{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T09:53:50Z","timestamp":1781862830032,"version":"3.54.5"},"reference-count":57,"publisher":"MDPI AG","issue":"12","license":[{"start":{"date-parts":[[2026,6,18]],"date-time":"2026-06-18T00:00:00Z","timestamp":1781740800000},"content-version":"vor","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"funder":[{"name":"Hubei Provincial Natural Science Foundation of China","award":["2025AFB579"],"award-info":[{"award-number":["2025AFB579"]}]}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Materials"],"abstract":"<jats:p>The durability of reinforced concrete is closely related to the transport behavior of water and aggressive ions within the complex nanoporous network of calcium silicate hydrate. While molecular dynamics simulations provide critical atomistic insights into these confined transport behaviors, their immense computational cost limits their scalability to complex structural and temporal domains. To overcome this bottleneck, we propose a novel, modular computational framework that synergizes high-throughput molecular dynamics with advanced graph neural networks. By rigorously learning the mapping between the local atomic environment and kinetic behaviors, our model achieves high-fidelity predictions of pore water diffusion coefficients in saturated calcium silicate hydrate while improving computational efficiency by three orders of magnitude compared to conventional force field methods. Furthermore, the model demonstrates strong transferability and can accurately capture localized nonlinear diffusion characteristics in multiparticle pore structures with rough surfaces. Building on the interchangeability of this framework\u2019s core modules, we envision a visionary multiscale computational strategy that dynamically couples nanoscale atomistic predictions with mesoscale simulations. This work not only provides an ultrafast, highly accurate tool for screening transport properties across diverse structural configurations but also lays the groundwork for next-generation multiscale modeling of chloride ingress, ultimately advancing the design of resilient and sustainable reinforced concrete.<\/jats:p>","DOI":"10.3390\/ma19122631","type":"journal-article","created":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T09:18:43Z","timestamp":1781860723000},"page":"2631","update-policy":"https:\/\/doi.org\/10.3390\/mdpi_crossmark_policy","source":"Crossref","is-referenced-by-count":0,"title":["A Machine Learning-Based Computational Architecture for Unlocking Water Dynamics in Saturated Calcium Silicate Hydrate"],"prefix":"10.3390","volume":"19","author":[{"given":"Chunlong","family":"Liu","sequence":"first","affiliation":[{"name":"School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China"},{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"given":"Juntao","family":"Kang","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China"},{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-2372-8697","authenticated-orcid":false,"given":"Qimin","family":"Liu","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China"},{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0003-4276-5434","authenticated-orcid":false,"given":"Zechuan","family":"Yu","sequence":"additional","affiliation":[{"name":"School of Civil Engineering and Architecture, Wuhan University of Technology, Wuhan 430070, China"},{"name":"Sanya Science and Education Innovation Park, Wuhan University of Technology, Sanya 572000, China"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"1968","published-online":{"date-parts":[[2026,6,18]]},"reference":[{"key":"ref_1","doi-asserted-by":"crossref","first-page":"106784","DOI":"10.1016\/j.cemconres.2022.106784","article-title":"A comprehensive review of C-S-H empirical and computational models, their applications, and practical aspects","volume":"156","author":"Bonnaud","year":"2022","journal-title":"Cem. Concr. Res."},{"key":"ref_2","doi-asserted-by":"crossref","first-page":"106892","DOI":"10.1016\/j.cemconres.2022.106892","article-title":"Pore structure characterization of cement paste by different experimental methods and its influence on permeability evaluation","volume":"159","author":"Jiang","year":"2022","journal-title":"Cem. Concr. Res."},{"key":"ref_3","doi-asserted-by":"crossref","first-page":"136","DOI":"10.1016\/j.cemconres.2017.04.006","article-title":"Transport properties of concrete after drying-wetting regimes to elucidate the effects of moisture content, hysteresis and microcracking","volume":"98","author":"Wu","year":"2017","journal-title":"Cem. Concr. Res."},{"key":"ref_4","doi-asserted-by":"crossref","first-page":"126371","DOI":"10.1016\/j.conbuildmat.2022.126371","article-title":"Review on the deterioration and approaches to enhance the durability of concrete in the freeze\u2013thaw environment","volume":"321","author":"Wang","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_5","doi-asserted-by":"crossref","first-page":"119340","DOI":"10.1016\/j.conbuildmat.2020.119340","article-title":"Damage mechanism and interfacial transition zone characteristics of concrete under sulfate erosion and Dry-Wet cycles","volume":"255","author":"He","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_6","doi-asserted-by":"crossref","first-page":"105531","DOI":"10.1016\/j.cemconcomp.2024.105531","article-title":"Study on the deterioration of concrete performance in saline soil area under the combined effect of high low temperatures, chloride and sulfate salts","volume":"150","author":"Luo","year":"2024","journal-title":"Cem. Concr. Compos."},{"key":"ref_7","doi-asserted-by":"crossref","first-page":"27950","DOI":"10.1021\/acs.jpcc.7b08141","article-title":"Water Redistribution within the Microstructure of Cementitious Materials due to Temperature Changes Studied with 1H NMR","volume":"121","author":"Wyrzykowski","year":"2017","journal-title":"J. Phys. Chem. C"},{"key":"ref_8","doi-asserted-by":"crossref","first-page":"119843","DOI":"10.1016\/j.conbuildmat.2020.119843","article-title":"Water diffusion measurements in cement paste, mortar and concrete using a fast NMR based technique","volume":"259","author":"Fleury","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_9","doi-asserted-by":"crossref","first-page":"2","DOI":"10.1016\/j.jcis.2015.04.006","article-title":"Translational and rotational dynamics of water contained in aged Portland cement pastes studied by quasi-elastic neutron scattering","volume":"452","author":"Li","year":"2015","journal-title":"J. Colloid Interface Sci."},{"key":"ref_10","doi-asserted-by":"crossref","first-page":"55","DOI":"10.1016\/j.cemconres.2016.04.011","article-title":"Water dynamics in cement paste at early age prepared with pozzolanic volcanic ash and Ordinary Portland Cement using quasielastic neutron scattering","volume":"86","author":"Tyagi","year":"2016","journal-title":"Cem. Concr. Res."},{"key":"ref_11","doi-asserted-by":"crossref","first-page":"3080","DOI":"10.1021\/jp808754t","article-title":"Water Confined in Cement Pastes as a Probe of Cement Microstructure Evolution","volume":"113","author":"Ridi","year":"2009","journal-title":"J. Phys. Chem. B"},{"key":"ref_12","doi-asserted-by":"crossref","first-page":"255","DOI":"10.1016\/j.jcis.2011.02.026","article-title":"Cement: A two thousand year old nano-colloid","volume":"357","author":"Ridi","year":"2011","journal-title":"J. Colloid Interface Sci."},{"key":"ref_13","doi-asserted-by":"crossref","first-page":"472","DOI":"10.1016\/j.conbuildmat.2011.07.017","article-title":"Computational investigation on mass diffusivity in Portland cement paste based on X-ray computed microtomography (\u03bcCT) image","volume":"27","author":"Zhang","year":"2012","journal-title":"Constr. Build. Mater."},{"key":"ref_14","doi-asserted-by":"crossref","first-page":"18","DOI":"10.1016\/j.cemconres.2017.02.005","article-title":"Pore-scale modelling of relative permeability of cementitious materials using X-ray computed microtomography images","volume":"95","author":"Zhang","year":"2017","journal-title":"Cem. Concr. Res."},{"key":"ref_15","doi-asserted-by":"crossref","first-page":"73","DOI":"10.1016\/j.conbuildmat.2019.02.004","article-title":"CT-CFD integrated investigation into porosity and permeability of neat early-age well cement at downhole condition","volume":"205","author":"Yang","year":"2019","journal-title":"Constr. Build. Mater."},{"key":"ref_16","doi-asserted-by":"crossref","first-page":"121422","DOI":"10.1016\/j.conbuildmat.2020.121422","article-title":"Clogging mechanism of pervious concrete: From experiments to CFD-DEM simulations","volume":"270","author":"Nan","year":"2021","journal-title":"Constr. Build. Mater."},{"key":"ref_17","doi-asserted-by":"crossref","first-page":"106934","DOI":"10.1016\/j.jobe.2023.106934","article-title":"Enhancing the hydrophobicity of cement-based materials by fabricating microstructured surfaces: Experimental and numerical study","volume":"74","author":"Tian","year":"2023","journal-title":"J. Build. Eng."},{"key":"ref_18","doi-asserted-by":"crossref","first-page":"104870","DOI":"10.1016\/j.earscirev.2024.104870","article-title":"Pore-scale modeling of solute transport in partially-saturated porous media","volume":"256","author":"Saeibehrouzi","year":"2024","journal-title":"Earth-Sci. Rev."},{"key":"ref_19","doi-asserted-by":"crossref","first-page":"1524","DOI":"10.1016\/j.cemconres.2012.08.005","article-title":"Modeling of ionic diffusivity in non-saturated cement-based materials using lattice Boltzmann method","volume":"42","author":"Zhang","year":"2012","journal-title":"Cem. Concr. Res."},{"key":"ref_20","doi-asserted-by":"crossref","first-page":"92","DOI":"10.1016\/j.cemconcomp.2017.09.014","article-title":"Pore-scale modeling of chloride ion diffusion in cement microstructures","volume":"85","author":"Yang","year":"2018","journal-title":"Cem. Concr. Compos."},{"key":"ref_21","doi-asserted-by":"crossref","first-page":"118527","DOI":"10.1016\/j.conbuildmat.2020.118527","article-title":"Permeability prediction of hydrated cement paste based on its 3D image analysis","volume":"247","author":"Song","year":"2020","journal-title":"Constr. Build. Mater."},{"key":"ref_22","doi-asserted-by":"crossref","first-page":"126060","DOI":"10.1016\/j.conbuildmat.2021.126060","article-title":"Lattice Boltzmann modelling of ionic diffusivity in non-saturated limestone blended cement paste","volume":"316","author":"Liu","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_23","doi-asserted-by":"crossref","first-page":"109634","DOI":"10.1016\/j.jobe.2024.109634","article-title":"A study on the distribution and movement of water in unsaturated cement paste by a multi-component multi-phase lattice Boltzmann simulation","volume":"91","author":"Li","year":"2024","journal-title":"J. Build. Eng."},{"key":"ref_24","doi-asserted-by":"crossref","first-page":"173","DOI":"10.1186\/s11671-015-0862-y","article-title":"Nano- and mesoscale modeling of cement matrix","volume":"10","author":"Yu","year":"2015","journal-title":"Nanoscale Res. Lett."},{"key":"ref_25","doi-asserted-by":"crossref","first-page":"36967","DOI":"10.1038\/srep36967","article-title":"Mesoscopic packing of disk-like building blocks in calcium silicate hydrate","volume":"6","author":"Yu","year":"2016","journal-title":"Sci. Rep."},{"key":"ref_26","doi-asserted-by":"crossref","first-page":"282","DOI":"10.1016\/j.compositesb.2018.01.014","article-title":"Nano-engineering of construction materials using molecular dynamics simulations: Prospects and challenges","volume":"143","author":"Lau","year":"2018","journal-title":"Compos. Part B Eng."},{"key":"ref_27","doi-asserted-by":"crossref","first-page":"106517","DOI":"10.1016\/j.cemconres.2021.106517","article-title":"Role of carbon nanotube in reinforcing cementitious materials: An experimental and coarse-grained molecular dynamics study","volume":"147","author":"Qin","year":"2021","journal-title":"Cem. Concr. Res."},{"key":"ref_28","doi-asserted-by":"crossref","first-page":"107501","DOI":"10.1016\/j.cemconres.2024.107501","article-title":"Weaving the next-level structure of calcium silicate hydrate at the submicron scale via a remapping algorithm from coarse-grained to all-atom model","volume":"180","author":"Zhou","year":"2024","journal-title":"Cem. Concr. Res."},{"key":"ref_29","doi-asserted-by":"crossref","first-page":"107700","DOI":"10.1016\/j.cemconres.2024.107700","article-title":"Understanding nanoscale mechanism of compression casting on rubber-cement interface: A molecular dynamics study","volume":"186","author":"Kang","year":"2024","journal-title":"Cem. Concr. Res."},{"key":"ref_30","doi-asserted-by":"crossref","first-page":"2499","DOI":"10.1021\/ja107003a","article-title":"Glassy Nature of Water in an Ultraconfining Disordered Material: The Case of Calcium\u2212Silicate\u2212Hydrate","volume":"133","author":"Youssef","year":"2011","journal-title":"J. Am. Chem. Soc."},{"key":"ref_31","doi-asserted-by":"crossref","first-page":"563","DOI":"10.1016\/j.conbuildmat.2017.06.053","article-title":"Molecular dynamics study on the chemical bound, physical adsorbed and ultra-confined water molecules in the nano-pore of calcium silicate hydrate","volume":"151","author":"Li","year":"2017","journal-title":"Constr. Build. Mater."},{"key":"ref_32","doi-asserted-by":"crossref","first-page":"128068","DOI":"10.1016\/j.conbuildmat.2022.128068","article-title":"Molecular dynamics study on sodium chloride solution transport through the Calcium-Silicate-Hydrate nanocone channel","volume":"342","author":"Hou","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_33","doi-asserted-by":"crossref","first-page":"120950","DOI":"10.1016\/j.conbuildmat.2020.120950","article-title":"Efficient machine learning models for prediction of concrete strengths","volume":"266","author":"Nguyen","year":"2021","journal-title":"Constr. Build. Mater."},{"key":"ref_34","doi-asserted-by":"crossref","first-page":"106449","DOI":"10.1016\/j.cemconres.2021.106449","article-title":"Predicting concrete compressive strength using hybrid ensembling of surrogate machine learning models","volume":"145","author":"Asteris","year":"2021","journal-title":"Cem. Concr. Res."},{"key":"ref_35","doi-asserted-by":"crossref","first-page":"106681","DOI":"10.1016\/j.cemconres.2021.106681","article-title":"Microstructure-informed deep convolutional neural network for predicting short-term creep modulus of cement paste","volume":"152","author":"Liang","year":"2022","journal-title":"Cem. Concr. Res."},{"key":"ref_36","doi-asserted-by":"crossref","first-page":"104414","DOI":"10.1016\/j.cemconcomp.2022.104414","article-title":"Prediction of concrete strengths enabled by missing data imputation and interpretable machine learning","volume":"128","author":"Lyngdoh","year":"2022","journal-title":"Cem. Concr. Compos."},{"key":"ref_37","doi-asserted-by":"crossref","first-page":"21336","DOI":"10.1038\/s41598-020-78368-1","article-title":"Elucidating the constitutive relationship of calcium\u2013silicate\u2013hydrate gel using high throughput reactive molecular simulations and machine learning","volume":"10","author":"Lyngdoh","year":"2020","journal-title":"Sci. Rep."},{"key":"ref_38","doi-asserted-by":"crossref","first-page":"135257","DOI":"10.1016\/j.conbuildmat.2024.135257","article-title":"The role of deep learning in reducing computational cost when simulating chloride ion attack on hydrated calcium silicate with molecular dynamics","volume":"417","author":"Wang","year":"2024","journal-title":"Constr. Build. Mater."},{"key":"ref_39","doi-asserted-by":"crossref","first-page":"107690","DOI":"10.1016\/j.cemconres.2024.107690","article-title":"Insights on the mechanical properties and failure mechanisms of calcium silicate hydrates based on deep-learning potential molecular dynamics","volume":"186","author":"Li","year":"2024","journal-title":"Cem. Concr. Res."},{"key":"ref_40","doi-asserted-by":"crossref","unstructured":"Ilki, A., \u00c7avunt, D., and \u00c7avunt, Y.S. (2023). Effects of Temperature and NaCl Concentration on the Adsorption of C-S-H Gel in Cement Paste: A Multi-fidelity Molecular Dynamics Simulation. Building for the Future: Durable, Sustainable, Resilient, Springer.","DOI":"10.1007\/978-3-031-32519-9"},{"key":"ref_41","doi-asserted-by":"crossref","first-page":"106685","DOI":"10.1016\/j.cemconres.2021.106685","article-title":"A deep learning potential applied in tobermorite phases and extended to calcium silicate hydrates","volume":"152","author":"Zhou","year":"2022","journal-title":"Cem. Concr. Res."},{"key":"ref_42","doi-asserted-by":"crossref","first-page":"107092","DOI":"10.1016\/j.cemconres.2023.107092","article-title":"Unravelling the dissolution dynamics of silicate minerals by deep learning molecular dynamics simulation: A case of dicalcium silicate","volume":"165","author":"Li","year":"2023","journal-title":"Cem. Concr. Res."},{"key":"ref_43","first-page":"1335","article-title":"A deep learning-based potential developed for calcium silicate hydrates with both high accuracy and efficiency","volume":"12","author":"Li","year":"2023","journal-title":"J. Sustain. Cem.-Based Mater."},{"key":"ref_44","doi-asserted-by":"crossref","first-page":"16102","DOI":"10.1073\/pnas.0902180106","article-title":"A realistic molecular model of cement hydrates","volume":"106","author":"Pellenq","year":"2009","journal-title":"Proc. Natl. Acad. Sci. USA"},{"key":"ref_45","doi-asserted-by":"crossref","first-page":"1002","DOI":"10.1039\/C0CP00516A","article-title":"Empirical force fields for complex hydrated calcio-silicate layered materials","volume":"13","author":"Shahsavari","year":"2010","journal-title":"Phys. Chem. Chem. Phys."},{"key":"ref_46","unstructured":"Sch\u00fctt, K.T., Kindermans, P.-J., Sauceda, H.E., Chmiela, S., Tkatchenko, A., and M\u00fcller, K.-R. (2017). SchNet: A continuous-filter convolutional neural network for modeling quantum interactions. arXiv."},{"key":"ref_47","doi-asserted-by":"crossref","first-page":"241722","DOI":"10.1063\/1.5019779","article-title":"SchNet\u2014A deep learning architecture for molecules and materials","volume":"148","author":"Sauceda","year":"2018","journal-title":"J. Chem. Phys."},{"key":"ref_48","doi-asserted-by":"crossref","first-page":"122477","DOI":"10.1016\/j.conbuildmat.2021.122477","article-title":"Molecular dynamics study the structure, bonding, dynamic and mechanical properties of calcium silicate hydrate with ultra-confined water: Effects of nanopore size","volume":"280","author":"Sun","year":"2021","journal-title":"Constr. Build. Mater."},{"key":"ref_49","doi-asserted-by":"crossref","first-page":"129311","DOI":"10.1016\/j.conbuildmat.2022.129311","article-title":"Water transport in calcium silicate hydrate nanoscale pores by molecular dynamics: Unsaturated steady-state diffusion and suction","volume":"356","author":"Liu","year":"2022","journal-title":"Constr. Build. Mater."},{"key":"ref_50","doi-asserted-by":"crossref","first-page":"1411","DOI":"10.1039\/C4CP04137B","article-title":"Water transport in the nano-pore of the calcium silicate phase: Reactivity, structure and dynamics","volume":"17","author":"Hou","year":"2014","journal-title":"Phys. Chem. Chem. Phys."},{"key":"ref_51","doi-asserted-by":"crossref","first-page":"1309","DOI":"10.1007\/s10404-015-1646-5","article-title":"Structural, dynamic and mechanical evolution of water confined in the nanopores of disordered calcium silicate sheets","volume":"19","author":"Hou","year":"2015","journal-title":"Microfluid. Nanofluidics"},{"key":"ref_52","doi-asserted-by":"crossref","first-page":"17966","DOI":"10.1021\/jp062922f","article-title":"Water Dynamics in Hardened Ordinary Portland Cement Paste or Concrete:\u2009 From Quasielastic Neutron Scattering","volume":"110","author":"Bordallo","year":"2006","journal-title":"J. Phys. Chem. B"},{"key":"ref_53","doi-asserted-by":"crossref","first-page":"9","DOI":"10.1016\/j.micromeso.2014.04.011","article-title":"Molecular dynamics study of water and ions transport in nano-pore of layered structure: A case study of tobermorite","volume":"195","author":"Hou","year":"2014","journal-title":"Microporous Mesoporous Mater."},{"key":"ref_54","doi-asserted-by":"crossref","first-page":"113842","DOI":"10.1016\/j.micromeso.2025.113842","article-title":"Water-induced CO2 adsorption in ZIF-8: Insights from experiments and advanced monte carlo simulations","volume":"400","author":"Gotzias","year":"2026","journal-title":"Microporous Mesoporous Mater."},{"key":"ref_55","doi-asserted-by":"crossref","first-page":"11423","DOI":"10.52202\/068431-0830","article-title":"MACE: Higher Order Equivariant Message Passing Neural Networks for Fast and Accurate Force Fields","volume":"35","author":"Batatia","year":"2022","journal-title":"Adv. Neural Inf. Process. Syst."},{"key":"ref_56","doi-asserted-by":"crossref","first-page":"579","DOI":"10.1038\/s41467-023-36329-y","article-title":"Learning local equivariant representations for large-scale atomistic dynamics","volume":"14","author":"Musaelian","year":"2023","journal-title":"Nat. Commun."},{"key":"ref_57","doi-asserted-by":"crossref","first-page":"2453","DOI":"10.1038\/s41467-022-29939-5","article-title":"E(3)-equivariant graph neural networks for data-efficient and accurate interatomic potentials","volume":"13","author":"Batzner","year":"2022","journal-title":"Nat. Commun."}],"container-title":["Materials"],"original-title":[],"language":"en","link":[{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/12\/2631\/pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2026,6,19]],"date-time":"2026-06-19T09:23:51Z","timestamp":1781861031000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.mdpi.com\/1996-1944\/19\/12\/2631"}},"subtitle":[],"short-title":[],"issued":{"date-parts":[[2026,6,18]]},"references-count":57,"journal-issue":{"issue":"12","published-online":{"date-parts":[[2026,6]]}},"alternative-id":["ma19122631"],"URL":"https:\/\/doi.org\/10.3390\/ma19122631","relation":{},"ISSN":["1996-1944"],"issn-type":[{"value":"1996-1944","type":"electronic"}],"subject":[],"published":{"date-parts":[[2026,6,18]]}}}