arXiv subjects

Puneet Mishra

Publications and source records attributed to Puneet Mishra.

5 recordsLinked to original sources

arXiv2025

A MATLAB tutorial on deep feature extraction combined with chemometrics for analytical applications

Background In analytical chemistry, spatial information about materials is commonly captured through imaging techniques, such as traditional color cameras or with advanced hyperspectral cameras and microscopes. However, efficiently extracting and analyzing this spatial information for exploratory and predictive purposes remains a challenge, especially when using traditional chemometric methods. Recent advances in deep learning and artificial intelligence have significantly enhanced image processing capabilities, enabling the extraction of multiscale deep features that are otherwise challenging to capture with conventional image processing techniques. Despite the wide availability of open-source deep learning models, adoption in analytical chemistry remains limited because of the absence of structured, step-by-step guidance for implementing these models. Results This tutorial aims to bridge this gap by providing a step-by-step guide for applying deep learning approaches to extract spatial information from imaging data and integrating it with other data sources, such as spectral information. Importantly, the focus of this work is not on training deep learning models for image processing but on using existing open source models to extract deep features from imaging data. Significance The tutorial provides MATLAB code tutorial demonstrations, showcasing the processing of imaging data from various imaging modalities commonly encountered in analytical chemistry. Readers must run the tutorial steps on their own datasets using the codes presented in this tutorial.

cs.CV↗

arXiv2025

Transforming Hyperspectral Images Into Chemical Maps: A Novel End-to-End Deep Learning Approach

Current approaches to chemical map generation from hyperspectral images are based on models such as partial least squares (PLS) regression, generating pixel-wise predictions that do not consider spatial context and suffer from a high degree of noise. This study proposes an end-to-end deep learning approach using a modified version of U-Net and a custom loss function to directly obtain chemical maps from hyperspectral images, skipping all intermediate steps required for traditional pixel-wise analysis. This study compares the U-Net with the traditional PLS regression on a real dataset of pork belly samples with associated mean fat reference values. The U-Net obtains a test set root mean squared error that is 7% lower than that of PLS regression on the task of mean fat prediction. At the same time, U-Net generates fine detail chemical maps where 99.91% of the variance is spatially correlated. Conversely, only 2.37% of the variance in the PLS-generated chemical maps is spatially correlated, indicating that each pixel-wise prediction is largely independent of neighboring pixels. Additionally, while the PLS-generated chemical maps contain predictions far beyond the physically possible range of 0-100%, U-Net learns to stay inside this range. Thus, the findings of this study indicate that U-Net is superior to PLS for chemical map generation.

cs.CV↗

arXiv2016

Two-dimensional atomic layer-molecule hybrid superconductors with controllable exchange coupling

The coexistence and competition of superconductivity and magnetism can lead to a variety of rich physics and technological applications. Recent discovery of atomic-layer superconductors and self-assembly of magnetic molecules on solid surfaces should allow one to create a new two-dimensional (2D) hybrid superconducting system, but its possibility has never been fully investigated so far. Here we report the fabrication of highly ordered 2D hybrid superconductors based on indium atomic layers on silicon surfaces and magnetic metal-phthalocyanines (MPc) and clarify their detailed structural, superconducting and magnetic properties. Our primary findings include a substantial controllability of the superconducting transition temperatures (Tc) through substitution of central metal ions (M = Cu, Fe, Mn) of the molecules. This is attributed to charge transfers between the magnetic molecules and the superconducting layers and to different degrees of exchange coupling between them, which originates from anisotropic distributions of the relevant d-orbitals. The present study opens a route for designing and creating exotic 2D superconductors with an atomic-scale precision.

cond-mat.supr-con↗

arXiv2011

Macroscopic Superconducting Current through a Silicon Surface Reconstruction with Indium Adatoms: Si(111)-(R7$\times$R3)-In

Macroscopic and robust supercurrents are observed by direct electron transport measurements on a silicon surface reconstruction with In adatoms (Si(111)-(R7xR3)-In). The superconducting transition manifests itself as an emergence of the zero resistance state below 2.8 K. $I-V$ characteristics exhibit sharp and hysteretic switching between superconducting and normal states with well-defined critical and retrapping currents. The two-dimensional (2D) critical current density $J_\mathrm{2D,c}$ is estimated to be as high as $1.8 \ \mathrm{A/m}$ at 1.8 K. The temperature dependence of $J_\mathrm{2D,c}$ indicates that the surface atomic steps play the role of strongly coupled Josephson junctions.

cond-mat.mes-hall↗

arXiv2011

One-dimensional surface states on a striped Ag thin film with stacking fault arrays

One-dimensional (1D) stripe structures with a periodicity of 1.3 nm are formed by introduction of stacking fault arrays into a Ag thin film. The surface states of such striped Ag thin films are studied using a low temperature scanning tunneling microscope. Standing waves running in the longitudinal direction and characteristic spectral peaks are observed by differential conductance (dI/dV) measurements, revealing the presence of 1D states on the surface stripes. Their formation can be attributed to quantum confinement of Ag(111) surface states into a stripe by stacking faults. To quantify the degree of confinement, the effective potential barrier at the stacking fault for Ag(111) surface states is estimated from independent measurements. A single quantum well model with the effective potential barrier can reproduce the main features of dI/dV spectra on stripes, while a Kronig-Penney model fails to do so. Thus the present system should be viewed as decoupled 1D states on individual stripes rather than as anisotropic 2D Bloch states extending over a stripe array.

cond-mat.mes-hall↗