7 papers
phepy: Visual benchmarks and improvements for out-of-distribution detectors
Felix Krumbiegel, Juniper Tyree, Michael Boy +2
Applying machine learning to increasingly high-dimensional problems with sparse or biased training data increases the risk that a model is used on inputs outside its training domai…
TopoFlow: Topography-aware Pollutant Flow Learning for High-Resolution Air Quality Prediction
Ammar Kheder, Helmi Toropainen, Wenqing Peng +4
We propose TopoFlow (Topography-aware pollutant Flow learning), a physics-guided neural network for efficient, high-resolution air quality prediction. To explicitly embed physical…
Inverse Neural Operator for ODE Parameter Optimization
Zhi-Song Liu, Wenqing Peng, Helmi Toropainen +5
We propose the Inverse Neural Operator (INO), a two-stage framework for recovering hidden ODE parameters from sparse, partial observations. In Stage 1, a Conditional Fourier Neural…
Cross-Resolution Attention Network for High-Resolution PM2.5 Prediction
Ammar Kheder, Helmi Toropainen, Wenqing Peng +3
Vision Transformers have achieved remarkable success in spatio-temporal prediction, but their scalability remains limited for ultra-high-resolution, continent-scale domains require…
SPIN-ODE: Stiff Physics-Informed Neural ODE for Chemical Reaction Rate Estimation
Wenqing Peng, Zhi-Song Liu, Michael Boy
Estimating rate coefficients from complex chemical reactions is essential for advancing detailed chemistry. However, the stiffness inherent in real-world atmospheric chemistry syst…
Deep Spatio-Temporal Neural Network for Air Quality Reanalysis
Ammar Kheder, Benjamin Foreback, Lili Wang +2
Air quality prediction is key to mitigating health impacts and guiding decisions, yet existing models tend to focus on temporal trends while overlooking spatial generalization. We…