This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior, by integrating physics directly into the neural network.
Abstract
The research explores the pioneering integration of Physics-Informed Neural Networks (PINNs) into the domain of Ground-Penetrating Radar (GPR) data prediction. This research presents a detailed development framework for a specialized PINN model, proficient at interpreting and forecasting GPR data, much like how medical imaging models predict tumor behavior. By harnessing the synergy between deep learning algorithms and the physical laws governing subsurface structures or in medical terms, human tissues the model effectively embeds the physics of electromagnetic wave propagation into its architecture. This ensures that predictions not only align with fundamental physical principles but also mirror the precision needed in medical diagnostics for detecting and monitoring tumors. The suggested deep learning structure comprises three components: a CNN, a spatial feature channel attention (SFCA) mechanism, and ConvLSTM, along with temporal feature frame attention (TFFA) modules. The attention mechanism computes channel attention and temporal attention weights using self-adaptation, thereby fine tuning the visual and temporal feature responses to extract the most pertinent and significant visual and temporal features. By integrating physics directly into the neural network, our model has shown enhanced accuracy in forecasting GPR data. This improvement is vital for conducting effective assessments of bridge deck conditions and other evaluations related to civil infrastructure. The use of Physics Informed Neural Networks (PINNs) has demonstrated the potential to transform the field of Non-Destructive Evaluation (NDE) by enhancing the precision of infrastructure deterioration predictions. Moreover, it offers a deeper insight into the fundamental mechanisms of deterioration, viewed through the prism of physics-based models.
Mathematical modeling of tumor growth using partial differential equations (PDEs) has emerged as a powerful tool for understanding cancer progression and optimizing therapeutic strategies. However, traditional numerical methods face significant challenges when applied to complex geometries, sparse clinical data, and in...
M. M. Pariona· Revista de Estudos Interdisc...· 0 citations
A physics-Informed Convolutional Neural Network for sort of brain tumour categorization from MRI images and followed by its testing framework to improve consistency and healthcare organizational adoption of deep learning frameworks is proposed.
Ayat Muthana, Zainab Mohammad Habeeb· Al-Noor Journal of Engineeri...· 0 citations
A gradient-based adaptive spatially weighted PhyCRNet (GSW-PhyCRNet), where gradient information is utilized to guide adaptive spatial refinement, enabling the model to capture local spatial features and improve the fitting precision of physical constraints is proposed.
Jian-Bo Cheng, Li Cheng, Cheng-Ze Hong et al.· European Physical Journal B...· 0 citations
This review synthesizes recent advances in loss function designs for Physics-Informed Neural Networks (PINNs), a transformative approach to solving partial differential equations (PDEs) by embedding physical laws into deep learning frameworks, to equip researchers with insights to refine PINN methodologies.
M. Esmaeilbeigi, Daniela Annunziata, Salvatore Cuomo et al.· Journal of Scientific Comput...· 0 citations
This research addresses the critical task of brain tumor detection and classification by leveraging advanced neural networks and deep learning techniques. The study focuses on detecting three prevalent types of brain tumors—glioma, meningioma, and pituitary tumors—as well as identifying cases without tumors. Two cuttin...
Amal Alshahrani· Engineering, Technology &...· 0 citations
The reliability and durability of civil engineering structures rely heavily on advanced Structural Health Monitoring (SHM) systems based on in-depth knowledge. Conventional approaches, often based on manual inspections suffer from high costs, long inspection times, and subjective judgment. Neural Network-based methods...
A. Khatir, R. Capozucca· HCMCOU Journal of Science -...· 0 citations
Related blog posts
Microsoft Research Blog· microsoft.comNov 16, 2026
AI coding agents are increasingly help developers fix bugs and build features largely on their own, but every interaction with their models consumes tokens. In each session, an agent sends instructions, tool descriptions, and session history to its model. Most efforts to reduce this cost focus on individual tasks. Yet developers return to the same […] The post TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient appeared first on Microsoft Research.
MIT News · Artificial Intelligence· news.mit.eduNov 13, 2026