameter for the design and unhindered operation of underground energy transportation and storage systems. Various experimental, empirical, semi-empirical, mathematical, and numerical methods have been tried in the past, but lack either accuracy or are computationally cumbersome. The recent developments in computer science provided a new computational approach, the neural networks, which are easy to implement, faster, versatile, and reasonably accurate. In this study, we present three classes of neural networks based on different network constructions, learning and computational strategies to predict the ETC of the soil. A total of 384 data points are collected from literature, and the three networks, Artificial neural network (ANN), group method of data handling (GMDH) and gene expression programming (GEP), are constructed and trained. The best accuracy of each network is measured with the coefficient of determination (𝑅²) and found to be 91.6, 83.2 and 80.5 for ANN, GMDH and GEP, respectively. Furthermore, two sands with 80% and 99% quartz content are measured, and the best performing network from each class of ANN, GMDH and GEP is independently validated. The GEP model provided the best estimate for 99% quartz sand and GMDH with 80%.
|Type of Publication:||
A1 Journal article – refereed
|Field of Science:||
This research was funded by Deanship of Scientific Research at King Khalid University, Abha 61421, Asir, Kingdom of Saudi Arabia through Large Groups Project under grant number RGP.2/140/43 (V.T.).
© 2022 by the authors. Licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/licenses/by/4.0/).