Bulletin of the American Physical Society
APS March Meeting 2022
Volume 67, Number 3
Monday–Friday, March 14–18, 2022; Chicago
Session Y15: Renewable Energy and Data ScienceInvited Session Live Streamed
|
Hide Abstracts |
Sponsoring Units: GERA GDS Chair: Arun Baskaran, Argonne National Laboratory Room: McCormick Place W-183C |
Friday, March 18, 2022 8:00AM - 8:36AM |
Y15.00001: Advancing Nano- and Quantum Photonics with Machine Learning Invited Speaker: Alexandra Boltasseva Discovering unconventional optical designs via machine-learning promises to advance on-chip circuitry, imaging, sensing, energy, and quantum information technology. In this talk, we discuss photonic design approaches and emerging material platforms for showcasing machine-learning-assisted topology optimization for optical metasurface designs with applications in thermophotovoltaics, reflective optics, and lightsail technology. We demonstrate the effectiveness of autoencoders for compressing the vast design space of metasurfaces into a smaller search space. By employing global optimization via adjoint methods or quantum annealing, one can find the optimal metasurface designs within the smaller space constructed by the autoencoder. The quantum-assisted machine learning framework, named bVAE-QUBO, presented in this work is the first demonstration of a generic machine learning framework that compresses an arbitrary continuous optimization problem into an Ising-model formalism for quantum sampling. When compared to other global optimization techniques, bVAE-QUBO has the potential for quantum speedups and achieving higher quality designs than traditional adjoint optimization methods. The techniques employed in this work extend well beyond the metasurface optimization space and into many inverse design problems for engineering and physics. |
Friday, March 18, 2022 8:36AM - 9:12AM |
Y15.00002: Chemical Stability of Perovskite Semiconductors: Kinetics of Degradation and Machine Learning Models of Device Lifetime Invited Speaker: Hugh W Hillhouse Understanding the chemical reactions that hybrid organic-inorganic halide perovskite (HP) semiconductors undergo in the presence of moisture, oxygen, and light are essential to the commercial development of HP solar cells and optoelectronics. The presentation will cover recent experiments that have determined the dominant degradation mechanism, developed quantitative kinetic rate laws, and demonstrated machine learning models that utilize the kinetic expressions are capable of forecasting device lifetime. The core dataset for the kinetic model is based on in-situ optical absorbance measurements during 105 degradations conducted over 41 unique environmental conditions. The data are used to quantify the kinetics of methylammonium lead iodide (MAPbI3) degradation in response to combinations of moisture, oxygen, and illumination over a range of temperatures. We discover and report a new chemical reaction pathway referred to as a water-accelerated photo-oxidation (WPO) pathway, which is the dominant chemical degradation pathway when light, oxygen, and humidity are present (and much faster than other dry photooxidation pathways, DPOs). The overall rate of degradation is very sensitive to small amounts of water, which behaves effectively like catalyst. The WPO process has significant implications for perovskite stability and encapsulation, which will be discussed. In addition, the presentation will include recent stability results on the broader (FA, MA, Cs)Pb(I,Br)3 space and details of a machine learning approach that uses the kinetic rate expressions as features in a predictive model of perovskite solar cell lifetime (T80). |
Friday, March 18, 2022 9:12AM - 9:48AM |
Y15.00003: Combining AI Reasoning and Machine Learning for Accelerating Materials Discovery Invited Speaker: Carla P Gomes Artificial Intelligence (AI) is a rapidly advancing field inspired by human intelligence. AI systems are now performing at human and even superhuman levels on various tasks, such as image identification and face and speech recognition. The tremendous AI progress that we have witnessed in the last decade has been primarily driven by deep learning advances and heavily hinges on the availability of large, annotated datasets to supervise model training. However, often we only have access to small datasets and incomplete data. Humans amplify a few data examples with intuitions and detailed reasoning from first principles and prior knowledge for discovery. I will describe Deep Reasoning Networks (DRNets), a general framework that seamlessly integrates deep learning and reasoning via an interpretable latent space for incorporating prior knowledge and tackling challenging problems. DRNets requires only modest amounts of (unlabeled) data, in sharp contrast to standard deep learning approaches. DRNets reach superhuman performance for crystal-structure phase mapping, a core, long-standing challenge in materials science, enabling the discovery of solar-fuels materials. For an intuitive demonstration of our approach, we also solve variants of the Sudoku game. This work was featured in a cover article of Nature Machine Intelligence entitled, Automating crystal-structure phase mapping by combining deep learning with constraint reasoning. I will also talk about the Scientific Autonomous Reasoning Agent (SARA) for accelerating materials discovery, which was recently featured in a Science Advances article entitled, Autonomous materials synthesis via hierarchical active learning of non-equilibrium phase diagrams. |
Friday, March 18, 2022 9:48AM - 10:24AM |
Y15.00004: Automated experiment in microscopy towards discovering new physics and new materials Invited Speaker: Sergei V Kalinin In this presentation, I will discuss recent progress in machine learning applications in electron microscopy, ranging from feature extraction, learning generative physical models, and to physics discovery via active learning. The applications of classical deep learning methods in streaming image analysis are strongly affected by the out of distribution drift effects, and the approaches to minimize these to enable real time feature finding are discussed. I further illustrate discovery of structure-property relationships on the example of plasmonic structures. Finally, I illustrate transition from post-experiment data analysis to active learning process. Here, the strategies based on simple Gaussian Processes often tend to produce sub-optimal results due to the lack of prior knowledge and very simplified (via learned kernel function) representation of spatial complexity of the system. Comparatively, deep kernel learning (DKL) methods allow to realize both the exploration of complex systems towards the discovery of structure-property relationship, and enable automated experiment targeting physics (rather than simple spatial feature) discovery. The latter is illustrated via experimental discovery of the edge plasmons in STEM/EELS and 4D STEM exploration of twisted bilayer structures. |
Follow Us |
Engage
Become an APS Member |
My APS
Renew Membership |
Information for |
About APSThe American Physical Society (APS) is a non-profit membership organization working to advance the knowledge of physics. |
© 2025 American Physical Society
| All rights reserved | Terms of Use
| Contact Us
Headquarters
1 Physics Ellipse, College Park, MD 20740-3844
(301) 209-3200
Editorial Office
100 Motor Pkwy, Suite 110, Hauppauge, NY 11788
(631) 591-4000
Office of Public Affairs
529 14th St NW, Suite 1050, Washington, D.C. 20045-2001
(202) 662-8700