← Back to all news
arXiv Machine Learning By Mehrdad Shafiei Dizaji, Hoda Azari

Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks

Read the original on arXiv Machine Learning →

The paper introduces a Physics‑Informed Neural Network (PINN) tailored for predicting Ground‑Penetrating Radar (GPR) data, integrating electromagnetic wave propagation physics into a deep learning framework. The architecture combines a CNN, spatial feature channel attention, ConvLSTM, and temporal feature frame attention to extract relevant visual and temporal features. Results show improved accuracy in forecasting GPR data, aiding assessments of bridge deck conditions and other civil infrastructure evaluations.

Machine-generated by The Flow from the publisher's headline and feed description — not written or checked by a human. The full article lives at arXiv Machine Learning.

Related stories

arXiv AI
Sep 17

Enhancing Physics-Informed Neural Networks with Domain-aware Fourier Features: Towards Improved Performance and Interpretable Results

The paper proposes Domain-aware Fourier Features (DaFFs) for Physics-Informed Neural Networks (PINNs), embedding domain-specific geometry and boundary conditions into the positional encoding. DaFFs eliminate the need for explicit boundary loss terms, simplify optimization, and reduce training cost, leading to orders-of-magnitude lower errors and faster convergence compared to vanilla PINNs and RFF-based PINNs. An LRP-based explainability framework further shows that DaFFs produce more physically consistent relevance attributions, improving interpretability.

By Alberto Mi\~no Calero, Luis Salamanca, Konstantinos E. Tatsis
ragsafety
More like this →
Hugging Face Trending Papers
Jun 25

A Multi-Fidelity Convolutional Autoencoder-Transfer Learning Framework for Guided-Wave-Based Damage Diagnosis Using Large Simulated and Limited Experimental Datasets

Guided wave-based structural health monitoring (GWSHM) with onboard transducers offers significant potential for the early diagnosis of damage in engineering structures. However, the practical deployment of deep learning models is often hindered by the limited availability of labelled experimental data and the high computational cost of generating large-scale high-fidelity simulation datasets.

fine-tuning
More like this →
arXiv AI
Sep 18

Physical knowledge on historical data matters more than enforcing physical constraints on the forecast

The paper introduces a Physics Informed Recurrent Neural Network (PIRNN) that simultaneously predicts target time series and unobservable intermediate physical variables, enhancing robustness and interpretability. It adapts to any physical model with multiple equations and variables, demonstrated on groundwater level predictions using the Gardenia model. Experiments on twelve real‑world datasets show PIRNN outperforming several neural network baselines and the Gardenia model, with an ablation study confirming the value of physical knowledge.

By Etienne Lehembre (CA, LIFO), Pascal Audigane (BRGM), Vincent Nguyen (LIFO), Christel Vrain (LIFO, CA), Thi-Bich-Hanh Dao (LIFO, CA)
benchmarks
More like this →