skip to main content


Title: Accelerated AI development for autonomous materials synthesis in flow
Autonomous robotic experimentation strategies are rapidly rising in use because, without the need for user intervention, they can efficiently and precisely converge onto optimal intrinsic and extrinsic synthesis conditions for a wide range of emerging materials. However, as the material syntheses become more complex, the meta-decisions of artificial intelligence (AI)-guided decision-making algorithms used in autonomous platforms become more important. In this work, a surrogate model is developed using data from over 1000 in-house conducted syntheses of metal halide perovskite quantum dots in a self-driven modular microfluidic material synthesizer. The model is designed to represent the global failure rate, unfeasible regions of the synthesis space, synthesis ground truth, and sampling noise of a real robotic material synthesis system with multiple output parameters (peak emission, emission linewidth, and quantum yield). With this model, over 150 AI-guided decision-making strategies within a single-period horizon reinforcement learning framework are automatically explored across more than 600 000 simulated experiments – the equivalent of 7.5 years of continuous robotic operation and 400 L of reagents – to identify the most effective methods for accelerated materials development with multiple objectives. Specifically, the structure and meta-decisions of an ensemble neural network-based material development strategy are investigated, which offers a favorable technique for intelligently and efficiently navigating a complex material synthesis space with multiple targets. The developed ensemble neural network-based decision-making algorithm enables more efficient material formulation optimization in a no prior information environment than well-established algorithms.  more » « less
Award ID(s):
1902702
NSF-PAR ID:
10251476
Author(s) / Creator(s):
; ; ;
Date Published:
Journal Name:
Chemical Science
Volume:
12
Issue:
17
ISSN:
2041-6520
Page Range / eLocation ID:
6025 to 6036
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1.  
    more » « less
  2. Applying AI power to predict syntheses of novel materials requires high-quality, large-scale datasets. Extraction of synthesis information from scientific publications is still challenging, especially for extracting synthesis actions, because of the lack of a comprehensive labeled dataset using a solid, robust, and well-established ontology for describing synthesis procedures. In this work, we propose the first unified language of synthesis actions (ULSA) for describing inorganic synthesis procedures. We created a dataset of 3040 synthesis procedures annotated by domain experts according to the proposed ULSA scheme. To demonstrate the capabilities of ULSA, we built a neural network-based model to map arbitrary inorganic synthesis paragraphs into ULSA and used it to construct synthesis flowcharts for synthesis procedures. Analysis of the flowcharts showed that (a) ULSA covers essential vocabulary used by researchers when describing synthesis procedures and (b) it can capture important features of synthesis protocols. The present work focuses on the synthesis protocols for solid-state, sol–gel, and solution-based inorganic synthesis, but the language could be extended in the future to include other synthesis methods. This work is an important step towards creating a synthesis ontology and a solid foundation for autonomous robotic synthesis. 
    more » « less
  3. The Industrial Internet of Things has increased the number of sensors permanently installed in industrial plants. Yet there will be gaps in coverage due to broken sensors or sparce density in very large plants, such as in the petrochemical industry. Modern emergency response operations are beginning to use Small Unmanned Aerial Systems (sUAS) as remote sensors to provide rapid improved situational awareness. Ground-based sensors are an integral component of overall situational awareness platforms, as they can provide longer-term persistent monitoring that aerial drones are unable to provide. Squishy Robotics and the Berkeley Emergent Space Tensegrities Laboratory have developed hardware and a framework for rapidly deploying sensor robots for integrated ground-aerial disaster response. The semi-autonomous delivery of sensors using tensegrity (tension-integrity) robotics uses structures that are flexible, lightweight, and have high stiffness-to-weight ratios, making them ideal candidates for robust high-altitude deployments. Squishy Robotics has developed a tensegrity robot for commercial use in Hazardous Materials (HazMat) scenarios that is capable of being deployed from commercial drones or other aircraft. Squishy Robots have been successfully deployed with a delicate sensing and communication payload of up to 1,000 ft. This paper describes the framework for optimizing the deployment of emergency sensors spatially over time. AI techniques (e.g., Long Short-Term Memory neural networks) identify regions where sensors would be most valued without requiring humans to enter the potentially dangerous area. The cost function for optimization considers costs of false-positive and false-negative errors. Decisions on mitigation include shutting down the plant or evacuating the local community. The Expected Value of Information (EVI) is used to identify the most valuable type and location of physical sensors to be deployed to increase the decision-analytic value of a sensor network. A case study using data from the Tennessee Eastman process dataset of a chemical plant displayed in OSI Soft is provided. 
    more » « less
  4. Forecasting models are a central part of many control systems, where high consequence decisions must be made on long latency control variables. These models are particularly relevant for emerging artificial intelligence (AI)-guided instrumentation, in which prescriptive knowledge is needed to guide autonomous decision-making. Here we describe the implementation of a long short-term memory model (LSTM) for forecasting of electron energy loss spectroscopy (EELS) data, one of the richest analytical probes of materials and chemical systems. We describe key considerations for data collection, preprocessing, training, validation, and benchmarking, showing how this approach can yield powerful predictive insight into order-disorder phase transitions. Finally, we comment on how such a model may integrate with emerging AI-guided instrumentation for powerful high-speed experimentation. 
    more » « less
  5. Abstract

    Forecasting models are a central part of many control systems, where high-consequence decisions must be made on long latency control variables. These models are particularly relevant for emerging artificial intelligence (AI)-guided instrumentation, in which prescriptive knowledge is needed to guide autonomous decision-making. Here we describe the implementation of a long short-term memory model (LSTM) for forecasting in situ electron energy loss spectroscopy (EELS) data, one of the richest analytical probes of materials and chemical systems. We describe key considerations for data collection, preprocessing, training, validation, and benchmarking, showing how this approach can yield powerful predictive insight into order-disorder phase transitions. Finally, we comment on how such a model may integrate with emerging AI-guided instrumentation for powerful high-speed experimentation.

     
    more » « less