arXiv subjects

Shoeb Athar

Publications and source records attributed to Shoeb Athar.

4 recordsLinked to original sources

arXiv2026

Robust Machine Learning Framework for Reliable Discovery of High-Performance Half-Heusler Thermoelectrics

Machine learning (ML) can facilitate efficient thermoelectric (TE) material discovery essential to address the environmental crisis. However, ML models often suffer from poor experimental generalizability despite high metrics. This study presents a robust workflow, applied to the half-Heusler (hH) structural prototype, for figure of merit (zT) prediction, to improve the generalizability of ML models. To resolve challenges in dataset handling and feature filtering, we first introduce a rigorous PCA-based splitting method that ensures training and test sets are unbiased and representative of the full chemical space. We then integrate Bayesian hyperparameter optimization with k-best feature filtering across three architectures-Random Forest, XGBoost, and Neural Networks - while employing SISSO symbolic regression for physical insight and comparison. Using SHAP and SISSO analysis, we identify A-site dopant concentration (xA'), and A-site Heat of Vaporization (HVA) as the primary drivers of zT besides Temperature (T). Finally, a high-throughput screening of approximately 6.6x10^8 potential compositions, filtered by stability constraints, yielded several novel high-zT candidates. Breaking from the traditional focus of improving test RMSE/R^2 values of the models, this work shifts the attention on establishing the test set a true proxy for model generalizability and strengthening the often neglected modules of the existing ML workflows for the data-driven design of next-generation thermoelectric materials.

cond-mat.mtrl-sci↗

arXiv2026

Beyond Predicted ZT: Machine Learning Strategies for the Experimental Discovery of Thermoelectric Materials

The discovery of high-performance thermoelectric (TE) materials for advancing green energy harvesting from waste heat is an urgent need in the context of looming energy crisis and climate change. The rapid advancement of machine learning (ML) has accelerated the design of thermoelectric (TE) materials, yet a persistent "gap" remains between high-accuracy computational predictions and their successful experimental validation. While ML models frequently report impressive test scores (R^2 values of 0.90-0.98) for complex TE properties (zT, power factor, and electrical/thermal conductivity), only a handful of these predictions have culminated in the experimental discovery of new high-zT materials. In this review, we identify and discuss that the primary obstacles are poor model generalizability-stemming from the "small-data" problem, sampling biases in cross-validation, and inadequate structural representation-alongside the critical challenge of thermodynamic phase stability. Moreover, we argue that standard randomized validation often overestimates model performance by ignoring "hidden hierarchies" and clustering within chemical families. Finally, to bridge this gap between ML-predictions and experimental realization, we advocate for advanced validation strategies like PCA-based sampling and a synergetic active learning loop that integrates ML "fast filters" for stability (e.g., GNoME) with high-throughput combinatorial thin-film synthesis to rapidly map stable, high-zT compositional spaces.

cond-mat.mtrl-sci↗

arXiv2025

Tackling dataset curation challenges towards reliable machine learning: a case study on thermoelectric materials

Machine Learning (ML) driven discovery of novel and efficient thermoelectric (TE) materials warrants experimental TE datasets of high volume, diversity, and quality. While the largest publicly available dataset, Starrydata2, has a high data volume, it contains inaccurate data due to the inherent limitations of Large Language Model (LLM)-assisted data curation, ambiguous nomenclature and complex formulas of materials in the literature. Another unaddressed issue is the inclusion of multi-source experimental data, with high standard deviations and without synthesis information. Using half-Heusler (hH) materials as an example, this work is aimed at first highlighting these errors and inconsistencies which cannot be filtered with conventional dataset curation workflows. We then propose a statistical round-robin error-based data filtering method to address these issues, a method that can be applied to filter any other material property. Lastly, a hybrid dataset creation workflow, involving data from Starrydata2 and manual extraction, is proposed and the resulting dataset is analyzed and compared against Starrydata2.

cond-mat.mtrl-sci↗

arXiv2025

Carbogels for sustainable and scalable thermoelectric applications

Thermoelectric generators (TEGs) based on commercially used thermal super-insulating materials can facilitate sustainable and large-scale ambient waste heat recovery while bequeathing an added economic and environmental value to thermal insulations in industry. This requires the optimization of the thermoelectric (TE) properties through electrical functionalization of such materials. Moreover, the associated engineering challenges of assembling TEG modules must be overcome. Herein, we propose using super-insulating Resorcinol-formaldehyde (RF) carbogels for scalable and sustainable TE applications through their electrical functionalization. Using a combination of a pyrolysis process and carbon fibers insertion, we achieved an increment by 12 orders of magnitude in electrical conductivity as well as ZT whilst retaining their intrinsic ultralow thermal conductivity (<50 mW/mK). A TE module in the form of a thermoelectric vacuum insulation panel (TVIP), was then fabricated using only a p-type material, to demonstrate a proof-of-concept self-powered WiFi-based vacuum-failure detection application in confined spaces in automobiles or aeronautics. Finally, by extrapolating the optimized output power and with a CAD-assisted assembly of a large TEG module (1000 cm2), the potential of scalable low-grade waste heat recovery is discussed.

physics.app-ph↗