Improved Prediction of Soil Thermal Properties Using Recurrent Neural Networks
Publication: International Conference on Transportation and Development 2024
ABSTRACT
Frost effects, such as thaw weakening and frost heave, can significantly degrade pavements. Effective mitigation relies on accurate prediction of soil thermal properties. Current prediction methods use empirical equations or finite element analysis, with recent progress using machine learning. Recurrent neural networks, a type of machine learning model designed for prediction of sequential data, may be appropriate. Further, the model’s output can be fed back into itself recursively to make long-term predictions. Using this method and training data from Hill Air Force Base, Utah, and Air Force Academy, Colorado, we were able to forecast soil parameters including temperature, thermal conductivity, and moisture content for frost susceptible soils. The model had a deviation from experimental values of no more than 10%, with the most significant contributions to accuracy being the use of gated recurrent unit neurons and the incorporation of multiple soil parameters.
Get full access to this chapter
View all available purchase options and get full access to this chapter.
REFERENCES
Alzubaidi, L., Zhang, J., Humaidi, A. J., Al-Dujaili, A., Duan, Y., Al-Shamma, O., and Farhan, L. (2021). Review of deep learning: Concepts, CNN architectures, challenges, applications, future directions. Journal of Big Data, 8.
Barooni, M., Ziarati, K., and Barooni, A. (2023). Frost Prediction Using Machine Learning Methods in Fars Province. 28th International Computer Conference. Tehran: Computer Society of Iran.
Bianchini, A., and Gonzalez, C. R. (2012). Pavement-Transportation Computer Assisted Structural Engineering (PCASE) Implementation of the Modified Berggren (ModBerg) Equation for Computing the Frost Penetration Depth within Pavement Structures. Vicksburg: US Army Corps of Engineers.
Choi, H.-J., Kim, S., Kim, Y., and Won, J. (2022). Predicting Frost Depth of Soils in South Korea Using Machine Learning Techniques. Sustainability(14), 9767.
Dayarathne, R., Hawlader, B., Phillips, R., and Robert, D. (2023). Two-dimensional finite element modeling of long-term frost heave beneath chilled gas pipelines. Cold Regions Science and Technology, 208.
Lein, A. W., Slone, S. L., Smith, C. E., Jr., Bernier, A. P., and Oren, J. I. (2019). Frost-Depth Penetration and Frost Heave in Frost-Susceptible Soils. Hanover: US Army Corps of Engineers.
Novak, D. R., Bailey, C., Brill, K. F., Burke, P., Hogsett, W. A., Rausch, R., and Schichtel, M. (2014). Precipitation and Temperature Forecast Performance at the Weather Prediction Center. Weather and Forecasting, 29(3), 489–504.
Pollard, W. H. (2017). Chapter 15 - Periglacial Processes in Glacial Environments. In J. Menzies, & J. J. van der Meer, Past Glacial Environments (pp. 537–564). Elsevier.
Rajaei, P., and Baladi, G. Y. (2015). Frost Depth: General Prediction Model. Transportation Research Record: Journal of the Transportation Research Board, 2510, 74–80.
Talsma, C. J., Solander, K. C., Mudunuru, M. K., Crawford, B., and Powell, M. R. (2023). Frost prediction using machine learning and deep neural network models. Frontiers in Artificial Intelligence.
Zaytar, M. A., and Amrani, C. E. (2016). Sequence to Sequence Weather Forecasting with Long Short-Term Memory Recurrent Neural Networks. International Journal of Computer Applications, 143(11), 0975–8887.
Information & Authors
Information
Published In
History
Published online: Jun 13, 2024
Authors
Metrics & Citations
Metrics
Citations
Download citation
If you have the appropriate software installed, you can download article citation data to the citation manager of your choice. Simply select your manager software from the list below and click Download.