An Electric Potential-Augmented Benchmark Dataset for Physics-Guided Image Reconstruction of Electrical Capacitance Tomography
Researchers have developed a new benchmark dataset for Electrical Capacitance Tomography (ECT) image reconstruction that incorporates electric potential fields. This dataset, generated using a COMSOL-MATLAB pipeline, includes 20,000 samples with capacitance vectors, permittivity distributions, and full-field potential maps. The inclusion of this latent physical information aims to improve the accuracy and robustness of deep learning models by explicitly integrating physical laws into the learning process. AI
IMPACT Provides a standardized dataset to advance physics-guided machine learning for image reconstruction in ECT.