Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning

Abstract Amorphous calcium carbonate (ACC) plays an important role in the crystallization pathways of calcite and its polymorphs influencing many natural and anthropogenic processes, such as carbon sequestration. Characterizing the dissolution rate of ACC in presence of additives of contaminants in...

Full description

Saved in:
Bibliographic Details
Main Authors: Ryan Santoso, Lisa Guignon, Guido Deissmann, Jenna Poonoosamy
Format: Article
Language:English
Published: Nature Portfolio 2025-06-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-05984-0
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1850114470122094592
author Ryan Santoso
Lisa Guignon
Guido Deissmann
Jenna Poonoosamy
author_facet Ryan Santoso
Lisa Guignon
Guido Deissmann
Jenna Poonoosamy
author_sort Ryan Santoso
collection DOAJ
description Abstract Amorphous calcium carbonate (ACC) plays an important role in the crystallization pathways of calcite and its polymorphs influencing many natural and anthropogenic processes, such as carbon sequestration. Characterizing the dissolution rate of ACC in presence of additives of contaminants in favor of crystalline phases is challenging as such reactions occur readily in bulk solution. Droplet microfluidics offers a solution by confining ACC within a droplet, enabling a quantification of the transformation rate of ACC into crystalline phases. However, accurate quantification of this transformation requires analyzing more than thousands of droplets identifying the different polymorphs of calcium carbonate during an experiment, which is labor-intensive. Here we develop a visual-based machine learning method, combining cascading U-Net and K-Means clustering, to allow efficient analysis of droplet microfluidics experiment results. Using our method, we accurately inspect 11,288 droplets over 6 hours of experimental time to identify the polymorphs, using a CPU core in a laptop for only 42 minutes. This is achieved with manual labeling of 11 experimental microscopy images before augmentations. From our analyses the transformation rate of ACC into its crystalline phases can be inferred. The transformation rate indicates an increasing stability of the ACC phase in confinement. Our method is generalizable and can be applied to different setups of droplet microfluidics experiments, facilitating efficient experimentation and analysis of complex crystallization processes.
format Article
id doaj-art-6db3336f53774fcc9cfe458ac85407fc
institution OA Journals
issn 2045-2322
language English
publishDate 2025-06-01
publisher Nature Portfolio
record_format Article
series Scientific Reports
spelling doaj-art-6db3336f53774fcc9cfe458ac85407fc2025-08-20T02:36:50ZengNature PortfolioScientific Reports2045-23222025-06-0115111110.1038/s41598-025-05984-0Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learningRyan Santoso0Lisa Guignon1Guido Deissmann2Jenna Poonoosamy3Institute of Fusion Energy and Nuclear Waste Management - Nuclear Waste Management (IFN-2), Forschungszentrum Jülich GmbHInstitute of Fusion Energy and Nuclear Waste Management - Nuclear Waste Management (IFN-2), Forschungszentrum Jülich GmbHInstitute of Fusion Energy and Nuclear Waste Management - Nuclear Waste Management (IFN-2), Forschungszentrum Jülich GmbHInstitute of Fusion Energy and Nuclear Waste Management - Nuclear Waste Management (IFN-2), Forschungszentrum Jülich GmbHAbstract Amorphous calcium carbonate (ACC) plays an important role in the crystallization pathways of calcite and its polymorphs influencing many natural and anthropogenic processes, such as carbon sequestration. Characterizing the dissolution rate of ACC in presence of additives of contaminants in favor of crystalline phases is challenging as such reactions occur readily in bulk solution. Droplet microfluidics offers a solution by confining ACC within a droplet, enabling a quantification of the transformation rate of ACC into crystalline phases. However, accurate quantification of this transformation requires analyzing more than thousands of droplets identifying the different polymorphs of calcium carbonate during an experiment, which is labor-intensive. Here we develop a visual-based machine learning method, combining cascading U-Net and K-Means clustering, to allow efficient analysis of droplet microfluidics experiment results. Using our method, we accurately inspect 11,288 droplets over 6 hours of experimental time to identify the polymorphs, using a CPU core in a laptop for only 42 minutes. This is achieved with manual labeling of 11 experimental microscopy images before augmentations. From our analyses the transformation rate of ACC into its crystalline phases can be inferred. The transformation rate indicates an increasing stability of the ACC phase in confinement. Our method is generalizable and can be applied to different setups of droplet microfluidics experiments, facilitating efficient experimentation and analysis of complex crystallization processes.https://doi.org/10.1038/s41598-025-05984-0Droplet microfluidicsMachine learningAmorphous calcium carbonate
spellingShingle Ryan Santoso
Lisa Guignon
Guido Deissmann
Jenna Poonoosamy
Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
Scientific Reports
Droplet microfluidics
Machine learning
Amorphous calcium carbonate
title Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
title_full Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
title_fullStr Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
title_full_unstemmed Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
title_short Investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
title_sort investigating the metastability of amorphous calcium carbonate by droplet microfluidics experiments using machine learning
topic Droplet microfluidics
Machine learning
Amorphous calcium carbonate
url https://doi.org/10.1038/s41598-025-05984-0
work_keys_str_mv AT ryansantoso investigatingthemetastabilityofamorphouscalciumcarbonatebydropletmicrofluidicsexperimentsusingmachinelearning
AT lisaguignon investigatingthemetastabilityofamorphouscalciumcarbonatebydropletmicrofluidicsexperimentsusingmachinelearning
AT guidodeissmann investigatingthemetastabilityofamorphouscalciumcarbonatebydropletmicrofluidicsexperimentsusingmachinelearning
AT jennapoonoosamy investigatingthemetastabilityofamorphouscalciumcarbonatebydropletmicrofluidicsexperimentsusingmachinelearning