Skip to content

Predicting Subsurface Abnormalities Growth using Physics-Informed Neural Networks

Sep 2026 · 0 citations · 35 references
Computer Science

TL;DR

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.

View source

Similar papers

Open access Sep 2026

PHYSICS-INFORMED NEURAL NETWORKS FOR SPATIOTEMPORAL TUMOR GROWTH MODELING: A COMPREHENSIVE SIMULATION STUDY

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 · 0 citations
Open access Aug 2026

Advancements in  Medical Image Processing: Integrating Physics With Convolutional Neural Networks (CNN) for Enhanced Diagnostic

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 · 0 citations
Sep 2026

Gradient-based spatially weighted physics-informed convolutional recurrent network for solving discrete integrable equations

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. · 0 citations
Review Open access Aug 2026

Advancements and Future Directions in Loss Function Designs for Physics-Informed Neural Networks: A Comprehensive Review

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. · 0 citations
Open access Oct 2026

Brain Tumor Classification Using Computer Vision and Deep Learning Techniques

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 · 0 citations
Review Open access Sep 2026

Artificial, convolutional, and deep neural networks for structural health monitoring: A review

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 · 0 citations

Related blog posts

Microsoft Research Blog Nov 16, 2026

TokenEconomizer: Learning from Experience to Make AI Coding Agents More Efficient

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.

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.