Research Acceleration in Self‐Driving Labs: Technological Roadmap toward Accelerated Materials and Molecular Discovery

Delgado‐Licona, Fernando; Abolhasani, Milad

doi:10.1002/aisy.202200331

Cited by 17 publications

(18 citation statements)

References 86 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Nonetheless, flow reactors suffer from the possibility of clogging when dealing with solid-state materials or precipitates. 112 These cases (including thin-film preparation, battery materials, or polymerization with precipitation of solid products or byproducts) are better suited for parallel batch reactors. 2 Modular microfluidic units could accelerate process optimization and formulation discovery; however, a standardized protocol in modular configuration for a targeted reactive system needs to be established.…”

Section: Integrating Hardware Into Sdlsmentioning

confidence: 99%

“…Taking advantage of the information generated during the optimization process itself, ML enables an iterative experimental design that maximizes the information gained per sample and that requires a smaller number of experiments with respect to traditional DoE. 112,127…”

Section: Algorithmsmentioning

confidence: 99%

“…While we will rst describe the current state of the eld, this is by no means a comprehensive review, and we encourage the reader toward reviews and perspectives of SDLs and autonomous experimentation. [1][2][3][4][5][6][7][8][9][10][11][12][13][14]16,[23][24][25][26][27][28][29][30][31][32][33][34][35][36][37][38] Following this, we will turn our attention to barriers and opportunities associated with data, hardware, knowledge generation, scaling, education, and ethics. As the eld of autonomous experimentation grows and SDLs become more common, we hope to see rapid growth in scientic discovery.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

What is missing in autonomous discovery: open challenges for the community

Maffettone,

Friederich,

Baird

et al. 2023

Digital Discovery

View full text Add to dashboard Cite

show abstract

Section: Integrating Hardware Into Sdlsmentioning

confidence: 99%

Section: Algorithmsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

What is missing in autonomous discovery: open challenges for the community

Maffettone,

Friederich,

Baird

et al. 2023

Digital Discovery

View full text Add to dashboard Cite

show abstract

“…The importance of high throughput experimentation (HTE) for data generation that will enable materials discovery has a long history. − Increasingly, this takes the form of closed-loop autonomous research systems or “self-driving laboratories ,− like the ARES system mentioned above. Whether fully autonomous or not, each step in the workflow of design, synthesis, characterization, and optimization (also referred as design/build/test/learn) can be accelerated by incorporating ML tools …”

Section: The State Of Current Machine Learning Approachesmentioning

confidence: 99%

In Pursuit of the Exceptional: Research Directions for Machine Learning in Chemical and Materials Science

Schrier,

Norquist,

Buonassisi

et al. 2023

J. Am. Chem. Soc.

View full text Add to dashboard Cite

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

show abstract

“…While the typical cost for developing a material is calculated to Digital Discovery PAPER be around 10 to 20 years from initial research to rst industry application, 7 recent reviews estimate that material acceleration platforms can accelerate this pace by 10 to 100 times. 8 For example, Burger et al 9 presented a fully automated laboratory by the use of a mobile robot that was able to nd enhanced photocatalysts for hydrogen production from water. The robot was programmed to move in the laboratory and operate the lab equipment, offering a exible approach to laboratory automation.…”

Section: Introductionmentioning

confidence: 99%