Cheminformatics for accelerated design of chemical admixtures

Childs, Christopher M.; Canbek, Oğulcan; Kirby, Tia M.; Zhang, Cheng; Zheng, Jiangnan; Szeto, Connor; Póczos, Barnabás; Kurtis, Kimberly E.; Washburn, Newell R.

doi:10.1016/j.cemconres.2020.106173

Cited by 8 publications

(5 citation statements)

References 41 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…During the sample preparation, seeds were dispersed in deionized water with an initial temperature of 20°C 27 . The RMC was first added to the container, and then the seeded solution was mixed with RMC.…”

Section: Methodsmentioning

confidence: 99%

“…During the sample preparation, seeds were dispersed in deionized water with an initial temperature of 20 • C. 27 The RMC was first added to the container, and then the seeded solution was mixed with RMC. Meanwhile, half of the seeded solution was added first, and the mixture was stirred by a glass rod, and the remaining half solution was added subsequently with a second stirring of the mixture.…”

Section: Semi-adiabatic Calorimetrymentioning

confidence: 99%

See 1 more Smart Citation

Understanding the role of seeds in reactive magnesia cement (RMC) formulations

et al. 2023

View full text Add to dashboard Cite

Nucleation effects of seeds in reactive magnesia cement (RMC) systems have been reported, but this process has never been directly observed. In this study, different types and contents of seeds were introduced in RMC formulations. Resultsshow that seeded RMC samples revealed accelerated hydration/carbonation that led to their more rapid strength development, and the use of magnesite outperformed other seeds given their overall performances, as explained by their more homogenous microstructures. Further, in the model solution, the amount of Mg2+ ions adsorbed onto seeds particles continuously increased with the increment of Mg2+ concentrations, confirming the nucleation effects of seeds in RMC formulations directly, and seeds surfaces revealed a much higher affinity for Mg2+ ions than other ions due to their acid-base interactions. Therefore, the use of seeds could act as accelerators that shorten the curing period of RMC-based concrete products on a large scale.

show abstract

Section: Methodsmentioning

confidence: 99%

Section: Semi-adiabatic Calorimetrymentioning

confidence: 99%

Understanding the role of seeds in reactive magnesia cement (RMC) formulations

et al. 2023

View full text Add to dashboard Cite

show abstract

“…For the available, relevant data, the schema of reported features or outputs is often inconsistent across sources. Community consensus on what variables to report or what treatment methods to use may also change over time, potentially making it difficult to adequately construct even a small database. , Indeed, while the quality of learning with ML generally increases with more observations, materials’ small data often require tailored approaches to represent and learn from sparse and noisy data. − …”

Section: Introductionmentioning

confidence: 99%

“…For example, Soper-Hopper et al used over 3000 2-D descriptors from Dragon 7.0 to make ML predictions of collision cross sections starting with a database of 195 entries . Childs et al used a dataset of only 23 molecules and extended-connectivity fingerprints with 2048 bits and achieved good cross-validated performance in predicting chemical admixtures for cement . However, while ML models with good predictability can be achieved, a common shortcoming in many studies using high-resolution descriptors is a lack of physical interpretability, as determining the dependence on an abstract, high-dimensional set of features can be difficult .…”

Section: Introductionmentioning

confidence: 99%

“…20 Childs et al used a dataset of only 23 molecules and extended-connectivity fingerprints with 2048 bits and achieved good cross-validated performance in predicting chemical admixtures for cement. 14 However, while ML models with good predictability can be achieved, a common shortcoming in many studies using high-resolution descriptors is a lack of physical interpretability, as determining the dependence on an abstract, high-dimensional set of features can be difficult. 10 When possible, there is value in extracting physicochemical knowledge not only to validate predictions but also to enhance the effectiveness of future models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Small Data Machine Learning: Classification and Prediction of Poly(ethylene terephthalate) Stabilizers Using Molecular Descriptors

Liu

Venkatesh

McBride

et al. 2020

ACS Appl. Polym. Mater.

View full text Add to dashboard Cite

Experimental data from a patent were analyzed to learn about the small molecule additives that were most effective in mitigating the degradation of polyethylene terephthalate. Two sets of molecular descriptors were calculated for a dataset of 39 additive candidates; unsupervised and supervised analyses were performed to determine the most influential structural features that led to reduced degradation. A clustering approach revealed evidence that performance differences had some structural pattern dependence on the molecular descriptors that were employed. To pinpoint the features responsible for those physical differences, a reduced design region approach was applied to analyze descriptors both individually and in multiple dimensions to determine the effectiveness in a binary classification of high and low performances. For each molecular descriptor type, two or three influential descriptors were identified and justified with respect to the additive performance and physicochemical ability to mitigate degradation. Random forest models were constructed with relatively high predictability for both MACCS-166 (AUC = 0.86) and alvaDesc molecular descriptors (AUC = 0.93). We compare molecular descriptor methods for their ability to construct classifiers and to prioritize experimental work toward building a rich dataset. We find that, in small materials datasets, understanding the underlying physicochemical behavior is indispensable for validating the effectiveness of machine learning models.

show abstract

Aspects of Admixture Research: On the Use of Machine Learning in Superplasticizer Chemistry

Gädt,

Wagner

2023

ce papers

View full text Add to dashboard Cite

The use of superplasticizers in concrete, especially polycarboxylate ethers (PCE), has delivered the ability to easily achieve low water to cement ratios and thereby either higher strength or lower cement contents. In the last years, significant progress has been made with regard to understanding the structure‐activity relationship of the interaction of PCE and cement. For example, scaling laws have been derived for the size of adsorbed PCE, the magnitude of the steric interaction force, for the retardation of cement hydration by PCEs and more recently for competitive adsorption. While this is extremely useful, the picture is not fully complete yet.In this contribution, we wish to highlight some recent work in the field of data analysis of PCE. Inspired by a very early machine‐learning study of concrete formulations, we extracted structural PCE data together with rheology data from the literature. We compare PCE performance across studies and attempt to uncover underlying structure‐activity‐relationships (using machine learning models). It turns out that the data set quality and quantity is not yet sufficient to establish reliable models.

show abstract

Cheminformatics for accelerated design of chemical admixtures

Cited by 8 publications

References 41 publications

Understanding the role of seeds in reactive magnesia cement (RMC) formulations

Understanding the role of seeds in reactive magnesia cement (RMC) formulations

Small Data Machine Learning: Classification and Prediction of Poly(ethylene terephthalate) Stabilizers Using Molecular Descriptors

Aspects of Admixture Research: On the Use of Machine Learning in Superplasticizer Chemistry

Contact Info

Product

Resources

About