Decoding structure-spectrum relationships with physically organized latent spaces DOI
Zhu Liang, Matthew R. Carbone, Wei Chen

et al.

Physical Review Materials, Journal Year: 2023, Volume and Issue: 7(5)

Published: May 16, 2023

A semisupervised machine learning method for the discovery of structure-spectrum relationships is developed and then demonstrated using specific example interpreting x-ray absorption near-edge structure (XANES) spectra. This constructs a one-to-one mapping between individual descriptors spectral trends. Specifically, an adversarial autoencoder augmented with rank constraint (RankAAE). The RankAAE methodology produces continuous interpretable latent space, where each dimension can track descriptor. As part this process, model provides robust quantitative measure relationship by decoupling intertwined contributions from multiple structural characteristics. makes it ideal interpretation descriptors. capability procedure showcased considering five local database >50 000 simulated XANES spectra across eight first-row transition metal oxide families. resulting not only reproduce known trends in literature but also reveal unintuitive ones that are visually indiscernible large datasets. results suggest has great potential to assist researchers complex scientific data, testing physical hypotheses, revealing patterns extend insight.

Language: Английский

Calculating the Precision of Student-Generated Datasets Using RStudio DOI
Joseph Chiarelli, Melissa A. St. Hilaire, Brandi L. Baldock

et al.

Journal of Chemical Education, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 24, 2025

Language: Английский

Citations

1
Research Acceleration in Self‐Driving Labs: Technological Roadmap toward Accelerated Materials and Molecular Discovery DOI Creative Commons
Fernando Delgado‐Licona, Milad Abolhasani

Advanced Intelligent Systems, Journal Year: 2022, Volume and Issue: 5(4)

Published: Dec. 23, 2022

The urgency of finding solutions to global energy, sustainability, and healthcare challenges has motivated rethinking the conventional chemistry material science workflows. Self‐driving labs, emerged through integration disruptive physical digital technologies, including robotics, additive manufacturing, reaction miniaturization, artificial intelligence, have potential accelerate pace materials molecular discovery by 10–100X. Using autonomous robotic experimentation workflows, self‐driving labs enable access a larger part chemical universe reduce time‐to‐solution an iterative hypothesis formulation, intelligent experiment selection, automated testing. By providing data‐centric abstraction accelerated cycle, in this perspective article, required hardware software technological infrastructure unlock true is discussed. In particular, process intensification as accelerator mechanism for modules digitalization strategies further cycle sciences are

Language: Английский

Citations

31
Atlas: A Brain for Self-driving Laboratories DOI Creative Commons
Riley J. Hickman, Malcolm Sim, Sergio Pablo‐García

et al.

Published: Sept. 5, 2023

Self-driving laboratories (SDLs) are next-generation research and development platforms for closed-loop, autonomous experimentation that combine ideas from artificial intelligence, robotics, high-performance computing. A critical component of SDLs is the decision-making algorithm used to prioritize experiments be performed. This SDL “brain” often relies on optimization strategies guided by machine learning models, such as Bayesian optimization. However, diversity hardware constraints scientific questions being tackled require availability a set flexible algorithms have yet implemented in single software tool. Here, we report Atlas, an application-agnostic Python library specifically tailored needs SDLs. Atlas provides facile access state-of-the-art, model-based algorithms—including mixed-parameter, multi-objective, constrained, robust, multi-fidelity, meta-learning, molecular optimization—as all-in-one tool expected suit majority specialized needs. After brief description its core capabilities, demonstrate Atlas’ utility optimizing oxidation potential metal complexes with electrochemical platform. We expect expand breadth design discovery problems natural sciences immediately addressable

Language: Английский

Citations

21
Recent advances and applications of machine learning in electrocatalysis DOI Open Access
You Hu, Junhua Chen, Zheng Wei

et al.

Journal of Materials Informatics, Journal Year: 2023, Volume and Issue: 3(3)

Published: Aug. 31, 2023

Electrocatalysis plays an important role in the production of clean energy and pollution control. Researchers have made great efforts to explore efficient, stable, inexpensive electrocatalysts. However, traditional trial error experiments theoretical calculations require a significant amount time resources, which limits development speed Fortunately, rapid machine learning (ML) has brought new solutions scientific problems paradigms The combination ML with experimental propelled advancements electrocatalysis research, particularly areas materials screening, performance prediction, catalysis theory development. In this review, we present comprehensive overview workflow cutting-edge techniques field electrocatalysis. addition, discuss diverse applications predicting performance, guiding synthesis, exploring catalysis. Finally, conclude review challenges

Language: Английский

Citations

17
Strategic view on the current role of AI in advancing environmental sustainability: a SWOT analysis DOI Creative Commons
Lucas Greif, Andreas Kimmig, Sleiman El Bobbou

et al.

Discover Artificial Intelligence, Journal Year: 2024, Volume and Issue: 4(1)

Published: July 1, 2024

Abstract Sustainability has become a critical global concern, focusing on key environmental goals such as achieving net-zero emissions by 2050, reducing waste, and increasing the use of recycled materials in products. These efforts often involve companies striving to minimize their carbon footprints enhance resource efficiency. Artificial intelligence (AI) demonstrated significant potential tackling these sustainability challenges. This study aims evaluate various aspects that must be considered when deploying AI for solutions. Employing SWOT analysis methodology, we assessed strengths, weaknesses, opportunities, threats 70 research articles associated with this context. The offers two main contributions. Firstly, it presents detailed highlighting recent advancements its role promoting sustainability. Key findings include importance data availability quality enablers AI’s effectiveness sustainable applications, necessity explainability mitigate risks, particularly smaller facing financial constraints adopting AI. Secondly, identifies future areas, emphasizing need appropriate regulations evaluation general-purpose models, latest large language initiatives. contributes growing body knowledge providing insights recommendations researchers, practitioners, policymakers, thus paving way further exploration at intersection development.

Language: Английский

Citations

8
Active Learning of Ligands That Enhance Perovskite Nanocrystal Luminescence DOI
Min A Kim, Qianxiang Ai, Alexander J. Norquist

et al.

ACS Nano, Journal Year: 2024, Volume and Issue: 18(22), P. 14514 - 14522

Published: May 22, 2024

Ligands play a critical role in the optical properties and chemical stability of colloidal nanocrystals (NCs), but identifying ligands that can enhance NC is daunting, given high dimensionality space. Here, we use machine learning (ML) robotic screening to accelerate discovery photoluminescence quantum yield (PLQY) CsPbBr3 perovskite NCs. We developed ML model designed predict relative PL enhancement NCs when coordinated with ligand selected from pool 29,904 candidate molecules. Ligand candidates were using an active (AL) approach accounted for uncertainty quantified by twin regressors. After eight experimental iterations batch AL (corresponding 21 initial 72 model-recommended ligands), decreased, demonstrating increased confidence predictions. Feature importance counterfactual analyses predictions illustrate potential field strength designing PL-enhancing ligands. Our versatile framework be readily adapted screen effect on wide range nanomaterials.

Language: Английский

Citations

6
COMPAS-2: a dataset of cata-condensed hetero-polycyclic aromatic systems DOI Creative Commons
Eduardo Mayo Yanes, Sabyasachi Chakraborty, Renana Gershoni‐Poranne

et al.

Scientific Data, Journal Year: 2024, Volume and Issue: 11(1)

Published: Jan. 19, 2024

Polycyclic aromatic systems are highly important to numerous applications, in particular organic electronics and optoelectronics. High-throughput screening generative models that can help identify new molecules advance these technologies require large amounts of high-quality data, which is expensive generate. In this report, we present the largest freely available dataset geometries properties cata-condensed poly(hetero)cyclic calculated date. Our contains ~500k comprising 11 types antiaromatic building blocks at GFN1-xTB level representative a diverse chemical space. We detail structure enumeration process methods used provide various electronic (including HOMO-LUMO gap, adiabatic ionization potential, electron affinity). Additionally, benchmark against ~50k CAM-B3LYP-D3BJ/def2-SVP develop fitting scheme correct xTB values higher accuracy. These datasets represent second installment COMputational database Aromatic Systems (COMPAS) Project.

Language: Английский

Citations

5
Where artificial intelligence stands in the development of electrochemical sensors for healthcare applications-A review DOI Creative Commons
Andreea Cernat, Adrian Groza, Mihaela Tertiş

et al.

TrAC Trends in Analytical Chemistry, Journal Year: 2024, Volume and Issue: 181, P. 117999 - 117999

Published: Oct. 5, 2024

Language: Английский

Citations

5
How to Accelerate R&D and Optimize Experiment Planning with Machine Learning and Data Science DOI Creative Commons

Daniel Pacheco Gutiérrez,

Linnea M. Folkmann,

Hermann Tribukait

et al.

CHIMIA International Journal for Chemistry, Journal Year: 2023, Volume and Issue: 77(1/2), P. 7 - 7

Published: Feb. 22, 2023

Accelerating R&D is essential to address some of the challenges humanity currently facing, such as achieving global sustainability goals. Today’s Edisonian approach trial-and-error still prevalent in labs takes up two decades fundamental and applied research for new materials reach market. Turning around this situation calls strategies upgrade expedite innovation. By conducting smart experiment planning that data-driven guided by AI/ML, researchers can more efficiently search through complex - often constrained space possible experiments find or hit optima much faster than with current approaches. Moreover, digitized data management, will be able maximize utility their short long terms aid statistics, ML visualization tools. In what follows, we describe a framework lay out key technologies accelerate optimize

Language: Английский

Citations

10
Machine learning in electrocatalysis - living up to the hype? DOI
Árni Björn Höskuldsson

Current Opinion in Electrochemistry, Journal Year: 2025, Volume and Issue: unknown, P. 101649 - 101649

Published: Jan. 1, 2025

Language: Английский

Citations

0