Developing a custom loss function for regulating underestimation and overestimation of concrete mechanical properties predictions in neural network models
Open Access
- 3 April 2026
- journal article
- research article
- Published by Springer Nature in Scientific Reports
- Vol. 16 (1)
Abstract
Accurate prediction of concrete properties is a critical aspect of structural engineering. Conventional neural network models, while effective in various predictive tasks, often fall short in this context because they do not distinguish between the risks associated with underestimation and overestimation of strength. Existing codes of practice in civil engineering advocate a conservative estimation approach, prioritizing underestimation to preserve safety margins. Standard neural network models, which treat all prediction errors uniformly, are therefore not aligned with this conservative bias, which motivates the present study. The aim of this research is to design a custom loss function that embeds domain-specific safety requirements into artificial intelligence models. This function penalizes underestimations less severely than overestimations, reflecting the conservative principles of structural design. The problem formulation emphasizes the importance of conservative concrete strength prediction within the broader context of structural safety. Rubberized concrete is adopted as a case study to investigate the performance of the proposed custom loss function and to benchmark it against traditional loss functions. The study results show that the developed custom loss function effectively addresses conservative estimation needs by reducing the overestimation ratio from about 25–100% with traditional approaches to as low as 1%. At the same time, prediction accuracy remains comparable to conventional loss functions. Accordingly, the proposed custom loss function can serve as a technical enhancement that improves prediction behavior in line with conservative design philosophy and supports the reliable use of neural network models as one component within the structural design process.Keywords
This publication has 25 references indexed in Scilit:
- Machine Learning-Based Estimation of Reinforced Concrete Columns Stiffness Modifiers for Improved Accuracy in Linear Response History AnalysisJournal of Earthquake Engineering, 2024
- A systematic and bibliometric review on physics-based neural networks applications as a solution for structural engineering partial differential equationsStructures, 2024
- Deep learning paradigm for prediction of stress distribution in damaged structural components with stress concentrationsAdvances in Engineering Software, 2022
- Prediction of thermo-mechanical properties of rubber-modified recycled aggregate concreteConstruction and Building Materials, 2022
- Predicting the mechanical properties of cement mortar using the support vector machine approachConstruction and Building Materials, 2021
- Deep learning model for estimating the mechanical properties of concrete containing silica fume exposed to high temperaturesFrontiers of Structural and Civil Engineering, 2020
- Properties prediction of environmentally friendly ultra-high-performance concrete using artificial neural networksEuropean Journal of Environmental and Civil Engineering, 2020
- Concrete compressive strength using artificial neural networksNeural Computing and Applications, 2019
- Flexural Response Prediction of Reinforced Concrete Members Based on Statistical ObservationsArabian Journal for Science and Engineering, 2017
- Properties of rubberized concretes containing silica fumeCement and Concrete Research, 2004