Applications of machine learning in spectroscopy

Ramírez, Carlos; Greenop, Michael; Ashton, Lorna; Rehman, Ihtesham Ur

doi:10.1080/05704928.2020.1859525

“…Another particularly promising area of ML in assisting the R&D of energy storage materials is the enhancement of characterization techniques, including microscopy processing [154,[176][177][178] and spectroscopy analysis. [179][180][181] Here, we mainly focus on recent applications of ML on image analysis to demonstrate the power of ML on recognition and classification. In materials science, it is highly desirable to characterize the local behaviors from nanoscale to microscale, which are closely correlated to the macroscopic properties of materials.…”

Section: Assisting Experimentation and Characterizationmentioning

confidence: 99%

Machine learning in energy storage materials

Shen

¹

,

Liu

²

,

Shen

³

et al. 2022

Interdisciplinary Materials

View full text Add to dashboard Cite

With its extremely strong capability of data analysis, machine learning has shown versatile potential in the revolution of the materials research paradigm. Here, taking dielectric capacitors and lithium-ion batteries as two representative examples, we review substantial advances of machine learning in the research and development of energy storage materials. First, a thorough discussion of the machine learning framework in materials science is presented. Then, we summarize the applications of machine learning from three aspects, including discovering and designing novel materials, enriching theoretical simulations, and assisting experimentation and characterization. Finally, a brief outlook is highlighted to spark more insights on the innovative implementation of machine learning in materials science.

show abstract

“…with outlier rejection and smoothing), or ii) to automate processing of spectra with fully autonomous algorithms, [7,25,55,56] or iii) to implement data-driven analysis via dimensionality reduction techniques [57,58] and trained machine learning models. [59]…”

Section: Discussionmentioning

confidence: 99%

PRISMA: A robust and intuitive tool for high-throughput processing of chemical spectra

Flores

¹

,

Mozhzhukhina

²

,

Li

³

et al. 2021

Preprint

View full text Add to dashboard Cite

The popularization of high-throughput spectroscopies to characterize functional materials requires the simultaneous development of new analysis tools to efficiently process large numbers of measurements into scientifically meaningful observables. Here we introduce PRISMA, an open-source tool to rapidly analyze hundreds of spectra in a semi-automated way. PRISMA follows a human-in-the-loop workflow, where the user interacts with an intuitive graphical user interface (GUI) to control multiple steps in the spectrum analysis process: trimming, baseline correction, and peak fitting. The user tunes the analysis in real-time and applies the optimal parameters to all spectra, outputting processed results in an easy-to-read csv format within seconds. Crucially, the tuned parameters are stored to guarantee the full reproducibility of the analysis. We describe the functionalities implemented in PRISMA and test its capabilities with three experimental cases relevant to the study of electrochemical energy storage and conversion devices: temperature-dependent Raman measurement of phase transitions, a linear Raman mapping of a graphite composite electrode, and an operando X-ray diffraction experiment of LiNiO2 Li-ion electrode. Even if X-ray diffraction is not a spectroscopic technique, diffraction patterns are represented as one-dimensional arrays of counts equally suitable for analysis with PRISMA. The case studies demonstrate the robustness of the app and its ability to unearth insightful trends in peak parameters, which are easier to represent, interpret and further analyze with more advanced techniques.

show abstract

“…with outlier rejection and smoothing), or ii) to automate processing of spectra with fully autonomous algorithms, [7,24,54,55] or iii) to implement data-driven analysis via dimensionality reduction techniques [56,57] and trained machine learning models. [58]…”

Section: Discussionmentioning

confidence: 99%

PRISMA: A robust and intuitive tool for high-throughput processing of chemical spectra

Flores

¹

,

Mozhzhukhina

²

,

Li

³

et al. 2021

Preprint

View full text Add to dashboard Cite

The popularization of high-throughput spectroscopies to characterize functional materials requires the simultaneous development of new analysis tools to efficiently process large numbers of measurements into scientifically meaningful observables. Here we introduce PRISMA, an open-source tool to rapidly analyze hundreds of spectra in a semi-automated way. PRISMA follows a human-in-the-loop workflow, where the user interacts with an intuitive graphical user interface (GUI) to control multiple steps in the spectrum analysis process: trimming, baseline correction, and peak fitting. The user tunes the analysis in real-time and applies the optimal parameters to all spectra, outputting processed results in an easy-to-read csv format within seconds. Crucially, the tuned parameters are stored to guarantee the full reproducibility of the analysis. We describe the functionalities implemented in PRISMA and test its capabilities with three experimental cases relevant to the study of electrochemical energy storage and conversion devices: temperature-dependent Raman measurement of phase transitions, a linear Raman mapping of a graphite composite electrode, and an operando X-ray diffraction experiment of LiNiO2 Li-ion electrode. Even if X-ray diffraction is not a spectroscopic technique, diffraction patterns are represented as one-dimensional arrays of counts equally suitable for analysis with PRISMA. The case studies demonstrate the robustness of the app and its ability to unearth insightful trends in peak parameters, which are easier to represent, interpret and further analyze with more advanced techniques.

show abstract

Applications of machine learning in spectroscopy

Cited by 93 publications

References 109 publications

Machine learning in energy storage materials

Machine learning in energy storage materials

PRISMA: A robust and intuitive tool for high-throughput processing of chemical spectra

PRISMA: A robust and intuitive tool for high-throughput processing of chemical spectra

Contact Info

Product

Resources

About