Design of Organic Electronic Materials With a Goal-Directed Generative Model Powered by Deep Neural Networks and High-Throughput Molecular Simulations

Abstract

In recent years, generative machine learning approaches have attracted significant attention as an enabling approach for designing novel molecular materials with minimal design bias and thereby realizing more directed design for a specific materials property space. Further, data-driven approaches have emerged as a new tool to accelerate the development of novel organic electronic materials for organic light-emitting diode (OLED) applications. We demonstrate and validate a goal-directed generative machine learning framework based on a recurrent neural network (RNN) deep reinforcement learning approach for the design of hole transporting OLED materials. These large-scale molecular simulations also demonstrate a rapid, cost-effective method to identify new materials in OLEDs while also enabling expansion into many other verticals such as catalyst design, aerospace, life science, and petrochemicals.

Virtual Screening for Organic Solar Cells and Light Emitting Diodes

“…The training set of ML can be based on experimentally available structures, such as organic molecules in the Cambridge Structural Database [ 129 ] or generated by solving the forward problem for a set of computer‐generated structures. [ 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.…”

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

“…The approach of MPO calculations is discussed in detail elsewhere. 5 Properties of HTMs: In optoelectronic devices, HTMs should present high rates of hole mobility and good thermal stability. These materials transport holes from the anode to the emissive layer of an OLED device, to form excitons for radiative recombination, see Figure 2.…”

Seven-member-ring-based electron-transporting materials for high-efficiency OLEDs

“…[1][2][3][4][5][6][7][8][9][10] To be more energy-saving and to afford a longer device lifetime, numerous approaches have been proposed to achieve high-efficiency OLEDs. They include the design, 11,12 molecular simulation, 13 synthesis, [14][15][16] and purification 17 of new materials with better electroluminescent characteristics, the design, [18][19][20][21] electric simulation, 22,23 and fabrication 24 of efficiency-effective device architectures, [25][26][27][28][29] and the design and optical simulation of internal and external light extraction systems. [30][31][32][33] Among the OLED materials, electron-transporting materials (ETMs) consume about one third of the applied energy and hence are critical to device performance.…”