The carbon cost of materials discovery: Can machine learning really accelerate the discovery of new photovoltaics?
Year: 2025
Type: article
Abstract: emissions associated with each computational strategy, we evaluate the trade-offs between predictive efficacy and environmental cost. Our results reveal multiple hybrid ML/DFT strategies that optimize different points along the accuracy-emissions front. We find that direct prediction of scalar quantities, such as maximum efficiency, is significantly more tractable than using predicted absorption spectra as an intermediate step. Interestingly, ML models trained on DFT data can outperform DFT workflows using alternative exchange-correlation functionals in screening applications, highlighting the consistency and utility of data-driven approaches. We also assess strategies to improve ML-driven screening through expanded datasets and improved model architectures tailored to PV-relevant features. This work provides a quantitative framework for building low-emission, high-throughput discovery pipelines.
Source: Materials Horizons
DOI: 10.1039/d5mh01404b
Authors: Matthew Walker, Keith T. Butler
Institution: University College London
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Open Access status: hybrid
Awards: Deep Learning with Limited Data for Battery Materials Design, Materials Chemistry HEC Consortium (MCC), G243872479, Designing and optimizing polar photovoltaics with physics informed machine learning, The Materials and Molecular Modelling Hub, G417250887, Tier 2 Hub in Materials and Molecular Modelling, Introducing heterogeneous HPC solutions to UK's MMM community, G8997374688, G90098195
OpenAlex ID: W4417258371