Composable neural emulators accelerate thermoelectric generator design.
basic_science · Level V
Where this comes from
- Record sourced from PubMed, PMID 41986625.
- Also identified by DOI 10.1038/s41586-026-10223-1 and PMC identifier 13083250.
- Licence recorded as CC BY-NC-ND.
- Because redistribution is not established, this page shows the abstract only. Follow the links below for the full text.
Abstract
Designing high-performance thermoelectric (TE) devices is challenging because it requires not only advanced materials but also optimal configurations, which are critical for maximizing device performance but remain time-consuming and resource-intensive to identify<sup>1-5</sup>. Here we develop TEGNet, a neural network emulator that predicts TE generator performance with greater than 99% accuracy while using only 0.01% of the computational time required by commercial finite-element solvers. TEGNet exhibits strong architectural generality across various material systems and allows flexible combinations of material-specific emulators, unlocking rapid and accurate exploration of diverse device architectures. Using TEGNet, we experimentally optimize MgAgSb/Bi<sub>0.4</sub>Sb<sub>1.6</sub>Te<sub>3</sub> segmented and Mg<sub>3</sub>Bi<sub>1.4</sub>Sb<sub>0.6</sub>-MgAgSb n-p paired TE generators, achieving conversion efficiencies of 9.3% and 8.7%, respectively, ranking competitively high among those previously reported<sup>6-10</sup>. This work demonstrates the power of artificial intelligence (AI) in TE generator design, inspiring further research on AI for thermoelectrics.
Medical subject headings
- Neural Networks, Computer
- Equipment Design
- Equipment Design/methods
- Electric Power Supplies
- Artificial Intelligence
- Temperature
- Electricity
- Finite Element Analysis