Physics-Regularized Neural Networks for Urban Air Quality Prediction Under Meteorological Variability: Emission Source Estimation from Sparse Observations in London
Abstract
Abstract Urban air quality is intrinsically linked to meteorological conditions and local climate variability. Accurate emission estimation under varying atmospheric conditions requires methods that can integrate sparse monitoring data with atmospheric transport physics. Urban PM 2.5 pollution remains a major environmental concern, yet many cities rely on sparse monitoring networks with substantial missing data. Under such observational scarcity, reconstructing spatially continuous concentration fields and source-related patterns from a few stations constitutes an ill-posed inverse problem, where multiple solutions can fit the same measurements. Under such conditions, conventional receptor models and chemical transport models often struggle to provide spatially continuous information due to data limitations or high computational cost. We develop a physics-regularized neural network (PRNN) framework that incorporates ERA5 meteorological reanalysis data to estimate continuous PM 2.5 emission-related fields from sparse urban monitoring networks. The approach integrates simplified atmospheric transport physics into the learning process by constraining the admissible inverse solutions using an advection–reaction mass-balance residual, rather than treating the task as a purely data-driven prediction problem. This formulation supports joint learning of pollutant concentration fields and associated effective emission indicators under realistic data scarcity. The approach is…
Read the paper
Related studies
- Preliminary Toxicity Analysis of 3DCRT versus IMRT on the High Dose Arm of the RTOG 0126 Prostate Cancer Trial
- Adaptive Radiotherapy for Head and Neck Cancer: Initial Clinical Outcomes from a Prospective Trial
- American Association of Physicists in Medicine Task Group 263: Standardizing Nomenclatures in Radiation Oncology
- Motion Management Strategies and Technical Issues Associated with Stereotactic Body Radiotherapy of Thoracic and Upper Abdominal Tumors: A Review from NRG Oncology
- High-dose-rate interstitial brachytherapy as a monotherapy for localized prostate cancer: treatment description and preliminary results of a phase I/II clinical trial
- Highly efficient training, refinement, and validation of a knowledge-based plan quality control system for radiotherapy clinical trials
Go deeper in Evidence Hub
Evidence Hub adds a study data sheet (design, sample size, evidence level, key numbers), an AI summary and a chat grounded in the paper's text.