A Deep Learning Framework for Full-Field Thermal Field Distribution Prediction from Digital Image Correlation Strain Measurements
Source abstract
Abstract
Digital Image Correlation (DIC) and infrared thermography (IRT) are widely used for full-field experimental analysis of materials and structures; however, direct thermal measurements are often constrained by limited access, thermally opaque safety enclosures, or the availability of infrared equipment. This study presents a deep learning-based framework for predicting full-field temperature distributions directly from a DIC-derived effective strain field. A supervised U-Net regression model was trained on paired effective strain–temperature data obtained from high-speed three-point bending experiments on aluminum specimens. The network learns a direct mapping between effective strain fields and corresponding temperature fields without requiring explicit thermomechanical modelling. The model’s performance was evaluated on an independent test set using RMSE, MAE, SSIM, and the coefficient of determination. The proposed framework achieved a coefficient of determination of up to R2 = 0.985 and showed strong spatial agreement with measured temperature fields, particularly during highly mechanically active deformation stages. These results demonstrate that reliable full-field temperature distributions can be reconstructed solely from strain measurements, providing a practical alternative to infrared thermography in experimental configurations where thermal imaging is impractical or unavailable.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Thermography and Photoacoustic Techniques · Optical measurement and interference techniques · Additive Manufacturing Materials and Processes
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
Faculty of Electrical Engineering Mechanical Engineering and Naval Architecture, University of Split, 21000 Split, Croatia
Faculty of Mechanical Engineering, University of Maribor, 2000 Maribor, Slovenia
Faculty of Mechanical Engineering, University of Ljubljana, 1000 Ljubljana, Slovenia
References (38)
Show source-provided references
1. Schreier, H., Orteu, J.-J., and Sutton, M.A. (2009). Image Correlation for Shape, Motion and Deformation Measurements, Springer.10.1007/978-0-387-78747-3 ↗
2. Digital Image Correlation: From Displacement Measurement to Identification of Elastic Properties—A Review10.1111/j.1475-1305.2006.00258.x ↗
3. Two-dimensional digital image correlation for in-plane displacement and strain measurement: A review10.1088/0957-0233/20/6/062001 ↗
4. Ncorr: Open-Source 2D Digital Image Correlation Matlab Software10.1007/s11340-015-0009-1 ↗
5. Maldague, X.P. (2001). Theory and Practice of Infrared Technology for Nondestructive Testing, Wiley.
6. An infrared image processing technique to analyse the calorific effects accompanying deformation of materials
7. Ronneberger, O., Fischer, P., and Brox, T. (2015, January 5–9). U-Net: Convolutional Networks for Biomedical Image Segmentation. Proceedings of the Medical Image Computing and Computer-Assisted Intervention—MICCAI 2015, Munich, Germany.10.1007/978-3-319-24574-4_28 ↗
8. Kaplan, H. (1993). Practical Applications of Infrared Thermal Sensing and Imaging Equipment, SPIE The International Society for Optics and Photonics. [3rd ed.].
9. A critical study of the Hopkinson pressure bar
10. Krstulović-Opara, L., Surjak, M., Vesenjak, M., Tonković, Z., Frančeski, J., Kodvanj, J., and Domazet, Ž. (October, January 29). Determination of material properties using dynamic tests supported by thermography, digital image correlation and numerical simulation. Proceedings of the 8th International Congress of Croatian Society of Mechanics, Opatija, Croatia.
11. Long, J., Shelhamer, E., and Darrell, T. (2015, January 7–12). Fully convolutional networks for semantic segmentation. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Boston, MA, USA.10.1109/CVPR.2015.7298965 ↗
12. Goodfellow, I., Bengio, Y., Courville, A., and Bengio, Y. (2016). Deep Learning, MIT Press.
13. Isola, P., Zhu, J.Y., Zhou, T., and Efros, A.A. (2017, January 21–26). Image-to-Image Translation with Conditional Adversarial Networks. Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR), Honolulu, HI, USA.10.1109/CVPR.2017.632 ↗
14. Zhu, J.Y., Park, T., Isola, P., and Efros, A.A. (2017, January 22–29). Efros Unpaired Image-to-Image Translation Using Cycle-Consistent Adversarial Networks. Proceedings of the IEEE International Conference on Computer Vision (ICCV), Venice, Italy.10.1109/ICCV.2017.244 ↗
15. Infrared Thermography for Temperature Measurement and Non-Destructive Testing10.3390/s140712305 ↗
16. Thermo-mechanical coupling in constitutive modeling of dissipative materials10.1016/j.ijsolstr.2016.04.024 ↗
17. Timoshenko, S.P., and Gere, J.M. (2012). Theory of Elastic Stability, Courier Corporation.
18. Gere, J.M., and Timoshenko, S.P. (1996). Mechanics of Materials, CL Engineering.
19. Jones, E.M.C., and Iadicola, M.A. (2025). International Digital Image Correlation Society, A Good Practices Guide for Digital Image Correlation, International Digital Image Correlation Society. [2nd ed.].
20. Batra, R. (2005). Elements of Continuum Mechanics, Wiley.10.2514/4.861765 ↗
21. Bishop, M. (2006). Pattern Recognition and Machine Learning, Springer.
22. Simard, P.Y., Steinkraus, D., and Platt, J.C. (2003, January 3–6). Best practices for convolutional neural networks applied to visual document analysis. Proceedings of the Seventh International Conference on Document Analysis and Recognition, Edinburgh, UK.
23. Quality assessment of speckle patterns for digital image correlation10.1016/j.optlaseng.2005.10.004 ↗
24. Liu, Y., Wang, F., Jiang, Z., Sfarra, S., Liu, K., and Yao, Y. (2023). Generative Deep Learning-Based Thermographic Inspection of Artwork. Sensors, 23.10.3390/s23146362 ↗
25. Data augmentation: A comprehensive survey of modern approaches10.1016/j.array.2022.100258 ↗
26. Liu, X., Karagoz, G., and Meratnia, N. (2024). Analyzing the Impact of Data Augmentation on the Explainability of Deep Learning-Based Medical Image Classification. Mach. Learn. Knowl. Extr., 7.10.3390/make7010001 ↗
27. Bridle, J.S. (1989). Probabilistic Interpretation of Feedforward Classification Network Outputs, with Relationships to Statistical Pattern Recognition. Neurocomputing, Springer.10.1007/978-3-642-76153-9_28 ↗
28. Data-driven methods for stress field predictions in random heterogeneous materials10.1016/j.engappai.2023.106267 ↗
29. Deep learning-based rapid prediction of temperature field and intelligent control of molten pool during directed energy deposition process
30. Shokrollahi, Y., Nikahd, M.M., Gholami, K., and Azamirad, G. (2023). Deep Learning Techniques for Predicting Stress Fields in Composite Materials: A Superior Alternative to Finite Element Analysis. Compos. Sci., 7.10.3390/jcs7080311 ↗
31. Deep Learning Methods for Reynolds-Averaged Navier–Stokes Simulations of Airfoil Flows10.2514/1.J058291 ↗
32. Enhanced low-dose CT image reconstruction by domain and task shifting gaussian denoisers10.3934/acse.2025018 ↗
33. (2025, December 03). Deep Learning Toolbox. Available online: https://www.mathworks.com/help/deeplearning/index.html.
34. Kingma, P., and Ba, J. (2017). Adam: A Method for Stochastic Optimization. arXiv.
35. Shalev-Shwartz, S., and Tewari, A. (2009, January 14–18). Stochastic methods for l1 regularized loss minimization. Proceedings of the 26th Annual International Conference on Machine Learning, Montreal, QC, Canada.
36. Xu, W., Khajehnejad, M.A., Avestimehr, A.S., and Hassibi, B. (2010, January 14–19). Breaking through the thresholds: An analysis for iterative reweighted ℓ1 minimization via the Grassmann angle framework. Proceedings of the IEEE International Conference on Acoustics, Speech and Signal Processing, Dallas, TX, USA.10.1109/ICASSP.2010.5495210 ↗
37. Correlation and Causation
38. On the Mathematical Properties of the Structural Similarity Index10.1109/TIP.2011.2173206 ↗