<- Back to blog start page


5 emerging technologies for better weather forecasting

Weather forecasting is constantly evolving with new technology and techniques. Some of the emerging trends in weather forecasting include using machine learning, new kinds of sensors, incorporating data from crowdsourcing, and developing better models to predict extreme weather events.

My starting point for exploring the weather forecasting technology space were these data from Mergeflow (click on the image below to see the data snapshot):

Data snapshot from Mergeflow, including venture investments, market analyses, patents, R&D publications, news and blogs related to weather forecasting.
Data snapshot from Mergeflow, including venture investments, market analyses, patents, R&D publications, news and blogs related to weather forecasting.

Starting out from these data, I selected five examples of technologies that I personally found particularly interesting. I focused on technologies that enable weather forecasts, not technologies that use weather forecasts (e.g. in logistics or farming).

Skydweller: Long-endurance autonomous UAVs for weather observation

Remember SolarImpulse, the airplane that went around the world, powered only by solar energy?

Skydweller is a U.S.-Spanish aerospace company that has licensed the SolarImpulse technologies. In September 2021, they raised $40M Series A from Leonardo, Marlinspike Capital, and Advection Growth Capital, among others.

SolarImpulse  2 in flight, image from Skydweller.
SolarImpulse 2 in flight image from <a href=httpsskydwelleraero target= blank rel=noreferrer noopener>Skydweller<a>

However, unlike SolarImpulse, which was a piloted aircraft, Skydweller modified the plane to fly autonomously. And it can take various payloads, including instruments for meteorological observations.

For data analytics, Skydweller has partnered with Palantir, to use their Foundry analytics platform.

PlanetiQ: Satellite-based weather sensor technology

PlanetiQ makes sensors that use GPS radio occultation. This is a technology that analyzes how the atmosphere bends GPS signals. And how the signal is bent is influenced by atmospheric density and other factors. In other words, how the GPS signal is bent tells you something about the current status and physical properties of the atmosphere.

This schematic illustrates how PlanetiQ's satellite-based sensors work. Image from PlanetiQ.
This schematic illustrates how PlanetiQs satellite based sensors work Image from <a href=httpplanetiqcomgps ro 101 target= blank rel=noreferrer noopener>PlanetiQ<a>

In 2019, PlanetiQ raised $18.7M Series B from New Science Ventures, AV8 Ventures, Valo Ventures, Kodem Growth Partners, Access Venture Partners, Virginia Tech Innovation Fund, Hemisphere Ventures, Service Provider Capital, Earth Investments, Moonshots Capital, and others.

If I interpret them correctly, PlanetiQ makes the sensors but not the satellites. The microsatellites that carry the sensors are made by Blue Canyon Technologies, a Raytheon subsidy. And just a few days ago, on April 1 2022, SpaceX launched the first such satellite with PlanetiQ’s sensors on board.

Scala Computing: On-demand high performance computing for weather forecasting

No, I won’t make any jokes about cloud computing here…

Let’s say you are a weather scientist. Then you’ll certainly know a lot about computational modeling. But you might not have the compute infrastructure expertise to actually implement and run your models in an affordable way.

This is where Scala Computing comes in. They have built a platform so that you can run your weather models, without having to worry about the details of the underlying compute infrastructure. Here is a schematic showing this infrastructure (click on the image to see it in full size):

Scala Computing infrastructure for weather simulations. Image from Scala Computing's product datasheet.
Scala Computing infrastructure for weather simulations. Image from Scala Computing’s product datasheet.

In 2019, Scala Computing raised $5M, in a round led by HardHill Trust.

Aeolus: A global wind radar, built by the European Space Agency

Aeolus is the name of ESA’s wind mission (and the name of the ancient Greek wind god). It uses a satellite-based wind LiDAR. A wind LiDAR is a remote sensing technology that uses lasers to measure wind speeds and directions. And the Aeolus mission uses this technology in order to better understand wind patterns on a global scale.

Example of a wind profile, generated by Aeolus. Image from ESA.
Example of a wind profile generated by Aeolus <a href=httpswwwesaintApplicationsObserving the EarthFutureEOAeolusAeolus goes public target= blank rel=noreferrer noopener>Image from ESA<a>

As is typical of space missions, Aeolus involves many collaborations between scientists from different research organizations. Just looking at some recent R&D publications resulting from the Aeolus project, Mergeflow gives a sizable network of co-authors (click on the image to see it in full size):

Co-author network for Aeolus-related R&D publications, extracted by Mergeflow.
Co-author network for Aeolus-related R&D publications, extracted by Mergeflow.

If you have a Mergeflow account, you can explore this network interactively here. If you don’t have an account, you can sign up for a free Mergeflow trial here.

CAMALIOT: Crowdsourcing data for more accurate weather forecasting

Remember PlanetiQ’s sensor above that measures how GPS signals are bent by the atmosphere, depending on its conditions? CAMALIOT is an ESA project that also uses GPS signals. It measures how GPS signals are modified, and then uses machine learning to relate these measurements to differences in atmospheric conditions. Humidity is a particular focus.

But CAMALIOT uses crowdsourcing. Here is the idea: As a GPS signal travels through the atmosphere, it is slightly delayed, depending e.g. on atmospheric conditions. This is called “scintillation” (like the effect that causes twinkling of stars). Now, when you have more than one signal between a satellite and a signal, each signal scintillates slightly differently. And measuring these differences tells you something about atmospheric conditions. This, in turn, can help improve weather forecasting.

There is an Android app that you can install, if you want to contribute to the project. But like I said, CAMALIOT requires more than one signal to travel between your phone and a satellite. This means you need a phone with a dual-frequency GPS. As far as I know, iPhones don’t have that yet, which is why the app is only available for Android currently.

Screenshot from the CAMALIOT app on my smartphone. Participants in the measurement campaign can win prizes, such as phones and Amazon vouchers.
Screenshot from the CAMALIOT app on my smartphone Participants in the measurement campaign can win prizes such as phones and Amazon vouchers

This article was written by:

Florian Wolf

Florian Wolf

Florian is founder and CEO at Mergeflow, where he is responsible for company strategy and analytics development at Mergeflow. Previously, Florian developed analytics software for risk management at institutional investors. He also worked as a Research Associate in Computer Science and Genetics at the University of Cambridge. Florian has a PhD in Cognitive Sciences from MIT.

Get notified when we have new research (once or twice per month):

We only collect and use your information in accordance with our Privacy Policy.