Active Learning Accelerates Design and Optimization of Hole-Transporting Materials for Organic Electronics

Abstract

Data-driven methods are receiving increasing attention to accelerate materials design and discovery for organic light-emitting diodes (OLEDs). Machine learning (ML) has enabled high-throughput screening of materials properties to suggest new candidates for organic electronics. However, building reliable predictive ML models requires creating and managing a high volume of data that adequately address the complexity of materials’ chemical space. In this regard, active learning (AL) has emerged as a powerful strategy to efficiently navigate the search space by prioritizing the decision-making process for unexplored data. This approach allows a more systematic mechanism to identify promising candidates by minimizing the number of computations required to explore an extensive materials library with diverse variables and parameters. In this paper, we applied a workflow of AL that accounts for multiple optoelectronic parameters to identify materials candidates for hole-transport layers (HTL) in OLEDs. Results of this work pave the way for efficient screening of materials for organic electronics with superior efficiencies before laborious simulations, synthesis, and device fabrication.

Virtual Screening for Organic Solar Cells and Light Emitting Diodes

“…[ 130 ] ML can also be used to propose structures with a given set of properties, addressing the inverse design problem. [ 131 ] This process can be further optimized by using active machine learning [ 132 , 133 ] or generative models. [ 134 ]…”

66‐3: Active Learning for the Design of Novel OLED Materials

“…Active learning (AL) has emerged as a promising strategy to address this issue. 2 By prioritizing the decision-making process with unexplored new data, allowing an efficient exploration of an extensive library, see Figure 1. A feedback loop in the AL framework enables an efficient data selection, leading to a smaller training set required for ML.…”

“…Despite the successful application of AL in different fields of application, such as lithium-ion batteries, catalysis, and drug discovery, the design and development of novel optoelectronic materials via data-driven approaches are in their early stages. 2 There are several complex factors that simultaneously impact the efficiency of materials in optoelectronic devices. As a direct consequence, reliable application of ML models for the design and development of optoelectronic materials by using simplistic descriptors such as energy levels of frontier molecular orbitals is generally impractical.…”

Active Discovery of Donor:Acceptor Combinations For Efficient Organic Solar Cells

“…This strategy is called active learning or sequential learning. Recently active learning has received much attention in a wide range of applications such as alloys, thermoelectrics, batteries, , OLEDs, and OSCs other organic semiconducting materials …”

“…Therefore, active learning is most beneficial in situations when data are few or challenging to gather, which is frequently the case in materials research. In fact, recent literature from a variety of areas has highlighted successful examples of active learning in discovery of new materials. ,, An important thing to note is that the buzzword “big data” refers to the search space, while the data set available for training is usually small and sparse, like in all other scientific domains. Thus, extrapolation is required, and traditional ML techniques might struggle to achieve it.…”