WAIT

💎 Idea

Today, hydrological satellite data analysis is bottlenecked by high entry barriers. Building custom solutions requires a rare mix of domain expertise, DevOps, and programming. Stakeholders are forced to waste time on repetitive tasks, while existing market tools are prohibitively expensive to implement. 

WaterTech start-ups who try to use satellite data to solve real life water crises face a huge difficulty. According to Gartner, 60-80% of their time is spent (or better say wasted) on raw satellite data. Gathering it, making sense of it.

It’s holding back the Time-to-Market of new projects for 3-6 months. With the WaterTech industry projected to grow to $300 billion until 2030, that represents billions of dollars of wasted resources and missed revenue.

That's why we introduce Breezy.

With Breezy, we eliminate that 80% waste. Think of it as ChatGPT for hydrological satellite data. We’ve built a No-Code Platform that sits on top of data from Copernicus, Sentinel Hub and other releveant data sources. 

You describe your idea in plain English, and our engine handles the complex selection of spectral bands, filters, and processing in the background. 

We turn months of engineering into minutes of insight, lowering the entry barrier from thousands of dollars to as low as $50.

🛰️ EU space technologies

We use Copernicus Sentinel data via Copernicus Data Space / Sentinel Hub APIs.

Main sources:

• Sentinel-2 L2A — multispectral optical imagery used to detect water colour changes, turbidity, sediments, brown-water signals and possible bloom-related patterns.
• Sentinel-1 GRD — radar data used as an optional support layer to improve water detection and reduce uncertainty in cloudy or difficult conditions.

From Sentinel-2 bands we calculate indicators such as:

• NDWI - Normalized Difference Water Index
• MNDWI - Modified Normalized Difference Water Index
• NDTI - Normalized Difference Turbidity Index
• NDSSI - Normalized Difference Suspended Sediment Index
• NDMI - Normalized Difference Moisture Index

These are converted into simple risk layers:

• turbidity risk
• sediment risk
• brown-water risk
• possible bloom proxy
• optical pollution load
• monitoring priority

This brings value because raw satellite data becomes an easy-to-read water risk map showing where conditions look unusual and where field checks should be prioritised.

  EU Space for Water

Which of the 3 challenges are you solving, and how does this contribute to protecting and managing our water resources?

🤼 Team:

Piotr Antoniszyn - Project Manager/Data Analyst

Maks Borysławski - Software Engineer

Maciej Max - Solution Architect

Oskar Molewski - Entrepreneur/Physicist/Sales

Dariusz Szałucki - GIS & Cloud Data Engineer