image: I-TE materials experience uneven anion and cation diffusion under temperature gradients, generating an electrical potential difference to power external devices. A ML regression model is trained with the features to evaluate the Seebeck coefficient accurately. This model enables direct screening of i-TE materials. Furthermore, interpretable analysis of the ML model can provide valuable physical insights, fostering the advancement of high-performance i-TE materials from a more intuitive perspective.
Credit: ©Science China Press
A team of researchers has developed a transformative machine learning (ML) approach to streamline the discovery and development of high-performance ionic thermoelectric (i-TE) materials. This cutting-edge framework overcomes longstanding barriers in the field, offering a rapid and precise method for predicting Seebeck coefficients—the defining measure of i-TE material performance. Their work not only advances theoretical understanding but also unveils promising materials for next-generation thermal sensors and miniaturized waste-heat recovery devices.
Ionic thermoelectric materials, known for their exceptional Seebeck coefficients—often surpassing 10 mV/K, two orders of magnitude higher than their electronic counterparts—are a focus for compact energy systems. Despite this potential, progress has been slow due to the reliance on labor-intensive, trial-and-error experimentation, and the lack of robust theoretical models to guide the exploration of their vast chemical space. The researchers tackled these challenges by leveraging the simplified molecular-input line-entry system (SMILES) for encoding molecular structures, enabling their machine learning model to handle the diversity of i-TE material types effectively.
The ML model, trained on a carefully curated dataset of 51 i-TE material samples, achieved an impressive coefficient of determination (R²) of 0.98 in test cases. By analyzing molecular features derived from SMILES, the model predicted a range of promising materials, among which a waterborne polyurethane-potassium iodide (WPU/KI) ionogel stood out. Experimental validation confirmed this ionogel’s Seebeck coefficient at 41.39 mV/K.
Through interpretable analysis, the team identified critical molecular descriptors influencing the Seebeck coefficient. Two features stood out: the number of rotatable bonds and the octanol-water partition coefficient of ion donors. Molecular dynamics simulations further confirmed their impact, revealing that these properties govern ion diffusion and interaction with the polymer matrix—key mechanisms behind high thermopower. For instance, a higher number of rotatable bonds correlated with reduced ion diffusion efficiency, while a low partition coefficient indicated stronger Coulomb interactions, enhancing thermoelectric performance.
This study also highlights the complementarity of ML models. While gradient boosting decision trees (GBDT) provided high-precision predictions within known ranges, symbolic regression models like genetic programming symbolic regression (GPSR) demonstrated utility in extrapolating beyond the dataset, suggesting novel material combinations.
The researchers validated their predictions by fabricating and testing the top-ranked materials. The WPU/KI ionogel exhibited stable performance under various conditions, with a temperature-induced voltage increase of 250 mV for a gradient of 5.5 K. Molecular dynamics simulations illuminated the physical interactions driving this performance, such as the strong electrostatic attractions between potassium ions and the polyurethane matrix.
This breakthrough ML framework holds the promise of revolutionizing the field of ionic thermoelectrics, bridging the gap between theoretical exploration and experimental discovery. With its high accuracy, scalability, and interpretability, it lays the groundwork for a new era of material innovation, propelling sustainable energy technologies forward.
Journal
National Science Review