Machine Learning–Enhanced Integrated Assessment of Thermal and Radiation Shielding Performance Degradation in GGBFS-Based Geopolymer Concrete: Quantifying Microstructural Damage and Optimizing Mix Design for Nuclear Applications

Abstract This study presents a comprehensive investigation into the concurrent thermal and radiation shielding performance of ground granulated blast furnace slag (GGBFS)-based geopolymer concrete (GPC) exposed to temperatures up to 600°C for durations of up to 120 min. Although GPC is widely acknowledged for its enhanced fire resistance and environmental benefits over ordinary portland cement (OPC) concrete, its dual functionality as a load-bearing and radiation-shielding material under thermal stress has not been rigorously quantified. This work bridges that gap by integrating mechanical, radiological, and microstructural analyses, directly linking thermally induced damage—such as dehydration, porosity growth, and microcracking—to measurable declines in performance. Experimental results (mean ± SD and n = 5 ) showed that after 120 min at 600°C, compressive strength decreased by 59.4%, from 36.47 ± 1.82 to 14.81 ± 0.74 MPa . Concurrently, the gamma ray linear attenuation coefficient and neutron removal cross section diminished by 36.5% and 25.3%, respectively, accompanied by marked increases in half-value and 10th-value layer thicknesses. A critical thermal threshold was identified near 400°C, beyond which degradation accelerates in a nonlinear manner. Statistical validation and machine learning models [artificial neural network (ANN), support vector machine (SVM), and long short-term memory (LSTM)] confirmed temperature and porosity as the dominant degradation drivers. Furthermore, mix design optimization via a genetic algorithm demonstrated that adjusting GGBFS content and Na 2 SiO 3 /NaOH ratios can recover up to ∼ 10 % of lost performance at 600°C. These findings challenge the assumption that GPC’s inherent fire resistance ensures reliable multifunctionality in nuclear applications, underscoring the necessity of thermally tailored geopolymer composites for extreme environments.

Authors

Institutions

Publication Details

Journal
Journal of Materials in Civil Engineering
Published
2026-11-09
DOI
https://doi.org/10.1061/jmcee7.mteng-24781
Primary Topic
Fire effects on concrete materials
Type
article
Field-Weighted Citation Impact
0.00
Controls
|||
ALL TIME
JAN
FEB
MAR
APR
MAY
JUN
JUL
AUG
SEP
OCT
NOV
article

Machine Learning–Enhanced Integrated Assessment of Thermal and Radiation Shielding Performance Degradation in GGBFS-Based Geopolymer Concrete: Quantifying Microstructural Damage and Optimizing Mix Design for Nuclear Applications

Seyed Hosein Ghasemzadeh Mousavinejad, Amin Gholizad, Arian DarvishaliNezhad, Seyyedeh Mohaddeseh Moosavifard et al.
Journal of Materials in Civil Engineering
Fire effects on concrete materials
article

Machine Learning–Enhanced Integrated Assessment of Thermal and Radiation Shielding Performance Degradation in GGBFS-Based Geopolymer Concrete: Quantifying Microstructural Damage and Optimizing Mix Design for Nuclear Applications

Seyed Hosein Ghasemzadeh Mousavinejad, Amin Gholizad, Arian DarvishaliNezhad, Seyyedeh Mohaddeseh Moosavifard, Sheyda Malehmir
article en

Abstract

Abstract This study presents a comprehensive investigation into the concurrent thermal and radiation shielding performance of ground granulated blast furnace slag (GGBFS)-based geopolymer concrete (GPC) exposed to temperatures up to 600°C for durations of up to 120 min. Although GPC is widely acknowledged for its enhanced fire resistance and environmental benefits over ordinary portland cement (OPC) concrete, its dual functionality as a load-bearing and radiation-shielding material under thermal stress has not been rigorously quantified. This work bridges that gap by integrating mechanical, radiological, and microstructural analyses, directly linking thermally induced damage—such as dehydration, porosity growth, and microcracking—to measurable declines in performance. Experimental results (mean ± SD and n = 5 ) showed that after 120 min at 600°C, compressive strength decreased by 59.4%, from 36.47 ± 1.82 to 14.81 ± 0.74 MPa . Concurrently, the gamma ray linear attenuation coefficient and neutron removal cross section diminished by 36.5% and 25.3%, respectively, accompanied by marked increases in half-value and 10th-value layer thicknesses. A critical thermal threshold was identified near 400°C, beyond which degradation accelerates in a nonlinear manner. Statistical validation and machine learning models [artificial neural network (ANN), support vector machine (SVM), and long short-term memory (LSTM)] confirmed temperature and porosity as the dominant degradation drivers. Furthermore, mix design optimization via a genetic algorithm demonstrated that adjusting GGBFS content and Na 2 SiO 3 /NaOH ratios can recover up to ∼ 10 % of lost performance at 600°C. These findings challenge the assumption that GPC’s inherent fire resistance ensures reliable multifunctionality in nuclear applications, underscoring the necessity of thermally tailored geopolymer composites for extreme environments.

Journal of Materials in Civil EngineeringVol. 39(3)
Academic Center for Education, Culture and Research (IR), University of Mohaghegh Ardabili (IR), University of Guilan (IR)
Fire effects on concrete materials
AI Navigator

Ask Laika to Summarize, Analyze, and Connect papers live on the map.

Summarize Papers & Methodologies

Extract key findings, datasets, and comparative methods across publications.

Benchmark Rankings & Visual Analytics

Rank top research institutions, authors, funders, topics, and journals by Field-Weighted Citation Impact (FWCI) and paper volume with instant charts.

Connect Distant Disciplines

Bridge topological clusters on the map to find hidden collaborative intersections.

Laika access coming soon