[Case Study] Accelerating the Design of Organic EL Materials through Active Learning

Added to bookmarks
Bookmarks list

Bookmark has been removed
Bookmarks list

You can't add any more bookmarks

By registering as a member, you can increase the number of bookmarks you can save and organize them with labels.
Free membership registration

last updated：Oct 01, 2025

シュレーディンガー

High efficiency and cost performance! An active learning workflow that utilizes the synergy of physics-based simulations and machine learning for predicting optoelectronic properties.

Molecular modeling and simulation tools have been proven effective for materials discovery and are increasingly being adopted in industrial research and development. Digital simulation significantly reduces the time required in research and development workflows compared to traditional experimental approaches, but challenges remain. Schrödinger has made it easier to address these challenges. Recently, Schrödinger developed an active learning workflow that leverages the synergy between physics-based simulations and machine learning for predicting optoelectronic properties. Recent research by Schrödinger, published in Frontiers in Chemistry and presented at SID-Display Week 2022, demonstrates an active learning paradigm for the discovery of OLED materials. *For more details, please refer to the PDF document or feel free to contact us.*

Inquire About This Product

basic information

Our computational chemistry platform can accommodate a wide range of materials research fields. ■ Prediction of physical properties through Density Functional Theory (DFT) calculations and first-principles calculations in periodic systems HOMO/LUMO/pKa/solvent effects/IR/Raman/UV-vis/VCD/NMR/oxidation-reduction potential/triplet excited state energy/TADF S1-Tx gap/fluorescence/phosphorescence/vibrational calculations/structure optimization/transition state calculations/reaction pathway analysis/adsorption energy/bond dissociation energy/electron and hole mobility/reorientation (rearrangement, reconfiguration) energy ■ Prediction of physical properties using Molecular Mechanics (MM), Molecular Dynamics (MD), and Coarse-Grained MD Density/conformation analysis/crosslinking structure/Young's modulus/viscosity/surface tension/glass transition temperature (Tg)/molecular diffusion/thermal expansion/crystal morphology/swelling/stress-strain curves/solubility parameters Methods available for use with machine learning Generation of various descriptors and fingerprints/Partial Least Squares (PLS) regression/multiple linear regression (MLR)/Principal Component Regression (PCR)/Kernel PLS/Bayesian classification/Recursive Partitioning (RP) analysis/Self-Organizing Maps/Tg, dielectric constant, boiling point, vapor pressure prediction models/genetic algorithms/active learning