In this section
@article{Sanchez,
author = {Sanchez, Fernandez J and Ruiz, Lopez A and Taborda, D},
journal = {Machine Learning and Data Science in Geotechnics},
title = {Data-driven surrogates for predicting thermal performance and response functions of thermo-active piles},
}
TY - JOUR
AB - Purpose This paper develops fast, accurate data-driven surrogate models to predict the thermal performance and thermal response functions of single thermo-active piles. These replace computationally expensive finite element simulations and geometry-specific g-function calculations with generalisable machinelearning models suitable for preliminary design and performance assessment. The work aims to improve accessibility, reduce computational cost, and support wider adoption of thermo-active piles within lowcarbon and net-zero infrastructure strategies. Design/methodology/approach Two Artificial Neural Network (ANN) surrogates were trained on databases generated from 3D transient finite element simulations of thermo-active piles. One surrogate predicts transient power output per unit length under a prescribed inlet fluid temperature, while the second predicts normalised pile wall and outlet thermal responses under constant heat flux. Input parameters were sampled using Latin Hypercube sampling. Model training employed feature normalisation, cross-validation, and regularisation, with performance evaluated using standard regression metrics and SHAP-based interpretability analysis. Findings Both surrogate models demonstrate excellent predictive accuracy and strong generalisation. The power output surrogate achieves R² values exceeding 0.99 with mean absolute errors typically below 2 W/m for most of the operational period. The thermal response surrogate reproduces pile wall and outlet gfunctions over ten years with global per-point R² values of 0.994–0.997 and per-timestep averages of 0.971 (wall) and 0.959 (outlet). Validation against a field thermal response test confirms reliable extrapolation beyond the trained diameter range. Computational time is reduced by several orders of magnitude compared with finite element analysis. Originality/value This study presents the first generalisable surrogate framework capable of predicting both power outputper un
AU - Sanchez,Fernandez J
AU - Ruiz,Lopez A
AU - Taborda,D
SN - 3029-0422
TI - Data-driven surrogates for predicting thermal performance and response functions of thermo-active piles
T2 - Machine Learning and Data Science in Geotechnics
ER -
Geotechnics
Civil and Environmental Engineering
Skempton Building
Imperial College London
South Kensington Campus
London, SW7 2AZ
Telephone:
+44 (0)20 7594 6077
Email: j.otoole@imperial.ac.uk
Alternatively, you can find a member of Geotechnics staff on the Department of Civil and Environmental Engineering website.
Follow us on Twitter: @GeotechnicsICL
We are located in the Skempton Building (building number 27 on the South Kensington Campus Map). How to find us
