arXiv subjects

Valentin Stanev

Publications and source records attributed to Valentin Stanev.

At least 19 recordsLinked to original sources

arXiv2025

Topic Modeling and Link-Prediction for Material Property Discovery

Link prediction infers missing or future relations between graph nodes, based on connection patterns. Scientific literature networks and knowledge graphs are typically large, sparse, and noisy, and often contain missing links between entities. We present an AI-driven hierarchical link prediction framework that integrates matrix factorization to infer hidden associations and steer discovery in complex material domains. Our method combines Hierarchical Nonnegative Matrix Factorization (HNMFk) and Boolean matrix factorization (BNMFk) with automatic model selection, as well as Logistic matrix factorization (LMF), we use to construct a three-level topic tree from a 46,862-document corpus focused on 73 transition-metal dichalcogenides (TMDs). These materials are studied in a variety of physics fields with many current and potential applications. An ensemble BNMFk + LMF approach fuses discrete interpretability with probabilistic scoring. The resulting HNMFk clusters map each material onto coherent topics like superconductivity, energy storage, and tribology. Also, missing or weakly connected links are highlight between topics and materials, suggesting novel hypotheses for cross-disciplinary exploration. We validate our method by removing publications about superconductivity in well-known superconductors, and show the model predicts associations with the superconducting TMD clusters. This shows the method finds hidden connections in a graph of material to latent topic associations built from scientific literature, especially useful when examining a diverse corpus of scientific documents covering the same class of phenomena or materials but originating from distinct communities and perspectives. The inferred links generating new hypotheses, produced by our method, are exposed through an interactive Streamlit dashboard, designed for human-in-the-loop scientific discovery.

cs.LG↗

arXiv2025

Rapid analysis of point-contact Andreev reflection spectra via machine learning with adaptive data augmentation

Delineating the superconducting order parameters is a pivotal task in investigating superconductivity for probing pairing mechanisms, as well as their symmetry and topology. Point-contact Andreev reflection (PCAR) measurement is a simple yet powerful tool for identifying the order parameters. The PCAR spectra exhibit significant variations depending on the type of the order parameter in a superconductor, including its magnitude ($\mathit{\Delta}$), as well as temperature, interfacial quality, Fermi velocity mismatch, and other factors. The information on the order parameter can be obtained by finding the combination of these parameters, generating a theoretical spectrum that fits a measured experimental spectrum. However, due to the complexity of the spectra and the high dimensionality of parameters, extracting the fitting parameters is often time-consuming and labor-intensive. In this study, we employ a convolutional neural network (CNN) algorithm to create models for rapid and automated analysis of PCAR spectra of various superconductors with different pairing symmetries (conventional $s$-wave, chiral $p_x+ip_y$-wave, and $d_{x^2-y^2}$-wave). The training datasets are generated based on the Blonder-Tinkham-Klapwijk (BTK) theory and further modified and augmented by selectively incorporating noise and peaks according to the bias voltages. This approach not only replicates the experimental spectra but also brings the model's attention to important features within the spectra. The optimized models provide fitting parameters for experimentally measured spectra in less than 100 ms per spectrum. Our approaches and findings pave the way for rapid and automated spectral analysis which will help accelerate research on superconductors with complex order parameters.

cond-mat.supr-con↗

arXiv2024

HEAL: Hierarchical Embedding Alignment Loss for Improved Retrieval and Representation Learning

Retrieval-Augmented Generation (RAG) enhances Large Language Models (LLMs) by integrating external document retrieval to provide domain-specific or up-to-date knowledge. The effectiveness of RAG depends on the relevance of retrieved documents, which is influenced by the semantic alignment of embeddings with the domain's specialized content. Although full fine-tuning can align language models to specific domains, it is computationally intensive and demands substantial data. This paper introduces Hierarchical Embedding Alignment Loss (HEAL), a novel method that leverages hierarchical fuzzy clustering with matrix factorization within contrastive learning to efficiently align LLM embeddings with domain-specific content. HEAL computes level/depth-wise contrastive losses and incorporates hierarchical penalties to align embeddings with the underlying relationships in label hierarchies. This approach enhances retrieval relevance and document classification, effectively reducing hallucinations in LLM outputs. In our experiments, we benchmark and evaluate HEAL across diverse domains, including Healthcare, Material Science, Cyber-security, and Applied Maths.

cs.IR↗

arXiv2021

Topic Analysis of Superconductivity Literature by Semantic Non-negative Matrix Factorization

We utilize a recently developed topic modeling method called SeNMFk, extending the standard Non-negative Matrix Factorization (NMF) methods by incorporating the semantic structure of the text, and adding a robust system for determining the number of topics. With SeNMFk, we were able to extract coherent topics validated by human experts. From these topics, a few are relatively general and cover broad concepts, while the majority can be precisely mapped to specific scientific effects or measurement techniques. The topics also differ by ubiquity, with only three topics prevalent in almost 40 percent of the abstract, while each specific topic tends to dominate a small subset of the abstracts. These results demonstrate the ability of SeNMFk to produce a layered and nuanced analysis of large scientific corpora.

cs.DL↗

arXiv2020

CRYSPNet: Crystal Structure Predictions via Neural Network

Structure is the most basic and important property of crystalline solids; it determines directly or indirectly most materials characteristics. However, predicting crystal structure of solids remains a formidable and not fully solved problem. Standard theoretical tools for this task are computationally expensive and at times inaccurate. Here we present an alternative approach utilizing machine learning for crystal structure prediction. We developed a tool called Crystal Structure Prediction Network (CRYSPNet) that can predict the Bravais lattice, space group, and lattice parameters of an inorganic material based only on its chemical composition. CRYSPNet consists of a series of neural network models, using as inputs predictors aggregating the properties of the elements constituting the compound. It was trained and validated on more than 100,000 entries from the Inorganic Crystal Structure Database. The tool demonstrates robust predictive capability and outperforms alternative strategies by a large margin. Made available to the public (at https://github.com/AuroraLHT/cryspnet), it can be used both as an independent prediction engine or as a method to generate candidate structures for further computational and/or experimental validation.

cond-mat.mtrl-sci↗

arXiv2019

Materials development by interpretable machine learning

Machine learning technologies are expected to be great tools for scientific discoveries. In particular, materials development (which has brought a lot of innovation by finding new and better functional materials) is one of the most attractive scientific fields. To apply machine learning to actual materials development, collaboration between scientists and machine learning is becoming inevitable. However, such collaboration has been restricted so far due to black box machine learning, in which it is difficult for scientists to interpret the data-driven model from the viewpoint of material science and physics. Here, we show a material development success story that was achieved by good collaboration between scientists and one type of interpretable (explainable) machine learning called factorized asymptotic Bayesian inference hierarchical mixture of experts (FAB/HMEs). Based on material science and physics, we interpreted the data-driven model constructed by the FAB/HMEs, so that we discovered surprising correlation and knowledge about thermoelectric material. Guided by this, we carried out actual material synthesis that led to identification of a novel spin-driven thermoelectric material with the largest thermopower to date.

cond-mat.mtrl-sci↗

arXiv2018

High-throughput investigation of tunable superconductivity in FeSe films

There is an ongoing debate about the relative importance of structural change versus doping charge carriers on the mechanism of superconductivity in Fe-based materials. Elucidating this issue is a major challenge since it would require a large number of samples where structure properties or the carrier density is systematically varied. FeSe, with its structural simplicity, is an ideal platform for addressing this question. It has been demonstrated that the superconductivity in this material can be controlled through crystal lattice tuning, as well as electronic structure manipulation. Here, we apply a high-throughput methodology to FeSe to systematically delineate the interdependence of its structural and electronic properties. Using a dual-beam pulsed laser deposition, we have generated FeSe films with a marked gradient in the superconducting transition temperature (below 2 K < Tc < 12 K) across 1 cm width of the films. The Tc gradient films display ~ 1% continuous stretch and compression in the out-of-plane and in-plane lattice constants respectively, triggering the continuous enhancement of superconductivity. Combining transport and angular-resolved photoemission measurements on uniform FeSe films with tunable Tc from 3 K to 14 K, we find that the electron carrier density is intimately correlated with Tc, i.e., it increases by a factor of 6 and ultimately surpasses the almost constant hole concentration. Our transmission electron microscope and band structure calculations reveal that rather than by shifting the chemical potential, the enhanced superconductivity is linked to the selective adjustment of the dxy band dispersion across the Fermi level by means of reduced local lattice distortions. Therefore, such novel mechanism provides a key to understand discrete superconducting phases in FeSe.

cond-mat.supr-con↗

arXiv2018

Observation of perfect Andreev reflection due to Klein paradox in a topological superconducting state

In 1928, P. Dirac proposed a new wave equation to describe relativistic electrons. Shortly afterwards, O. Klein solved a simple potential step problem for the Dirac equation and stumbled upon an apparent paradox - the potential becomes transparent when the height is larger than the electron energy. For massless particles, backscattering is completely forbidden in Klein tunneling, leading to perfect transmission through any potential barrier. Recent advent of condensed matter systems with Dirac-like excitations, such as graphene and topological insulators (TIs), has opened the possibility of observing the Klein tunneling experimentally. In the surface states of TIs, fermions are bound by spin-momentum locking, and are thus immune to backscattering due to time-reversal symmetry. Here we report the observation of perfect Andreev reflection in point contact spectroscopy - a clear signature of Klein tunneling and a manifestation of the underlying relativistic physics of a proximity-induced superconducting state in a topological Kondo insulator.

cond-mat.mes-hall↗

arXiv2018

Machine-learning guided discovery of a high-performance spin-driven thermoelectric material

Thermoelectric conversion using Seebeck effect for generation of electricity is becoming an indispensable technology for energy harvesting and smart thermal management. Recently, the spin-driven thermoelectric effects (STEs), which employ emerging phenomena such as the spin-Seebeck effect (SSE) and the anomalous Nernst effect (ANE), have garnered much attention as a promising path towards low cost and versatile thermoelectric technology with easily scalable manufacturing. However, progress in development of STE devices is hindered by the lack of understanding of the mechanism and materials parameters that govern the STEs. To address this problem, we enlist machine learning modeling to establish the key physical parameters controlling SSE. Guided by these models, we have carried out a high-throughput experiment which led to the identification of a novel STE material with a thermopower an order of magnitude larger than that of the current generation STE devices.

cond-mat.mtrl-sci↗

arXiv2018

Unsupervised Phase Mapping of X-ray Diffraction Data by Nonnegative Matrix Factorization Integrated with Custom Clustering

Analyzing large X-ray diffraction (XRD) datasets is a key step in high-throughput mapping of the compositional phase diagrams of combinatorial materials libraries. Optimizing and automating this task can help accelerate the process of discovery of materials with novel and desirable properties. Here, we report a new method for pattern analysis and phase extraction of XRD datasets. The method expands the Nonnegative Matrix Factorization method, which has been used previously to analyze such datasets, by combining it with custom clustering and cross-correlation algorithms. This new method is capable of robust determination of the number of basis patterns present in the data which, in turn, enables straightforward identification of any possible peak-shifted patterns. Peak-shifting arises due to continuous change in the lattice constants as a function of composition, and is ubiquitous in XRD datasets from composition spread libraries. Successful identification of the peak-shifted patterns allows proper quantification and classification of the basis XRD patterns, which is necessary in order to decipher the contribution of each unique single-phase structure to the multi-phase regions. The process can be utilized to determine accurately the compositional phase diagram of a system under study. The presented method is applied to one synthetic and one experimental dataset, and demonstrates robust accuracy and identification abilities.

cond-mat.mtrl-sci↗

arXiv2017

Machine learning modeling of superconducting critical temperature

Superconductivity has been the focus of enormous research effort since its discovery more than a century ago. Yet, some features of this unique phenomenon remain poorly understood; prime among these is the connection between superconductivity and chemical/structural properties of materials. To bridge the gap, several machine learning schemes are developed herein to model the critical temperatures ($T_{\mathrm{c}}$) of the 12,000+ known superconductors available via the SuperCon database. Materials are first divided into two classes based on their $T_{\mathrm{c}}$ values, above and below 10 K, and a classification model predicting this label is trained. The model uses coarse-grained features based only on the chemical compositions. It shows strong predictive power, with out-of-sample accuracy of about 92%. Separate regression models are developed to predict the values of $T_{\mathrm{c}}$ for cuprate, iron-based, and "low-$T_{\mathrm{c}}$" compounds. These models also demonstrate good performance, with learned predictors offering potential insights into the mechanisms behind superconductivity in different families of materials. To improve the accuracy and interpretability of these models, new features are incorporated using materials data from the AFLOW Online Repositories. Finally, the classification and regression models are combined into a single integrated pipeline and employed to search the entire Inorganic Crystallographic Structure Database (ICSD) for potential new superconductors. We identify more than 30 non-cuprate and non-iron-based oxides as candidate materials.

cond-mat.supr-con↗

arXiv2015

Time-reversal symmetry breaking state in dirty three-band superconductor

I study the effects of disorder on the superconductivity of a three-band model with repulsive interband pairing. Such a model can support several possible superconducting order parameters, including a complex time-reversal symmetry breaking (TRSB) state. Impurity scattering suppresses the critical temperature of all these states, but the complex state survives, and remains a part of the phase diagram of the model even in the presence of moderate amount of disorder. This means that the TRSB states could be experimentally accessible in multiband materials like iron pnictides and chalcogenides.

cond-mat.supr-con↗

arXiv2015

Nonequilibrium enhancement of high-temperature superconductivity in a 3D model of cuprates

Recent experiments in the cuprates have seen evidence of a transient superconducting state upon optical excitation polarized along the c-axis [R. Mankowsky et al., Nature 516, 71 (2014)]. Motivated by these experiments we propose an extension of the single-layer $t-J-V$ model of cuprates to three dimensions in order to study the effects of inter-plane tunneling on the competition between superconductivity and bond density wave order. We find that an optical pump can suppress the charge order and simultaneously enhance superconductivity, due to the inherent competition between the two. We also provide an intuitive picture of the physical mechanism underlying this effect. Furthermore, based on a simple Floquet theory we estimate the magnitude of the enhancement.

cond-mat.supr-con↗

arXiv2014

Excitonic and Nematic Instabilities on the Surface of Topological Kondo Insulators

We study the effects of strong electron-electron interactions on the surface of cubic topological Kondo insulators (such as samarium hexaboride, SmB$_6$). Cubic topological Kondo insulators generally support three copies of massless Dirac nodes on the surface, but only two of them are energetically degenerate and exhibit an energy offset relative to the third one. With a tunable chemical potential, when the surface states host electron and hole pockets of comparable size, strong interactions may drive this system into rotational symmetry breaking nematic and translational symmetric breaking excitonic spin- or charge-density-wave phases, depending on the relative chirality of the Dirac cones. Taking a realistic surface band structure into account we analyze the associated Ginzburg-Landau theory and compute the mean field phase diagram for interacting surface states. Beyond mean field theory, this system can be described by a two-component isotropic Ashkin-Teller model at finite temperature, and we outline the phase diagram of this model. Our theory provides a possible explanation of recent measurements which detect a two-fold symmetric magnetoresistance and an upturn in surface resistivity with tunable gate voltage in SmB$_6$. Our discussion can also be germane to other cubic topological insulators, such as ytterbium hexaboride (YbB$_6$), plutonium hexaboride (PuB$_6$).

cond-mat.mes-hall↗

arXiv2014

Long range $p$-wave proximity effect into a disordered metal

We use quasiclassical methods of superconductivity to study the superconducting proximity effect from a topological $p$-wave superconductor into a disordered one-dimensional metallic wire. We demonstrate that the corresponding Eilenberger equations with disorder reduce to a closed non-linear equation for the superconducting component of the matrix Green's function. Remarkably, this equation is formally equivalent to a classical mechanical system (i.e., Newton's equations), with the Green function corresponding to a coordinate of a fictitious particle and the coordinate along the wire corresponding to time. This mapping allows to obtain exact solutions in the disordered nanowire in terms of elliptic functions. A surprising result that comes out of this solution is that the $p$-wave superconductivity proximity-induced into the disordered metal remains long-range, decaying as slowly as the conventional $s$-wave superconductivity. It is also shown that impurity scattering leads to the appearance of a zero-energy peak.

cond-mat.supr-con↗

arXiv2014

Study of antiferromagnetic and nematic phase transitions in $BaFe_2(As_{1-x}P_x)_2$ by AC micro-calorimetry and SQUID magnetometry

We study the antiferromagnetic (AFM) and structural phase transitions in single crystal $BaFe_2(As_{1-x}P_x)_2$ $(x=0, 0.3)$ at temperatures $T_N$ and $T_S$, respectively, by high resolution ac microcalorimetry and SQUID magnetometry. The specific heat measurements of both as grown and annealed $BaFe_2As_2$ displays a sharp peak at the AFM/Structural transitions. A kink in the entropy of annealed $BaFe_2As_2$ gives evidence for splitting of the two transitions by approximately 0.5K. No additional features could be identified in the specific heat of both $BaFe_2As_2$ and $BaFe_2(As_{0.7}P_{0.3})_2$ in the temperature regions around $T^*$ > $T_S$ where torque measurements [S. Kasahara et al., Nature 486, 382 (2012)] had revealed the "true" nematic phase transition, indicating that the behavior at $T^*$ does not represent a 2nd order phase transition, and that the phase transition of $BaFe_2(As_{1-x}P_x)_2$ into the orthorhombic phase does occur at $T_S$.

cond-mat.supr-con↗

arXiv2014

Quasiclassical Eilenberger theory of the topological proximity effect in a superconducting nanowire

We use the quasiclassical Eilenberger theory to study the topological superconducting proximity effects between a segment of a nanowire with a p-wave order parameter and a metallic segment. This model faithfully represents key qualitative features of an experimental setup, where only a part of a nanowire is in immediate contact with a bulk superconductor, inducing topological superconductivity. It is shown that the Eilenberger equations represent a viable alternative to the Bogoliubov-de Gennes theory of the topological superconducting heterostructures and provide a much simpler quantitative description of some observables. For our setup, we obtain exact analytical solutions for the quasiclassical Green's functions and the density of states as a function of position and energy. The correlations induced by the boundary involve terms associated with both p-wave and odd-frequency pairing, which are intertwined and contribute to observables on an equal footing. We recover the signatures of the standard Majorana mode near the end of the superconducting segment, but find no such localized mode induced in the metallic segment. Instead, the zero-bias feature is spread out across the entire metallic part in accordance with the previous works. In shorter wires, the Majorana mode and delocalized peak split up away from zero energy. For long metallic segments, non-topological Andreev bound states appear and eventually merge together, giving rise to a gapless superconductor.

cond-mat.supr-con↗

arXiv2013

Complex state induced by impurities in multiband superconductors

We study the role of impurities in a two-band superconductor, and elucidate the nature of the recently predicted transition from s_{+-} state to s_{++} state induced by interband impurity scattering. Using a Ginzburg-Landau theory, derived from microscopic equations, we demonstrate that close to T_c this transition is necessarily a direct one, but deeper in the superconducting state an intermediate complex state appears. This state has a distinct order parameter, which breaks the time-reversal symmetry, and is separated from the s_{+-} and s_{++} states by phase transitions. Based on our results, we suggest a phase diagram for systems with weak repulsive interband pairing, and discuss its relevance to iron-based superconductors.

cond-mat.supr-con↗