skip to main content

Title: AlphaFlow: autonomous discovery and optimization of multi-step chemistry using a self-driven fluidic lab guided by reinforcement learning

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

more » « less
Award ID(s):
Author(s) / Creator(s):
; ; ; ; ; ;
Publisher / Repository:
Nature Publishing Group
Date Published:
Journal Name:
Nature Communications
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. Abstract

    Metal cation‐doped lead halide perovskite (LHP) quantum dots (QDs) with photoluminescence quantum yields (PLQYs) higher than unity, due to quantum cutting phenomena, are an important building block of the next‐generation renewable energy technologies. However, synthetic route exploration and development of the highest‐performing QDs for device applications remain challenging. In this work, Smart Dope is presented, which is a self‐driving fluidic lab (SDFL), for the accelerated synthesis space exploration and autonomous optimization of LHP QDs. Specifically, the multi‐cation doping of CsPbCl3QDs using a one‐pot high‐temperature synthesis chemistry is reported. Smart Dope continuously synthesizes multi‐cation‐doped CsPbCl3QDs using a high‐pressure gas‐liquid segmented flow format to enable continuous experimentation with minimal experimental noise at reaction temperatures up to 255°C. Smart Dope offers multiple functionalities, including accelerated mechanistic studies through digital twin QD synthesis modeling, closed‐loop autonomous optimization for accelerated QD synthetic route discovery, and on‐demand continuous manufacturing of high‐performing QDs. Through these developments, Smart Dope autonomously identifies the optimal synthetic route of Mn‐Yb co‐doped CsPbCl3QDs with a PLQY of 158%, which is the highest reported value for this class of QDs to date. Smart Dope illustrates the power of SDFLs in accelerating the discovery and development of emerging advanced energy materials.

    more » « less
  2. Abstract

    Electrochemical research often requires stringent combinations of experimental parameters that are demanding to manually locate. Recent advances in automated instrumentation and machine-learning algorithms unlock the possibility for accelerated studies of electrochemical fundamentals via high-throughput, online decision-making. Here we report an autonomous electrochemical platform that implements an adaptive, closed-loop workflow for mechanistic investigation of molecular electrochemistry. As a proof-of-concept, this platform autonomously identifies and investigates anECmechanism, an interfacial electron transfer (Estep) followed by a solution reaction (Cstep), for cobalt tetraphenylporphyrin exposed to a library of organohalide electrophiles. The generally applicable workflow accurately discerns theECmechanism’s presence amid negative controls and outliers, adaptively designs desired experimental conditions, and quantitatively extracts kinetic information of theCstep spanning over 7 orders of magnitude, from which mechanistic insights into oxidative addition pathways are gained. This work opens opportunities for autonomous mechanistic discoveries in self-driving electrochemistry laboratories without manual intervention.

    more » « less
    more » « less
    more » « less
  5. Smooth camber morphing aircraft offer increased control authority and improved aerodynamic efficiency. Smart material actuators have become a popular driving force for shape changes, capable of adhering to weight and size constraints and allowing for simplicity in mechanical design. As a step towards creating uncrewed aerial vehicles (UAVs) capable of autonomously responding to flow conditions, this work examines a multifunctional morphing airfoil’s ability to follow commands in various flows. We integrated an airfoil with a morphing trailing edge consisting of an antagonistic pair of macro fiber composites (MFCs), serving as both skin and actuator, and internal piezoelectric flex sensors to form a closed loop composite system. Closed loop feedback control is necessary to accurately follow deflection commands due to the hysteretic behavior of MFCs. Here we used a deep reinforcement learning algorithm, Proximal Policy Optimization, to control the morphing airfoil. Two neural controllers were trained in a simulation developed through time series modeling on long short-term memory recurrent neural networks. The learned controllers were then tested on the composite wing using two state inference methods in still air and in a wind tunnel at various flow speeds. We compared the performance of our neural controllers to one using traditional position-derivative feedback control methods. Our experimental results validate that the autonomous neural controllers were faster and more accurate than traditional methods. This research shows that deep learning methods can overcome common obstacles for achieving sufficient modeling and control when implementing smart composite actuators in an autonomous aerospace environment.

    more » « less