This AI startup from The Hague knows precisely how much rain causes a disaster

Then reality intervened. Farmers didn't use pesticides because they had no alternatives. They used them because they could not bear the risk of organic farming. Structurally cut off from banks and financial markets, they had no buffer for failed harvests.

"We misunderstood the problem," the team later wrote. The ants were not the solution. Risk was the enemy. [1]

The Pivot That Saved the Mission

Simmaco founded GreenAnt in 2020 with the mission to make sustainable land management economically viable. The ant project was supposed to be the means. But in Thailand, speaking with farmers who explained why they could not let go of pesticides even if they wanted to, the mission remained the same. The means changed.

The pivot came from an unexpected direction. To monitor whether the ants were actually working, GreenAnt used satellite data to track the health of trees. That data turned out to be much more valuable than the insects themselves.

"We realized that satellite data is an incredibly powerful tool for climate resilience," says Simmaco. "So we built an accessible, affordable interface that translates it into actionable insights." [2]

What emerged is Desidera, a platform that uses radar satellites instead of optical ones. The difference is important. In Southeast Asia, clouds block the sky more than 300 days a year. Traditional satellites see nothing. Radar cuts right through.

Under the hood, Desidera operates on a digital twin of the earth that processes real-time satellite data and projects weather conditions three to five days ahead. The AI uses Graph Neural Networks, a technique particularly suited for simultaneously processing millions of interconnected geographical points. This allows GreenAnt to model flood risk faster than existing weather systems. [7]

The system detects the exact millimeter of rainfall at a specific location that will cause flooding, scans weather forecasts on those threshold values, and sends alerts before the water arrives. [2]

Answers, Not Datasets

Studies and practical experience suggest that improved predictions and decision support can increase productivity by up to 20%. But the real insight is not the number. It's about who can use it.

Most climate analyses require specialists to interpret the data. A small farmer in Myanmar or Vietnam doesn't have access to those experts. Desidera is designed so they don't need them. Users draw their plot on a map and ask questions via a chatbot. The AI provides answers, not datasets. [6]

"This approach addresses a critical knowledge gap," explains Simmaco. "It helps strengthen overall resilience." [2]

GreenAnt has run pilots in Myanmar and Thailand, including work with an international humanitarian NGO to protect flood-prone communities. In September 2024, Typhoon Yagi caused severe flooding that affected more than 1.1 million people in 70 townships and destroyed over 2.3 million hectares of farmland. [5] The same technology that monitors mangoes in Thailand now tracks disaster risk in one of the world's most vulnerable regions. [2]

A €9 Billion Market

Farmers aren't the only ones who need early warnings. The European insurtech market is expected to reach €9.2 billion by 2027, largely driven by climate-related challenges in insurance. [8] Natural disaster losses in Europe exceeded €50 billion in 2023, forcing insurance managers to reconsider decades-old risk models. [9] GreenAnt's bet is that the sector is willing to pay for foresight.

The team has grown to ten specialists in meteorology, machine learning, and insurance. Building credible models for insurers requires fluency in both climate science and actuarial risk. Established players like Aon and Munich Re already have advanced catastrophe models, but they lack the hyperlocal precision GreenAnt offers. That granularity is where the opportunity lies.

The company was recently selected for FoodSeed, the agritech accelerator supported by CDP Venture Capital and Eatable Adventures, which offers up to €500,000 in follow-on funding. [3] GreenAnt also received support from Plug and Play, InnoQube Switzerland, and the Cassini Accelerator Program. The next step: pilots in Vietnam, Thailand, the Philippines, and Italy. [4]

The Line That Tells the Story

The morning after the team proposed the idea of giving farmers access to capital through satellite-verified data, fifty farmers stood outside their building in Thailand. They immediately understood the value. [1]

That line tells the story better than any pitch deck. Climate technology doesn't fail because the science is wrong. It fails when it solves problems people don't actually have. GreenAnt started with a beautiful idea about ants and ended with infrastructure farmers line up for.

The complexity isn't in the algorithm. It's in understanding what people truly need.

Willem Blom
Founder Dutchstartup.ai