An official website of the United States government
Hybrid Data‐driven Discovery of High‐performance Silver Selenide‐based Thermoelectric Composites
Abstract Optimizing material compositions often enhances thermoelectric performances. However, the large selection of possible base elements and dopants results in a vast composition design space that is too large to systematically search using solely domain knowledge. To address this challenge, we propose a hybrid data‐driven strategy that integrates Bayesian Optimization (BO) and Gaussian Process Regression (GPR) to optimize the composition of five elements (Ag, Se, S, Cu, and Te) in AgSe‐based thermoelectric materials. We collect data from the literature to provide prior knowledge for the initial GPR model, which is updated by actively collected experimental data during the iteration between BO and experiments. Within seven iterations, the optimized AgSe‐based materials prepared using a simple high‐throughput ink mixing and blade coating method deliver a high power factor of 2100 μW/mK2, which is a 75% improvement from the baseline composite (nominal composition of Ag2Se1). The success of our study provides opportunities to generalize the demonstrated active machine learning technique to accelerate the development and optimization of a wide range of material systems with reduced experimental trials. This article is protected by copyright. All rights reserved
more »
« less
- Award ID(s):
- 1747685
- PAR ID:
- 10466612
- Publisher / Repository:
- Advanced Materials
- Date Published:
- Journal Name:
- Advanced Materials
- ISSN:
- 0935-9648
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
There has been a growing interest in solution-phase routes to thermoelectric materials due to the decreased costs and novel device architectures that these methods enable. Many excellent thermoelectric materials are metal chalcogenide semiconductors and the ability to create soluble metal chalcogenide semiconductor precursors using thiol–amine solvent mixtures was recently demonstrated by others. In this paper, we report the first thermoelectric property measurements on metal chalcogenide thin films made in this manner. We create Cu 2−x Se y S 1−y and Ag-doped Cu 2−x Se y S 1−y thin films and study the interrelationship between their composition and room temperature thermoelectric properties. We find that the precursor annealing temperature affects the metal : chalcogen ratio, and leads to charge carrier concentration changes that affect the Seebeck coefficient and electrical conductivity. Increasing the Se : S ratio increases electrical conductivity and decreases the Seebeck coefficient. We also find that incorporating Ag into the Cu 2−x Se y S 1−y film leads to appreciable improvements in thermoelectric performance by increasing the Seebeck coefficient and decreasing thermal conductivity. Overall, we find that the room temperature thermoelectric properties of these solution-processed materials are comparable to measurements on Cu 2−x Se alloys made via conventional thermoelectric material processing methods. Achieving parity between solution-phase processing and conventional processing is an important milestone and demonstrates the promise of this binary solvent approach as a solution-phase route to thermoelectric materials.more » « less
-
Abstract Bayesian optimization (BO) holds promise for accelerating materials science research; however, it faces challenges with high-dimensional inputs and experimental noise in real-world problems. This study addresses these issues by benchmarking batch BO on two synthetic six-variable optimization tasks at varying noise levels: a needle-in-a-haystack task (Ackley function) representing rare materials properties, and a smooth landscape (Hartmann function) simulating process optimization. We evaluate key BO strategies, including acquisition functions, batch-picking methods, and exploration hyperparameter tuning, while presenting a framework for tracking high-dimensional optimization progress. Results show optimization outcomes are highly sensitive to noise levels and landscape shapes. This information enables the design of robust materials optimization campaigns with pre-planned experimental budgets that account for real-world uncertainties. Our methodology facilitates greater BO utilization in experimental materials research, particularly for multi-variable optimization problems, by providing practical guidance for configuring BO campaigns in challenging scientific applications. Graphical abstractmore » « less
-
Flexible thermoelectric generators (TEGs) have shown immense potential for serving as a power source for wearable electronics and the Internet of Things. A key challenge preventing large-scale application of TEGs lies in the lack of a high-throughput processing method, which can sinter thermoelectric (TE) materials rapidly while maintaining their high thermoelectric properties. Herein, we integrate high-throughput experimentation and Bayesian optimization (BO) to accelerate the discovery of the optimum sintering conditions of silver–selenide TE films using an ultrafast intense pulsed light (flash) sintering technique. Due to the nature of the high-dimensional optimization problem of flash sintering processes, a Gaussian process regression (GPR) machine learning model is established to rapidly recommend the optimum flash sintering variables based on Bayesian expected improvement. For the first time, an ultrahigh-power factor flexible TE film (a power factor of 2205 μW m −1 K −2 with a zT of 1.1 at 300 K) is demonstrated with a sintering time less than 1.0 second, which is several orders of magnitude shorter than that of conventional thermal sintering techniques. The films also show excellent flexibility with 92% retention of the power factor (PF) after 10 3 bending cycles with a 5 mm bending radius. In addition, a wearable thermoelectric generator based on the flash-sintered films generates a very competitive power density of 0.5 mW cm −2 at a temperature difference of 10 K. This work not only shows the tremendous potential of high-performance and flexible silver–selenide TEGs but also demonstrates a machine learning-assisted flash sintering strategy that could be used for ultrafast, high-throughput and scalable processing of functional materials for a broad range of energy and electronic applications.more » « less
-
Abstract The design of materials and identification of optimal processing parameters constitute a complex and challenging task, necessitating efficient utilization of available data. Bayesian Optimization (BO) has gained popularity in materials design due to its ability to work with minimal data. However, many BO-based frameworks predominantly rely on statistical information, in the form of input-output data, and assume black-box objective functions. In practice, designers often possess knowledge of the underlying physical laws governing a material system, rendering the objective function not entirely black-box, as some information is partially observable. In this study, we propose a physics-informed BO approach that integrates physics-infused kernels to effectively leverage both statistical and physical information in the decision-making process. We demonstrate that this method significantly improves decision-making efficiency and enables more data-efficient BO. The applicability of this approach is showcased through the design of NiTi shape memory alloys, where the optimal processing parameters are identified to maximize the transformation temperature.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript
- Journal Article:
- https://doi.org/10.1002/adma.202212230
