Abstract :

With The Increasing Focus On Sustainable Construction, Interlocking Bricks Have Gained Attention Due To Their Environmental Benefits. However, Existing Approaches Primarily Emphasize Improving Mechanical Properties While Overlooking The Potential For Optimizing CO? Sequestration During The Curing Process. To Address This Challenge, This Study Proposes A Novel Methodology To Predict And Optimize The Carbon Sequestration Potential Of Sustainable Interlocking Bricks Using A Deep Learning-based Framework. Initially Data Are Collected From The “An Industrial Demonstration Study On CO? Mineralization Curing For Concrete” Dataset.That Includes Material Composition, Curing Conditions, Environmental Factors, And CO? Absorption Rates, Which Serve As Input For The Model. Then The Data Are Preprocessed UsingInverse Unscented Kalman Filter (I-UKF). Then The Preprocessed Data Are Fed Toa RotationInvariant Coordinate Convolutional Neural Network (RI-CoordConvNet) Which Models The Complex Relationships Between Chemical Composition, Curing Conditions, And CO? Sequestration Efficiency. Finally The Proposed Method Is Implemented In Python.The Model’s Predictive Performance Undergoes Evaluation Using Accuracy, Precision, Recall, And F1-score To Ensure Reliability. Additionally, The Proposed Model’s Predictions Undergo Benchmarking Against Traditional Machine Learning Methods, Highlighting The Advantages Of The Deep Learning-based Approach In Enhancing The Understanding And Optimization Of CO? Mineralization For Sustainable Brick Manufacturing. Keywords:Carbon, Interlocking Bricks, Mineralization, Concrete, Mechanical Properties, Construction, Chemical, Strength

Published:

08-7-2025

Issue:

Vol. 25 No. 7 (2025)

Page Nos:

109-119

Section:

Articles

License:

This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.

How to Cite