An official website of the United States government
Abstract The development of a materials synthesis route is usually based on heuristics and experience. A possible new approach would be to apply data-driven approaches to learn the patterns of synthesis from past experience and use them to predict the syntheses of novel materials. However, this route is impeded by the lack of a large-scale database of synthesis formulations. In this work, we applied advanced machine learning and natural language processing techniques to construct a dataset of 35,675 solution-based synthesis procedures extracted from the scientific literature. Each procedure contains essential synthesis information including the precursors and target materials, their quantities, and the synthesis actions and corresponding attributes. Every procedure is also augmented with the reaction formula. Through this work, we are making freely available the first large dataset of solution-based inorganic materials synthesis procedures.
more »
« less
Precursor recommendation for inorganic synthesis by machine learning materials similarity from scientific literature
Synthesis prediction is a key accelerator for the rapid design of advanced materials. However, determining synthesis variables such as the choice of precursor materials is challenging for inorganic materials because the sequence of reactions during heating is not well understood. In this work, we use a knowledge base of 29,900 solid-state synthesis recipes, text-mined from the scientific literature, to automatically learn which precursors to recommend for the synthesis of a novel target material. The data-driven approach learns chemical similarity of materials and refers the synthesis of a new target to precedent synthesis procedures of similar materials, mimicking human synthesis design. When proposing five precursor sets for each of 2654 unseen test target materials, the recommendation strategy achieves a success rate of at least 82%. Our approach captures decades of heuristic synthesis data in a mathematical form, making it accessible for use in recommendation engines and autonomous laboratories.
more »
« less
- Award ID(s):
- 1922372
- PAR ID:
- 10472899
- Publisher / Repository:
- American Association for the Advancement of Science
- Date Published:
- Journal Name:
- Science Advances
- Volume:
- 9
- Issue:
- 23
- ISSN:
- 2375-2548
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract A machine learning (ML) guided approach is presented for the accelerated optimization of chemical vapor deposition (CVD) synthesis of 2D materials toward the highest quality, starting from low‐quality or unsuccessful synthesis conditions. Using 26 sets of these synthesis conditions as the initial training dataset, our method systematically guides experimental synthesis towards optoelectronic‐grade monolayer MoS2flakes. A‐exciton linewidth (σA) as narrow as 38 meV could be achieved in 2D MoS2flakes after only an additional 35 trials (reflecting 15% of the full factorial design dataset for training purposes). In practical terms, this reflects a decrease of the possible experimental time to optimize the parameters from up to one year to about two months. This remarkable efficiency was achieved by formulating a constrained sequencing optimization problem solved via a combination of constraint learning and Bayesian Optimization with the narrowness of σAas the single target metric. By employing graph‐based semi‐supervised learning with data acquired through a multi‐criteria sampling method, the constraint model effectively delineates and refines the feasible design space for monolayer flake production. Additionally, the Gaussian Process regression effectively captures the relationships between synthesis parameters and outcomes, offering high predictive capability along with a measure of prediction uncertainty. This method is scalable to a higher number of synthesis parameters and target metrics and is transferrable to other materials and types of reactors. This study envisions that this method will be fundamental for CVD and similar techniques in the future.more » « less
-
Programming structures to realize any prescribed mechanical response under large deformation is highly desired for various functionalities, such as actuation and energy trapping. Yet, the use of a single material phase and heuristically developed structural patterns leads to restricted design space and potential failure to achieve specific target behaviors. Here, through a free-form inverse design approach, multiple hyperelastic materials with distinct properties are optimally synthesized into composite structures to precisely achieve arbitrary and extreme prescribed responses under large deformations. The digitally synthesized structures exhibit organic shapes and motions with irregular distributions of material phases. Within the structures, different materials play distinct roles yet seamlessly collaborate through sophisticated deformation mechanisms to produce the target behaviors, some of which are unachievable by a single material. While complex in geometry and material heterogeneity, the discovered structures are effectively manufactured via multimaterial fabrication with different polydimethylsiloxane (PDMS) elastomers with distinct behaviors and their highly nonlinear responses are physically and accurately realized in experiments. To enhance programmability, the synthesized structures are heteroassembled into architectures that exhibit highly complex yet navigable responses. The proposed synthesis, multimaterial fabrication, and heteroassembly strategy can be utilized to design function-oriented and situation-specific mechanical devices for a wide range of applications.more » « less
-
Silva, A.; Leino, K.R.M. (Ed.)In the Adapter-Design Pattern, a programmer implements a Target interface by constructing an Adapter that accesses an existing Adaptee code. In this work, we presented a reactive synthesis interpretation to the adapter design pattern, wherein an algorithm takes an Adaptee and a Target transducers, and the aim is to synthesize an Adapter transducer that, when composed with the Adaptee, generates a behavior that is equivalent to the behavior of the Target. One use of such an algorithm is to synthesize controllers that achieve similar goals on different hardware platforms. While this problem can be solved with existing synthesis algorithms, current state-of-the-art tools fail to scale. To cope with the computational complexity of the problem, we introduced a special form of specification format, called Separated GR(k), which can be solved with a scalable synthesis algorithm but still allows for a large set of realistic specifications. We solved the realizability and the synthesis problems for Separated GR(k), and showed how to exploit the separated nature of our specification to construct better algorithms, in terms of time complexity, than known algorithms for GR(k) synthesis. We then described a tool, called SGR(k), which we have implemented based on the above approach and showed, by experimental evaluation, how our tool outperforms current state-of-the-art tools on various benchmarks and test-cases.more » « less
-
null (Ed.)To accelerate materials discovery, computational methods such as inverse materials design have been proposed to predict the properties of target compounds of interest for specific applications. This in silico process can be used to guide subsequent synthesis and characterization. Inverse design is especially relevant for the field of organic molecules, for which there are nearly infinite synthetic modifications possible. With a target application of UV-absorbing, visibly transparent solar cells in mind, we calculated the orbital and transition energies of over 360 possible coronene derivatives. Our screening, or the constraints we imposed on the calculated series, resulted in the selection of three new derivatives, namely contorted pentabenzocoronene (cPBC), contorted tetrabenzocoronene (cTBC), and contorted tetrabenzofuranylbenzocoronene (cTBFBC) for synthesis and characterization. Our materials characterization found agreement between our calculated and experimental energy values, and through testing of these materials in organic photovoltaic (OPV) devices, we fabricated solar cells with an open-circuit voltage of 1.84 V and an average visible transparency of 88% of the active layer; both quantities exceed previous records for visibly transparent coronene-based solar cells. This work highlights the promise of inverse materials design for future materials discovery, as well as improvements to an exciting application of UV-targeted solar cells.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1126/sciadv.adg8180
