Toward Self-Driven Autonomous Material and Device Acceleration Platforms (AMADAP) for Emerging Photovoltaics Technologies DOI Creative Commons
Jiyun Zhang, Jens Hauch, Christoph J. Brabec

et al.

Accounts of Chemical Research, Journal Year: 2024, Volume and Issue: 57(9), P. 1434 - 1445

Published: April 23, 2024

ConspectusIn the ever-increasing renewable-energy demand scenario, developing new photovoltaic technologies is important, even in presence of established terawatt-scale silicon technology. Emerging play a crucial role diversifying material flows while expanding product portfolio, thus enhancing security and competitiveness within solar industry. They also serve as valuable backup for photovoltaic, providing resilience to overall energy infrastructure. However, development functional materials poses intricate multiobjective optimization challenges large multidimensional composition parameter space, some cases with millions potential candidates be explored. Solving it necessitates reproducible, user-independent laboratory work intelligent preselection innovative experimental methods.Materials acceleration platforms (MAPs) seamlessly integrate robotic synthesis characterization AI-driven data analysis design, positioning them enabling discovery exploration materials. are proposed revolutionize away from Edisonian trial-and-error approaches ultrashort cycles experiments exceptional precision, generating reliable highly qualitative situation that allows training machine learning algorithms predictive power. MAPs designed assist researcher aspects discovery, such synthesis, precursor preparation, sample processing characterization, analysis, drawing escalating attention field Device (DAPs), however, optimize films layer stacks. Unlike MAPs, which focus on central aspect DAPs identification refinement ideal conditions predetermined set Such prove especially invaluable when dealing "disordered semiconductors," depend heavily parameters ultimately define properties functionality thin film layers. By facilitating fine-tuning conditions, contribute significantly advancement disordered semiconductor devices, emerging photovoltaics.In this Account, we review recent advancements made by our group automated autonomous laboratories advanced device strong photovoltaics, solution-processing perovskite cells organic photovoltaics. We first introduce two developed in-house: microwave-assisted high-throughput platform interface materials, multipurpose robot-based pipetting semiconductors composites, SPINBOT system, spin-coating DAP complex architectures, finally, AMANDA, fully integrated autonomously operating DAP. Notably, underscore utilization experimentation technique address common encountered extensive spaces pertaining photovoltaics Finally, briefly propose holistic concept technology, self-driven (AMADAP) laboratory, development. hope discover how AMADAP can further strengthened universalized advancing hardware software infrastructures future.

Language: Английский

The rise of self-driving labs in chemical and materials sciences DOI Open Access
Milad Abolhasani, Eugenia Kumacheva

Nature Synthesis, Journal Year: 2023, Volume and Issue: 2(6), P. 483 - 492

Published: Jan. 30, 2023

Language: Английский

Citations

265
Generative Models as an Emerging Paradigm in the Chemical Sciences DOI Creative Commons
Dylan M. Anstine, Olexandr Isayev

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(16), P. 8736 - 8750

Published: April 13, 2023

Traditional computational approaches to design chemical species are limited by the need compute properties for a vast number of candidates, e.g., discriminative modeling. Therefore, inverse methods aim start from desired property and optimize corresponding structure. From machine learning viewpoint, problem can be addressed through so-called generative Mathematically, models defined probability distribution function given molecular or material In contrast, model seeks exploit joint with target characteristics. The overarching idea modeling is implement system that produces novel compounds expected have set features, effectively sidestepping issues found in forward process. this contribution, we overview critically analyze popular algorithms like adversarial networks, variational autoencoders, flow, diffusion models. We highlight key differences between each models, provide insights into recent success stories, discuss outstanding challenges realizing discovered solutions applications.

Language: Английский

Citations

169
A Review of Transition Metal Boride, Carbide, Pnictide, and Chalcogenide Water Oxidation Electrocatalysts DOI
Kenta Kawashima, Raúl A. Márquez, Lettie A. Smith

et al.

Chemical Reviews, Journal Year: 2023, Volume and Issue: 123(23), P. 12795 - 13208

Published: Nov. 15, 2023

Transition metal borides, carbides, pnictides, and chalcogenides (X-ides) have emerged as a class of materials for the oxygen evolution reaction (OER). Because their high earth abundance, electrical conductivity, OER performance, these electrocatalysts potential to enable practical application green energy conversion storage. Under potentials, X-ide demonstrate various degrees oxidation resistance due differences in chemical composition, crystal structure, morphology. Depending on oxidation, catalysts will fall into one three post-OER electrocatalyst categories: fully oxidized oxide/(oxy)hydroxide material, partially core@shell unoxidized material. In past ten years (from 2013 2022), over 890 peer-reviewed research papers focused electrocatalysts. Previous review provided limited conclusions omitted significance "catalytically active sites/species/phases" this review, comprehensive summary (i) experimental parameters (e.g., substrates, loading amounts, geometric overpotentials, Tafel slopes, etc.) (ii) electrochemical stability tests post-analyses publications from 2022 is provided. Both mono polyanion X-ides are discussed classified with respect material transformation during OER. Special analytical techniques employed study reconstruction also evaluated. Additionally, future challenges questions yet be answered each section. This aims provide researchers toolkit approach showcase necessary avenues investigation.

Language: Английский

Citations

119
AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning DOI Creative Commons
Amanda A. Volk, Robert W. Epps, Daniel T. Yonemoto

et al.

Nature Communications, Journal Year: 2023, Volume and Issue: 14(1)

Published: March 14, 2023

Closed-loop, autonomous experimentation enables accelerated and material-efficient exploration of large reaction spaces without the need for user intervention. However, advanced materials with complex, multi-step processes data sparse environments remains a challenge. In this work, we present AlphaFlow, self-driven fluidic lab capable discovery complex chemistries. AlphaFlow uses reinforcement learning integrated modular microdroplet reactor performing steps variable sequence, phase separation, washing, continuous in-situ spectral monitoring. To demonstrate power toward high dimensionality chemistries, use to discover optimize synthetic routes shell-growth core-shell semiconductor nanoparticles, inspired by colloidal atomic layer deposition (cALD). Without prior knowledge conventional cALD parameters, successfully identified optimized novel route, up 40 that outperformed sequences. Through capabilities closed-loop, learning-guided systems in exploring solving challenges nanoparticle syntheses, while relying solely on in-house generated from miniaturized microfluidic platform. Further application chemistries beyond can lead fundamental generation as well route discoveries optimization.

Language: Английский

Citations

88
Chemical reaction networks and opportunities for machine learning DOI
Mingjian Wen, Evan Walter Clark Spotte‐Smith, Samuel M. Blau

et al.

Nature Computational Science, Journal Year: 2023, Volume and Issue: 3(1), P. 12 - 24

Published: Jan. 16, 2023

Language: Английский

Citations

72
Revolutionizing drug formulation development: The increasing impact of machine learning DOI
Zeqing Bao,

Jack Bufton,

Riley J. Hickman

et al.

Advanced Drug Delivery Reviews, Journal Year: 2023, Volume and Issue: 202, P. 115108 - 115108

Published: Sept. 27, 2023

Language: Английский

Citations

53
Self-Driving Laboratory for Polymer Electronics DOI
Aikaterini Vriza, Henry Chan, Jie Xu

et al.

Chemistry of Materials, Journal Year: 2023, Volume and Issue: 35(8), P. 3046 - 3056

Published: March 9, 2023

Owing to the chemical pluripotency and viscoelastic nature of electronic polymers, polymer electronics have shown unique advances in many emerging applications such as skin-like electronics, large-area printed energy devices, neuromorphic computing but their development period is years-long. Recent advancements automation, robotics, learning algorithms led a growing number self-driving (autonomous) laboratories that begun revolutionize accelerated discovery materials. In this perspective, we first introduce current state autonomous laboratories. Then analyze why it challenging conduct research by an laboratory highlight needs. We further discuss our efforts building laboratory, namely Polybot, for automated synthesis characterization polymers processing fabrication into devices. Finally, share vision using different types research.

Language: Английский

Citations

48
In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science DOI
Joshua Schrier, Alexander J. Norquist,

Tonio Buonassisi

et al.

Journal of the American Chemical Society, Journal Year: 2023, Volume and Issue: 145(40), P. 21699 - 21716

Published: Sept. 27, 2023

Exceptional molecules and materials with one or more extraordinary properties are both technologically valuable fundamentally interesting, because they often involve new physical phenomena compositions that defy expectations. Historically, exceptionality has been achieved through serendipity, but recently, machine learning (ML) automated experimentation have widely proposed to accelerate target identification synthesis planning. In this Perspective, we argue the data-driven methods commonly used today well-suited for optimization not realization of exceptional molecules. Finding such outliers should be possible using ML, only by shifting away from traditional ML approaches tweak composition, crystal structure, reaction pathway. We highlight case studies high-Tc oxide superconductors superhard demonstrate challenges ML-guided discovery discuss limitations automation task. then provide six recommendations development capable discovery: (i) Avoid tyranny middle focus on extrema; (ii) When data limited, qualitative predictions direction than interpolative accuracy; (iii) Sample what can made how make it defer optimization; (iv) Create room (and look) unexpected while pursuing your goal; (v) Try fill-in-the-blanks input output space; (vi) Do confuse human understanding model interpretability. conclude a description these integrated into workflows, which enable materials.

Language: Английский

Citations

46
Accelerated chemical science with AI DOI Creative Commons
Seoin Back,

Alán Aspuru-Guzik,

Michele Ceriotti

et al.

Digital Discovery, Journal Year: 2023, Volume and Issue: 3(1), P. 23 - 33

Published: Dec. 6, 2023

The ASLLA Symposium focused on accelerating chemical science with AI. Discussions data, new applications, algorithms, and education were summarized. Recommendations for researchers, educators, academic bodies provided.

Language: Английский

Citations

46
Self-Driving Laboratories for Chemistry and Materials Science DOI Creative Commons
Gary Tom, Stefan P. Schmid, Sterling G. Baird

et al.

Chemical Reviews, Journal Year: 2024, Volume and Issue: 124(16), P. 9633 - 9732

Published: Aug. 13, 2024

Self-driving laboratories (SDLs) promise an accelerated application of the scientific method. Through automation experimental workflows, along with autonomous planning, SDLs hold potential to greatly accelerate research in chemistry and materials discovery. This review provides in-depth analysis state-of-the-art SDL technology, its applications across various disciplines, implications for industry. additionally overview enabling technologies SDLs, including their hardware, software, integration laboratory infrastructure. Most importantly, this explores diverse range domains where have made significant contributions, from drug discovery science genomics chemistry. We provide a comprehensive existing real-world examples different levels automation, challenges limitations associated each domain.

Language: Английский

Citations

39