Data-driven thermoelectric modeling: Current challenges and prospects

Abstract

Recent advancements in computing technologies coupled with the need to make sense of large amounts of raw data have renewed much interest in data-driven materials design and discovery. Traditional materials science research relies heavily on experimental data to gauge the properties of materials. However, this paradigm is purely based on trial and error and ongoing research can take decades to discover new materials. Data-driven modeling tools such as machine learning and its proven libraries can help speed up the materials’ discovery process through the implementation of powerful algorithms on readily available material datasets mined from the ever-increasing private- and government-funded material databases. In this Perspective, we applied various machine learning models on tens of hundreds of thermoelectric compounds obtained from density functional theory calculation results. In our preliminary analysis, we made use of pymatgen and the powerful materials science library matminer to add and explore key material features that have the propensity to accurately predict our achievable target output. We evaluated the accuracy and performance of our models with the coefficient of determination (R2), the root mean square error, and K-fold cross-validation metrics and identified the most important descriptors for our materials. Finally, we reviewed the current state-of-the-art in data-driven thermoelectric materials’ design and discovery, its current challenges, and prospects.

Recent Advances on Thermoelectric Silicon for Low-Temperature Applications

“…As noted, several of the most significant results achieved on silicon (and on other thermoelectric materials as well) have taken advantage of theoretical and computational investigations [ 96 , 97 ]. Large computer-generated datasets might provide additional tools to accelerate the discovery of new performing thermoelectric materials—and of ways to modify known materials to increase their efficiency [ 98 , 99 ].…”

Big Data in a Nano World: A Review on Computational, Data-Driven Design of Nanomaterials Structures, Properties, and Synthesis

“…The predictive power of quantum mechanics combined with the efficiency of density functional theory has revolutionized our ability to describe microscopic phenomena in materials. During past decades, first-principles computations have become an indispensable part of materials design, with applications ranging from energy harvesting, conversion, and storage, to quantum information and drug design. − With the advancement of modern supercomputers, computational capacity today enables high-throughput screening and data-driven in silico exploration of novel materials. At the same time, there has been a corresponding increase in scientific publications and a remarkable amount of data which fuels the application of artificial intelligence to interpret patterns, predict properties, and steer the directions of materials design.…”

Strain-Enhanced Thermoelectric Performance in GeS2 Monolayer

“…Thermoelectric technology is one of the most fantastic energy-conversion technologies that can convert heat energy and electrical energy into each other directly [ 1 , 2 , 3 ]. Thermoelectric materials have recently gained extensive attention as a critical factor for thermoelectric technology.…”