Machine learning for recognizing minerals from multispectral data

Jahoda, Pavel; Drozdovskiy, Igor; Sauro, Francesco; Turchi, Leonardo; Payler, Samuel J.; Bessone, Loredana

doi:10.1039/d0an01483d

Cited by 33 publications

(29 citation statements)

References 42 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…Jahoda et al summarized and synthesized the previous methods and verified them. 10 Fan et al proposed the DeepCID approach to solve component identification problems. 11 Zhang et al described a transfer learning method using both CNNs and DNNs to improve the classification accuracy of organics.…”

Section: Introductionmentioning

confidence: 99%

Deeply-recursive convolutional neural network for Raman spectra identification

et al. 2022

View full text Add to dashboard Cite

show abstract

Section: Introductionmentioning

confidence: 99%

Deeply-recursive convolutional neural network for Raman spectra identification

et al. 2022

View full text Add to dashboard Cite

show abstract

“…For commonly used spectra-based techniques such as Laser Induced Breakdown Spectroscopy (LIBS) [29], Alpha Particle X-Ray Spectrometer (APSX) and Mass Spectroscopy for example, a peak at a specific wavelength will usually indicate a specific material substance and the result can be reproduced reliably, regardless of mitigating factors [30,31]. For Raman, that is not necessarily the case.…”

Section: Raman Technique Compatibility With Automation and Machine Learningmentioning

confidence: 99%

“…This, plus the results of various conditions under which that sample has been captured, lead to an intrinsic multi-variate uncertainty that suggests a complex problem space. The increasing application of machine learning in planetary science and space exploration for problems residing in complex problem spaces [4,7,16,28,29,[32][33][34][35][36][37][38][39][40][41], suggests an opportunity to further apply these techniques.…”

Section: Raman Technique Compatibility With Automation and Machine Learningmentioning

confidence: 99%

GRaVN: A Convolutional Network Approach to Generalised Characterisation of Raman Spectra for Space Exploration

Kissi¹,

Xie²,

McIsaac³

et al. 2021

Preprint

View full text Add to dashboard Cite

During planetary exploration mission operations, one of the key responsibilities of the instrument teams to determine data viability for subsequent analysis. During the 2019 CanMoon Lunar Sample Return Analogue Mission, the Lead Raman Specialist manually examined each spectra to provide quality assurance/validation. This non-trivial process requires years of experience to complete accurately. With the proven efficacy of Convolutional Neural Networks (CNNs) in classification tasks, and the increased use of automation and control loops on planetary space platforms for navigation and science targeting, an opportunity presents itself to approach this validation problem utilising CNNs. We present the Generalised Raman Validation Network (GRaVN), an neural network focused specifically on extracting the generalised structure of Raman spectra for quality assurance/validation. This work demonstrates the viability of utilising a CNN network in validation activities for Raman spectroscopy. Utilising only two hidden layers, a configuration was developed that provided good levels of accuracy on a manually curated dataset. This indicates that such a system could be useful as part of an autonomous control loop during planetary exploration activities.

show abstract

“…Artificial neural networks (ANNs) can be used as a robust classification method for a successful pyrochlore and microlite classification by Raman spectroscopy, since the literature reports studies with mineral, Raman, and machine learning. [14][15][16] ANNs mimic the function of biological neurons mainly concerning the gain of knowledge from their surroundings through the learning of the trialand-error process. [17] Moreover, they learn according to the environment, which enables their application to various fields of science.…”

mentioning

confidence: 99%

Prospection of pyrochlore and microlite mineral groups through Raman spectroscopy coupled with artificial neural networks

Queiroz

Andrade

2022

J Raman Spectroscopy

View full text Add to dashboard Cite

Niobium (Nb) and tantalum (Ta) concentrated in pyrochlore and microlite mineral groups, respectively, have attracted worldwide attention due to their importance to aerospace and electronics industries. This manuscript addresses the use of Raman spectroscopy coupled with artificial neural networks (ANNs) for improving the identification and characterization of mineral species belonging to pyrochlore and microlite mineral groups. Spectral data were collected in the 100–1400 cm−1 range and two baseline corrections, namely Asymmetric Least Squares (ALS) and Piecewise Linear Fitting (PLF) were performed and compared. In most cases, ALS achieved better performance in the removal of background noise with no elimination of important features of the original spectrum. The ANNs were fed with balanced datasets and based on different topologies with logistics, hyperbolic tangent, and rectified linear unit activation functions in the hidden layers.

show abstract

Machine learning for recognizing minerals from multispectral data

Abstract: Machine Learning (ML) has found several applications in spectroscopy, including recognizing minerals and estimating elemental composition. ML algorithms have been widely used on datasets from individual spectroscopy methods such as...

Cited by 33 publications

References 42 publications

Deeply-recursive convolutional neural network for Raman spectra identification

Deeply-recursive convolutional neural network for Raman spectra identification

GRaVN: A Convolutional Network Approach to Generalised Characterisation of Raman Spectra for Space Exploration

Prospection of pyrochlore and microlite mineral groups through Raman spectroscopy coupled with artificial neural networks

Contact Info

Product

Resources

About