Online Inquiry

Key Property Prediction of Organic Electronic Materials


Nowadays, organic electronics has developed into a promising revolutionary technology. Organic electronic materials not only have good flexibility and transparency, but are also ultra-thin, ultra-light, and environmentally friendly. The internal structure of organic electronic materials significantly affects their electrical efficiency. Currently, the processes used to manufacture these materials are very sensitive and their structures are extremely complex which makes it difficult for scientists to predict the final structure and property of the material based on the production conditions. In order to design and develop new organic electronic materials, experimental scientists have focused on building a synthesis-structure-performance relationship network between different material systems. However, since there may be multiple chemical reactions between different materials, this method is time-consuming and inefficient. Modern calculation methods are powerful tools to provide effective solutions for the organic electronic materials design for specific purposes and provide guidance for experiments. Alfa Chemistry uses computational methods to perform systematic exploration of important properties of organic electronic materials.

Application of Property Prediction

  • Accelerate the development speed and efficiency of novel organic electrical materials.
  • Provide understanding and rationale for observed material behavior.
  • Assist in the selection of materials for use in optimized devices.

Simplified overview of a machine learning workflow.Figure 1. Simplified overview of a machine learning workflow. (Chibani, Si.; Coudert, F. X. 2020)

Our Services

At Alfa Chemistry, we use various calculation methods to model the complex relationships between materials and properties, given sufficient data, allowing efficient leveraging of database and quantum chemical calculations. Our fast and high-quality services include the following:

  • First-principles (ab initio) method

First-principles (ab initio) models refer to determine the structure or properties of materials using quantum mechanics. This method only requires the basic laws of physics, such as quantum mechanics and statistical mechanics. We can use this method to accurately predict various ground state properties before synthesizing organic electronic materials. At Alfa Chemistry, our scientists apply first-principles calculations to determine the composition and evaluate the influence of crystal structure on electrochemical performance, and explore the relative thermodynamic stability of polymorphic compounds.

1. Density functional theory (DFT) calculation: We use DFT to study the electronic systems inside the organic electronic materials.

2. The group expansion method: We use this method to obtain the disordered state of some parts of the organic electronic materials. In addition, the system information at a limited temperature can also be evaluated combined with Monte Carlo technology.

3. Monte Carlo (MC) simulation: We evaluate finite temperature behavior and calculate free energy using MC method.

  • Molecular dynamics (MD) simulation

Alfa Chemistry has established multistep calculation workflows which combine DFT and MD techniques, allowing for the calculation of advanced organic optoelectronic material properties such as carrier mobility, atomic morphology and so on. Moreover, some critical thermophysical properties, such as the glass-transition temperature (Tg) and coefficient of thermal expansion (CTE), can be calculated and obtained.

  • Artificial intelligence (AI)

In the field of material prediction, researchers train relevant AI algorithm models to summarize the material state and material performance laws. A diversity of AI algorithm models are then used to analyze and predict the important properties of materials in combination with the monitored material states.

1. Machine learning (ML)

Alfa Chemistry has combined material databases and ML methods to accurately predict crucial properties of organic electronic materials. We use the information of the physical and chemical properties of atoms to build a database containing a variety of atomic performance characteristics, which can deal with complex models and predict the unique properties of materials. Our groups have applied our unique database and ML methods to generate multiple predictive models successfully.

2. Deep learning

Deep learning method possesses an excellent nonlinear analyzing capability, and has a low demand for computing power. Therefore, it has been widely employed to quickly evaluate the performance of new materials. We predict the properties based on a given chemical structure of an organic electronic material after training the model with a database.

Alfa Chemistry's Advantages

  • We can apply useful experimental information to the calculation model construction, greatly improving the reliability and accuracy of the calculation method.
  • At Alfa Chemistry, the prediction accuracy can reach higher than 90% using a verification set of thousands of molecules.
  • Our experts continue to expand the database size to improve the prediction accuracy.

Our key property prediction of organic electronic materials services remarkably reduce the cost, promote further experiments, and enhance the understanding of chemical process for customers worldwide. Our personalized and all-around services will satisfy your innovative study demands. If you are interested in our services, please don't hesitate to contact us. We are glad to cooperate with you and witness your success!


  • Chibani, Si.; Coudert, F. X. Machine learning approaches for the prediction of materials properties. APL Materials. 2020, 8(8)

Alfa Chemistry


  • Tel:
  • Fax:
  • Email:
Copyright © 2023 Alfa Chemistry. All rights reserved.