EcoCurrentNet an integrated DNN-CatBoost model for predicting optoelectronic material performance under varying...

Area of Science:

• Materials Science
• Computational Science
• Optoelectronics

Background:

• Laboratory simulations often fail to replicate complex environmental conditions accurately.
• This discrepancy limits the reliability of optoelectronic material performance assessments for real-world applications.

Purpose of the Study:

• To develop an innovative model, EcoCurrentNet, for accurately simulating optoelectronic material performance under variable environmental conditions.
• To overcome the limitations of traditional laboratory-based performance assessments.

Main Methods:

• EcoCurrentNet integrates deep neural networks (DNN) with convolutional layers, residual blocks, and a CatBoost regression layer.
• The model captures spatial and nonlinear dependencies between material features and 12 environmental variables.
• It incorporates principles of thermodynamics and material science for enhanced accuracy.

Main Results:

• The model achieved a high R-squared score of 99.68%, indicating exceptional predictive accuracy.
• EcoCurrentNet effectively captures complex interactions between material properties and environmental factors.
• Demonstrated capability for reliable material behavior assessment beyond controlled laboratory settings.

Conclusions:

• EcoCurrentNet offers a more reliable and efficient approach to modeling complex physical systems like optoelectronic materials.
• The hybrid deep learning and gradient boosting architecture shows significant potential for advancing material design.
• This research paves the way for future innovations in optoelectronic material development and application.