Fundraising Fox
hylosense
Techstars '23Skopje, MK · Founded 2023 · 7 employees on LinkedIn · 2 known investors
Find your way into hylosense
Each arrow is one introduction. Sign up to fill in the first one.
Ask Henry Ukoha to introduce you to Gorjan Jovanovski
You →Henry · together at Techstars and Audi Mobility Accelerator 2023 →Gorjan
Sign up to find every way you can get introduced to hylosense
- Your email: who you already know at hylosense, and who your contacts know
- 2nd- and 3rd-degree connections: people you know who worked, studied or invested with the hylosense team
- Your LinkedIn: the connections who can make the intro for you
We rank every route by how warm it is, so you raise on warm intros instead of cold emails.
Hylosense develops environmental data analysis and weather forecasting technology. The company's founders previously created AirCare, a mobile app for air pollution tracking used by millions globally.
Also known as Hylosense
Founders & leadership
hylosense was founded in 2023 by Gorjan Jovanovski.
Investors · 2
How we know: open dataset · 5k.vc investor directory · Not right? Tell us
How we know: the Techstars portfolio · open dataset · Top 3000 Accelerator Startups (no YC) 2026-08 · open dataset · 5k.vc investor directory · Not right? Tell us
Company profile
researched Sep 2026Hylosense develops artificial-intelligence weather models trained individually for each power generation asset, rather than supplying a single regional forecast feed. The company ingests site-level inputs such as terrain, elevation, land cover and local microclimate, then calibrates a dedicated model per asset against that site's own SCADA observations. Forecasts are delivered day-ahead and intra-day through an API that feeds into customers' existing trading and SCADA systems, which the company states requires no hardware installation or workflow change, with models live within 30 days of deployment.
The company positions its output against generic numerical weather prediction products from providers such as ECMWF and DWD, claiming its site-tuned approach removes residual local bias. Stated performance figures include up to 60% better day-ahead generation accuracy, 20-40% improvement in day-ahead wind forecast accuracy in an ongoing Nordic pilot, and up to 64% improvement in temperature forecast accuracy across gas plant locations in the UK and Germany. Beyond short-term forecasting, Hylosense offers site risk assessment for prospective solar plant locations using climate projection data under different greenhouse-gas emission scenarios combined with terrain elevation and land cover data.
The team also publishes a public temperature inversion forecast tool that estimates conditions likely to trap air pollution near the surface, using thermal layer structure, inversion strength, cloud cover, wind and precipitation, and drawing on Hylosense data alongside the Open-Meteo API and OpenStreetMap.
Business model
Hylosense sells site-specific weather forecasting to energy companies, delivering day-ahead and intra-day forecasts via API into customers' existing trading and SCADA systems. The stated customer value is reduction of imbalance costs arising from mismatches between forecast and actual generation.
Traction
An ongoing pilot with Fortum forecasts wind at parks in the Nordics, reported as achieving 20-40% improvement in day-ahead wind forecast accuracy. Deployments across gas power plant locations in the UK and Germany are reported to have delivered up to 64% improvement in temperature forecast accuracy, with models live and calibrated within 30 days.
Latest developments
Hylosense was named a top influential company by Bloomberg Adria. It was awarded best startup at Fortum's Spark Innovation Challenge, out of which the ongoing Nordic wind forecasting pilot grew.
▸Full profile — market position, technology, go-to-market, geography
Market position
Hylosense competes with general-purpose numerical weather prediction feeds, referencing ECMWF and DWD outputs as the baseline its per-asset models are intended to improve upon.
Rather than distributing a single forecast product to all customers, Hylosense trains a separate model for each asset, calibrated to that site's own observations, targeting local bias that regional kilometre-scale grids leave unresolved.
Technology
One AI weather model is trained per generation asset. Inputs include the asset's terrain, elevation, land cover and local microclimate, and each model is calibrated against on-site SCADA observations rather than a shared regional average. The company states this captures local effects that grid-based forecasts from ECMWF and DWD average away. A separate temperature inversion forecasting tool computes pollution-trapping risk from thermal layering, inversion strength, high/mid cloud cover, low fog, wind speed above 15 km/h and rainfall above 2 mm, using Hylosense data with the Open-Meteo API and OpenStreetMap.
Go-to-market
Direct enterprise sales to utility generation, trading and grid operations teams, with prospects invited to schedule a technical briefing. The website includes an interactive calculator that estimates potential annual imbalance-cost savings per asset for gas plants, wind parks and solar parks. Pilot programs and innovation competitions have served as entry points, including Fortum's Spark Innovation Challenge.
Generation, trading and grid operations teams at utilities. Named application sectors are power generation (gas, wind, solar and hydro), energy trading desks managing intraday positions and imbalance exposure, transmission system operators concerned with grid capacity, congestion and losses, and energy storage operators planning charging and dispatch.
Geography
Customer engagements referenced include wind parks in the Nordics and gas power plant locations in the United Kingdom and Germany; the company states it works with utility teams worldwide.
Compiled by commissioned research from 6 cited public sources — announcements, filings, and press listed under research sources below.
Key figures
latest reportedCompany-reported or press-reported figures, each dated to when it was claimed — not independently audited.
Timeline · 4
launches, deals, and filingsHylosense was awarded best startup at Fortum's Spark Innovation Challenge.
Hylosense states it has been chosen as a top influential company by Bloomberg Adria.
Hylosense is running a pilot with Fortum forecasting wind at parks in the Nordics, reported as achieving 20% to 40% improvement in day-ahead wind forecast accuracy. The project grew out of Fortum's Spark Innovation Challenge.
Hylosense publishes a temperature inversion forecast tool that predicts air pollution trapping conditions, built on Hylosense data, the Open-Meteo API and OpenStreetMap.
Dated company events from announcements, filings, and press; legal rows summarize public dockets and regulator releases.
▸Research sources · 6
primary sources listed
- hylosensehylosense.com · web
6 public sources were cited for this profile; the first-party ones are listed here.
Frequently asked questions
- What does hylosense do?
- Hylosense builds per-asset AI weather models that help energy companies forecast generation and cut imbalance costs.
- Who founded hylosense?
- hylosense was founded by Gorjan Jovanovski in 2023.
- Who are hylosense's investors?
- hylosense's investors include South Central Ventures, Techstars.
- Where is hylosense headquartered?
- hylosense is headquartered in Skopje, MK.