TY - JOUR ID - 136759 TI - Machine Learning on Microstructural Chemical Maps to Classify Component Phases in Cement Pastes JO - Journal of Soft Computing in Civil Engineering JA - SCCE LA - en SN - AU - Ford, Emily AU - Maneparambil, Kailasnath AU - Neithalath, Narayanan AD - Graduate student, School of Sustainable Engineering and the Built Environment, Arizona State University, Tempe AZ 85287, USA AD - Intel Corporation, Chandler, AZ 85224, USA AD - Professor, School of Sustainable Engineering and the Built Environment, Arizona State University, Tempe AZ 85287, USA Y1 - 2021 PY - 2021 VL - 5 IS - 4 SP - 1 EP - 20 KW - Machine Learning KW - Nanoindentation KW - Chemical mapping KW - Microstructure KW - Cement pastes KW - Ultra-High performance concrete DO - 10.22115/scce.2021.302400.1357 N2 - This paper implements machine learning (ML) classification algorithms on microstructural chemical maps to predict the constituent phases. Intensities of chemical species (Ca, Al, Si, etc.), and in some cases the nanomechanical properties measured at the corresponding points, form the input to the ML model, which predicts the phase label (LD or HD C-S-H, clinker etc.) belonging to that location. Artificial neural networks (ANN) and forest ensemble methods are used for classification. Confusion matrices and receiver-operator characteristic (ROC) curves are used to analyze the classification efficiency. It is shown that, for complex microstructures such as those of ultra-high performance (UHP) pastes, the classifier performs well when nanomechanical information augments the chemical intensity data. For simpler systems such as well-hydrated plain cement pastes, the classifier accurately predicts the phase label from the intensities of Ca, Al, and Si alone. The work enables fast-and-efficient phase identification and property forecasting from microstructural chemical maps. UR - https://www.jsoftcivil.com/article_136759.html L1 - https://www.jsoftcivil.com/article_136759_ac647438733f6b7d898cc892fd60aa09.pdf ER -