Skip to content

Deep Learning-Based Meteorological Data Downscaling: A Comparative Study with Physics-Informed CNN and a Component-Level Ablation Analysis

· 0 citations · 11 references

TL;DR

The proposed Physics-Informed CNN (PICNN), which integrates multi-scale feature extraction, spatial attention mechanisms, and a composite physics-informed loss function incorporating mean squared error, Laplacian spatial smoothness regularization, and spatial energy conservation constraints, achieves the best performance among all models.

View source

Similar papers

Open access Sep 2026

Optimization of Spatial Downscaling Models for Satellite Imagery Based on Deep Learning and Generative Artificial Intelligence

Highlights What are the main findings? Off-the-shelf pretrained super-resolution models (ESRGAN, SwinIR) applied directly to Landsat-to-Sentinel-2 upscaling do not outperform bicubic interpolation on pixel-wise metrics, remaining statistically indistinguishable from it (Nemenyi post hoc), thereby revealing a domain ada...

Juan Valdés-Quintero, R. D. Vásquez-Salazar, J. C. Parra et al. · 0 citations
Open access Aug 2026

WindHCT: context and local hybrid CNN Transformer for wind speed super-resolution

Physically oriented evaluations further suggest that the proposed WindHCT improves several aspects of wind-field reconstruction beyond pixel-wise accuracy.

Won-ji Jo, Sung-Wook Park, Y. Park et al. · 0 citations
#diffusion models Open access Sep 2026

China regional 3 km downscaling based on residual Corrective Diffusion model

Forecasts of radar composite reflectivity reveal that CorrDiff, as a generative model, is capable of capturing fine-grained meteorological details, yielding more physically realistic predictions than deterministic regression-based downscaling models.

Hong-Lu Sun, Hao Jing, Zhi-Xiang Dai et al. · 0 citations
Open access Sep 2026

Modeling Atmospheric Radiative Transfer for Solar Energy Harvesting: A Chemical-Informed Deep Learning Approach with CNN-LSTM-Attention Networks

Accurate prediction of solar irradiance is fundamentally a problem of modeling radiative transfer through a dynamic, multi-component chemical system—the atmosphere. Variability in atmospheric composition and physical state, dictated by parameters like humidity, pressure, and aerosol content, poses a significant chal...

Simon Onuwa Agbonifo · 0 citations
Conference Aug 2026

Bridging Learning and Forecasting: An Analytical Study of LSTM and CNN Machine Learning Techniques for Weather Prediction

The research paper presents a detailed account of how deep learning, more specifically Long Short-Term Memory (LSTM) and Convolutional Neural Network (CNN) architectures, has been pivotal in advancing weather prediction accuracy as well as reliability. Even though numerical weather prediction models based on traditiona...

Ishant Bharol, Anita Goyal, Anmol Goyal · 0 citations
Open access Sep 2026

CMIP6-Driven Groundwater-Level Projections and Climate Risk Mapping for South Korea Using a Hybrid Deep Learning Framework

Groundwater variability is recognized as a critical constraint on long-term water resource sustainability in South Korea under nonstationary climate forcing. This study developed a groundwater-level (GWL) projection framework based on CMIP6 simulations, validated against national monitoring data, screened for physical...

M. Waqas, Sang Min Kim · 0 citations

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