Powered by OpenAIRE graph
Found an issue? Give us feedback
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/ ZENODOarrow_drop_down
image/svg+xml art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos Open Access logo, converted into svg, designed by PLoS. This version with transparent background. http://commons.wikimedia.org/wiki/File:Open_Access_logo_PLoS_white.svg art designer at PLoS, modified by Wikipedia users Nina, Beao, JakobVoss, and AnonMoos http://www.plos.org/
ZENODO
Other literature type . 2025
License: CC BY
Data sources: ZENODO
ZENODO
Research . 2025
License: CC BY
Data sources: Datacite
ZENODO
Research . 2025
License: CC BY
Data sources: Datacite
versions View all 2 versions
addClaim

Gli spettri ATR-IR di alcuni minerali analizzati tramite Autoencoder e K-means (ATR-IR spectra of some minerals analyzed using an Autoencoder and K-means)

Authors: Sparavigna, Amelia Carolina; Gemini (Modello Linguistico di Google);

Gli spettri ATR-IR di alcuni minerali analizzati tramite Autoencoder e K-means (ATR-IR spectra of some minerals analyzed using an Autoencoder and K-means)

Abstract

Questo studio presenta un approccio innovativo per l'analisi e la classificazione dei dati spettrali di minerali, combinando la spettroscopia ad Assorbimento Totale Attenuato (ATR) con un modello di autoencoder per la riduzione di dimensionalità e un algoritmo di clustering non supervisionato K-Means. L'obiettivo è esplorare le relazioni spettrali intrinseche tra i minerali e la capacità di un'intelligenza artificiale di raggrupparli in modo coerente e significativo. La ricerca ha dimostrato che la compressione dei dati spettrali tramite l'autoencoder crea una rappresentazione compatta nello spazio latente, che facilita un clustering più efficiente e interpretabile. Analisi successive con un numero crescente di cluster (fino a 44) hanno rivelato un equilibrio ottimale a 25 cluster, dove il modello ha separato con successo minerali distinti e ha identificato raggruppamenti naturali di minerali affini, come le zeoliti. I risultati confermano l'efficacia di questo metodo per la classificazione spettrale, offrendo un potente strumento per l'analisi geologica e mineralogica. This study presents an innovative approach for the analysis and classification of mineral spectral data, combining Attenuated Total Reflectance (ATR) spectroscopy with an autoencoder model for dimensionality reduction and an unsupervised K-Means clustering algorithm. The objective is to explore the intrinsic spectral relationships among minerals and an artificial intelligence's ability to group them in a coherent and meaningful way. The research demonstrated that compressing spectral data with the autoencoder creates a compact representation in the latent space, which facilitates more efficient and interpretable clustering. Subsequent analyses with an increasing number of clusters (up to 44) revealed an optimal balance at 25 clusters, where the model successfully separated distinct minerals and identified natural groupings of related minerals, such as zeolites. The results confirm the effectiveness of this method for spectral classification, offering a powerful tool for geological and mineralogical analysis.

Related Organizations
  • BIP!
    Impact byBIP!
    selected citations
    These citations are derived from selected sources.
    This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    0
    popularity
    This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
    Average
    influence
    This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
    Average
    impulse
    This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
    Average
Powered by OpenAIRE graph
Found an issue? Give us feedback
selected citations
These citations are derived from selected sources.
This is an alternative to the "Influence" indicator, which also reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Citations provided by BIP!
popularity
This indicator reflects the "current" impact/attention (the "hype") of an article in the research community at large, based on the underlying citation network.
BIP!Popularity provided by BIP!
influence
This indicator reflects the overall/total impact of an article in the research community at large, based on the underlying citation network (diachronically).
BIP!Influence provided by BIP!
impulse
This indicator reflects the initial momentum of an article directly after its publication, based on the underlying citation network.
BIP!Impulse provided by BIP!
0
Average
Average
Average
Green