Theory+AI/ML for microscopy and spectroscopy: Challenges and opportunities

Unruh, Davis; Kolluru, Venkata Surya Chaitanya; Baskaran, Arun; Chen, Yiming; Chan, Maria K. Y.

doi:10.1557/s43577-022-00446-8

Cited by 16 publications

(15 citation statements)

References 89 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most exciting future developments involve the intersection of modelling, characterization, and ML. Using computational spectroscopy and microscopy, ML models and iterative learning approaches will allow real time inference on experimental characterization data [27], allowing understanding of redox reaction and degradation mechanisms, and even spatial inhomogeneity of these mechanisms with mapping techniques.…”

Section: Advances In Science and Technology To Meet Challengesmentioning

confidence: 99%

2023 Roadmap on molecular modelling of electrochemical energy materials

Zhang,

Cheng,

Chen

et al. 2023

J. Phys. Energy

Self Cite

View full text Add to dashboard Cite

New materials for electrochemical energy storage and conversion are the key to the electrification and sustainable development of our modern societies. Molecular modelling based on the principles of quantum mechanics and statistical mechanics as well as empowered by machine learning techniques can help us to understand, control and design electrochemical energy materials at atomistic precision. Therefore, this roadmap, which is a collection of authoritative opinions, serves as a gateway for both the experts and the beginners to have a quick overview of the current status and corresponding challenges in molecular modelling of electrochemical energy materials for batteries, supercapacitors, CO2RR, and fuel cell applications.

show abstract

Section: Advances In Science and Technology To Meet Challengesmentioning

confidence: 99%

2023 Roadmap on molecular modelling of electrochemical energy materials

Zhang,

Cheng,

Chen

et al. 2023

J. Phys. Energy

Self Cite

View full text Add to dashboard Cite

show abstract

“…Such simulations can be used to generate synthetic data as shown by Hajilounezhad et al [38] where a scanning electron microscopy (SEM) simulation tool is used to get artificial images of a carbon nanotube forest along with the calculated properties of the structures used as ground truth. In another study, microstructure representations are generated using simulation models, which are then rendered to obtain simulated images [39]. Trampert et al [27] used Voronoi tessellations to generate synthetic polycrystalline microstructures: even though the statistical properties of the grain size distributions are only roughly comparable to those reported for real grain distributions, the degree of visual similarity and the type of contained features (e.g.…”

Section: Introductionmentioning

confidence: 99%

Deep learning of crystalline defects from TEM images: a solution for the problem of ‘never enough training data’

Govind,

Oliveros,

Dlouhy

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

Crystalline defects, such as line-like dislocations, play an important role for the performance and reliability of many metallic devices. Their interaction and evolution still poses a multitude of open questions to materials science and materials physics. In-situ TEM experiments can provide important insights into how dislocations behave and move. During such experiments, the dislocation microstructure is captured in form of videos. The analysis of individual video frames can provide useful insights but is limited by the capabilities of automated identification, digitization, and quantitative extraction of the dislocations as curved objects. The vast amount of data also makes manual annotation very time consuming, thereby limiting the use of Deep Learning-based, automated image analysis and segmentation of the dislocation microstructure.In this work, a parametric model for generating synthetic training data for segmentation of dislocations is developed. Even though domain scientists might dismiss synthetic training images sometimes as too artificial, our findings show that they can result in superior performance, particularly regarding the generalizing of the Deep Learning models with respect to different microstructures and imaging conditions. Additionally, we propose an enhanced deep learning method optimized for segmenting overlapping or intersecting dislocation lines. Upon testing this framework on four distinct real datasets, we find that our synthetic training data are able to yield high-quality results also on real images–even more so if fine-tune on a few real images was done. Our approach demonstrates the potential of synthetic data in overcoming the limitations of manual annotation in TEM, paving the way for more efficient and accurate analysis of dislocation microstructures. Last but not least, segmenting such thin, curvilinear structures is a task that is ubiquitous in many fields, which makes our method a potential candidate for other applications as well.

show abstract

“…For instance, Guda et al applied multivariate curve resolution methods on operando XANES spectra to isolate individual species/phases from the multicomponent data mixture in a catalyst system . Supervised ML techniques have been widely applied to establish a correspondence between spectra and target properties, either in a forward or inverse direction . A large body of work focused on the accurate inference of target properties from XANES.…”

Section: Introductionmentioning

confidence: 99%

Robust Machine Learning Inference from X-ray Absorption Near Edge Spectra through Featurization

Chen,

Hwang

et al. 2024

Chem. Mater.

Self Cite

View full text Add to dashboard Cite

X-ray absorption spectroscopy (XAS) is a commonly employed technique for characterizing functional materials. In particular, X-ray absorption near edge spectra (XANES) encode local coordination and electronic information, and machine learning approaches to extract this information are of significant interest. To date, most ML approaches for XANES have primarily focused on using the raw spectral intensities as input, overlooking the potential benefits of incorporating spectral transformations and dimensionality reduction techniques into ML predictions. In this work, we focused on systematically comparing the impact of different featurization methods on the performance of ML models for XAS analysis. We evaluated the classification and regression capabilities of these models on computed data sets and validated their performance on previously unseen experimental data sets. Our analysis revealed an intriguing discovery: the cumulative distribution function feature achieves both high prediction accuracy and exceptional transferability. This remarkably robust performance can be attributed to its tolerance to horizontal shifts in the spectra, which is crucial when validating models using experimental data. While this work exclusively focuses on XANES analysis, we anticipate that the methodology presented here will hold promise as a versatile asset to the broader spectroscopy community.

show abstract

Theory+AI/ML for microscopy and spectroscopy: Challenges and opportunities

Cited by 16 publications

References 89 publications

2023 Roadmap on molecular modelling of electrochemical energy materials

2023 Roadmap on molecular modelling of electrochemical energy materials

Deep learning of crystalline defects from TEM images: a solution for the problem of ‘never enough training data’

Robust Machine Learning Inference from X-ray Absorption Near Edge Spectra through Featurization

Contact Info

Product

Resources

About