波兰国际团队用深度学习与NVIDIA GPU改进湿度预报

Skip to content

For more than a century, meteorologists have chased storms with chalkboards, equations, and now, supercomputers. But for all the progress, they still stumble over one deceptively simple ingredient: water vapor.

Humidity is the invisible fuel for thunderstorms, flash floods, and hurricanes. It’s the difference between a passing sprinkle and a summer downpour that sends you sprinting for cover. And until now, satellites have struggled to capture it with the detail needed to warn us before skies crack open.

A team from the Wrocław University of Environmental and Life Sciences (UPWr) may help change that. In a paper published this month in _Satellite Navigation_, researchers describe how deep learning can transform blurry global navigation satellite system (GNSS)-based snapshots of the atmosphere into sharp 3D maps of humidity, revealing the hidden swirls that shape local weather.

The secret? A super-resolution generative adversarial network (SRGAN) — a kind of AI best known for making grainy photos look crisp. Instead of celebrities or landscapes, researchers trained the network on global weather data, powered by NVIDIA GPUs. The result: low-resolution readings from navigation satellites get “upscaled” into high-resolution humidity maps with far fewer errors.

62%

Poland

reduction in forecast errors

52%

California

error reduction, even in rainy conditions

Compared with older methods that smeared details into a watercolor blur, the AI produced sharp gradients that actually matched what ground instruments saw.

And because weather prediction is as much about trust as accuracy, the team added a twist: explainable AI. Using visualization tools like Grad-CAM and SHAP, they demonstrated where the model “looked” when making decisions. The AI’s gaze landed, reassuringly, on storm-prone areas — Poland’s western borders, California’s coastal mountains — exactly where forecasters know the atmosphere can turn nasty.

“

“High-resolution, reliable humidity data is the missing link in forecasting the kind of weather that disrupts lives. Our approach doesn’t just sharpen GNSS tomography — it also shows us how the model makes its decisions. That transparency is critical for building trust as AI enters weather forecasting.”

— Saeid Haji-Aghajany, Assistant Professor, Wrocław University of Environmental and Life Sciences

How it works

01

GNSS Signals

Navigation satellites passively sense water vapor as signals pass through the atmosphere.

02

SRGAN Upscaling

An NVIDIA GPU-powered deep learning model sharpens low-res humidity readings into 3D maps.

03

Explainable AI

Grad-CAM and SHAP show forecasters exactly where the model focuses its attention.

The implications could be enormous. Feed these sharper humidity fields into physics-based or AI-driven weather models, and you get forecasts that can catch sudden downpours or flash floods before they hit. Communities living under skies that turn dangerous in minutes could gain crucial lead time.

The bottom line

Not the thunder. Not the lightning.

It’s the humidity.

Reference:DOI: 10.1186/s43020-025-00177-6

• Categories:
• Corporate
• Deep Learning

Related News


AI Infrastructure

How NVIDIA’s Inference Software Stack Powers the Lowest Token Cost

Jun 30, 2026


AI Infrastructure

NVIDIA and AWS Collaborate to Bring AI to Production at Scale

Jun 23, 2026


AI

How Businesses Are Building Specialized AI They Can Trust

Jun 23, 2026


AI Infrastructure

NVIDIA Powers Over 400 of the World’s 500 Fastest Supercomputers

Jun 23, 2026

Follow Us

'/%3e %3cpath id='NVIDIA' d='M463.9,151.934v13.127h3.707V151.934Zm-29.164-.018v13.145h3.74v-10.2l2.918.01a2.674,2.674,0,0,1,2.086.724c.586.625.826,1.632.826,3.476v5.995h3.624V157.8c0-5.183-3.3-5.882-6.536-5.882Zm35.134.018v13.127h6.013c3.2,0,4.249-.533,5.38-1.727a7.352,7.352,0,0,0,1.316-4.692,7.789,7.789,0,0,0-1.2-4.516c-1.373-1.833-3.352-2.191-6.306-2.191Zm3.677,2.858h1.594c2.312,0,3.808,1.039,3.808,3.733s-1.5,3.734-3.808,3.734h-1.594Zm-14.992-2.858-3.094,10.4-2.965-10.4h-4l4.234,13.127h5.343l4.267-13.127Zm25.749,13.127h3.708V151.935h-3.709ZM494.7,151.939l-5.177,13.117h3.656l.819-2.318h6.126l.775,2.318h3.969l-5.216-13.118Zm2.407,2.393,2.246,6.145h-4.562Z' transform='translate(-399.551 -148.155)'/%3e %3cpath id='Eye_Mark' data-name='Eye Mark' d='M129.832,124.085v-1.807c.175-.013.353-.022.533-.028,4.941-.155,8.183,4.246,8.183,4.246s-3.5,4.863-7.255,4.863a4.553,4.553,0,0,1-1.461-.234v-5.478c1.924.232,2.31,1.082,3.467,3.01l2.572-2.169a6.81,6.81,0,0,0-5.042-2.462,9.328,9.328,0,0,0-1,.059m0-5.968v2.7c.177-.014.355-.025.533-.032,6.871-.232,11.348,5.635,11.348,5.635s-5.142,6.253-10.5,6.253a7.906,7.906,0,0,1-1.383-.122v1.668a9.1,9.1,0,0,0,1.151.075c4.985,0,8.59-2.546,12.081-5.559.578.463,2.948,1.591,3.435,2.085-3.319,2.778-11.055,5.018-15.44,5.018-.423,0-.829-.026-1.228-.064v2.344h18.947v-20Zm0,13.009v1.424c-4.611-.822-5.89-5.615-5.89-5.615a9.967,9.967,0,0,1,5.89-2.85v1.563h-.007a4.424,4.424,0,0,0-3.437,1.571s.845,3.035,3.444,3.908m-8.189-4.4a11.419,11.419,0,0,1,8.189-4.449v-1.463c-6.043.485-11.277,5.6-11.277,5.6s2.964,8.569,11.277,9.354v-1.555C123.731,133.451,121.643,126.728,121.643,126.728Z' transform='translate(-118.555 -118.117)' fill='%23000000'/%3e %3c/svg%3e)United States

• Privacy Policy
• Your Privacy Choices
• Terms of Service
• Accessibility
• Corporate Policies
• Product Security
• Contact

Copyright © 2026 NVIDIA Corporation

Share This

Facebook

LinkedIn

Share on Mastodon

Enter your Mastodon instance URL (optional)Share