Multi-Target Machine Learning Model for Optimized and Sustainable Concrete

Dear Colleagues,

Concrete is the most widely used construction material globally, yet its conventional production is associated with high energy consumption, substantial carbon dioxide emissions, and intensive use of natural resources. In response, alternative and sustainable concrete materials such as alkali-activated materials, geopolymer concrete, and blended cementitious systems incorporating industrial by-products like fly ash, ground granulated blast-furnace slag, silica fume, and agricultural waste have gained increasing attention. These materials exhibit complex physicochemical interactions governed by precursor composition, activator chemistry, curing conditions, and mixture proportions, leading to highly nonlinear and interdependent mechanical, durable, and environmental performance characteristics. Traditional experimental and empirical approaches often struggle to capture these complex relationships efficiently, particularly when multiple performance criteria must be satisfied simultaneously. To address these challenges, machine learning (ML) techniques offer a powerful data-driven framework for modeling and optimizing sustainable concrete systems. By learning from experimental and simulated datasets, ML models can effectively capture nonlinear interactions between material constituents, processing parameters, and resulting performance indicators. Ensemble learning methods and stacking-based hybrid models are particularly well suited for this application due to their ability to improve predictive accuracy, robustness, and generalization by combining multiple base learners. Building on this framework, a multi-target ML approach enables the simultaneous prediction and optimization of multiple concrete performance indicators, such as compressive strength, tensile strength, elastic modulus, durability indices, workability, shrinkage, embodied carbon, and costs. Unlike single-target models, multi-target learning explicitly accounts for correlations and trade-offs among performance metrics, which are critical for sustainable material design. This Special Issue on an integrated multi-target ensemble learning framework supports the development of optimized and sustainable concrete mixtures by balancing performance, durability, and environmental impact, while significantly reducing experimental effort and accelerating material innovation.

Dr. Farzin Kazemi
Dr. Neda Asgarkhani
Guest Editors

Manuscript Submission Information

Manuscripts should be submitted online at www.mdpi.com by registering and logging in to this website. Once you are registered, click here to go to the submission form. Manuscripts can be submitted until the deadline. All submissions that pass pre-check are peer-reviewed. Accepted papers will be published continuously in the journal (as soon as accepted) and will be listed together on the Special Issue website. Research articles, review articles as well as short communications are invited. For planned papers, a title and short abstract (about 250 words) can be sent to the Editorial Office for assessment.

Submitted manuscripts should not have been published previously, nor be under consideration for publication elsewhere (except conference proceedings papers). All manuscripts are thoroughly refereed through a single-anonymized peer-review process. A guide for authors and other relevant information for submission of manuscripts is available on the Instructions for Authors page. Materials is an international peer-reviewed open access semimonthly journal published by MDPI.

Please visit the Instructions for Authors page before submitting a manuscript. The Article Processing Charge (APC) for publication in this open access journal is 2600 CHF (Swiss Francs). Submitted papers should be well formatted and use good English. Authors may use MDPI's English editing service prior to publication or during author revisions.