Insight
3 min read
Simmaco had founded GreenAnt in 2020 with the mission of making sustainable land management economically viable. The ant project was meant to be the means. But in Thailand, in conversations with farmers who explained why they could not abandon pesticides, even if they wanted to, the mission stayed the same. The means changed.
The pivot came from an unexpected direction. To monitor whether the ants were actually working, GreenAnt had used satellite data to track the health of trees. That data turned out to be far more valuable than the insects themselves.
"We realised 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 rather than optical ones. The distinction matters. In Southeast Asia, clouds block the sky for more than 300 days a year. Conventional satellites see nothing. Radar cuts straight through.
Under the hood, Desidera runs 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 well suited to processing millions of interconnected geographic points simultaneously. This allows GreenAnt to model flood risk faster than existing weather systems. [7]
The system detects the exact millimetre of precipitation that will cause a flood at a specific location, scans weather forecasts for those threshold values, and sends warnings before the water arrives. [2]
Studies and practical experience suggest that improved forecasts and decision support can increase productivity by up to 20%. But the real insight is not the number. It is about who can actually use it.
Most climate analyses require specialists to interpret the data. A smallholder farmer in Myanmar or Vietnam has no access to those experts. Desidera is built so that they do not 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," Simmaco explains. "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 across 70 townships and destroyed more than 2.3 million hectares of agricultural land. [5] The same technology that monitors mangoes in Thailand now tracks disaster risk in one of the world's most vulnerable regions. [2]
Farmers are not the only ones who need early warnings. The European insurtech market is expected to reach €9.2 billion by 2027, driven largely by climate-related challenges in insurance. [8] Natural disaster losses in Europe exceeded €50 billion in 2023, forcing insurance executives 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 such as Aon and Munich Re already have sophisticated catastrophe models, but they lack the hyper-local precision that GreenAnt offers. That granularity is where the opportunity lies.
The company was recently selected for FoodSeed, the agritech accelerator backed by CDP Venture Capital and Eatable Adventures, which offers up to €500,000 in follow-on funding. [3] GreenAnt has 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 morning after the team had floated the idea of giving farmers access to capital through satellite-verified data, fifty farmers were standing outside their building in Thailand. They understood the value immediately. [1]
That queue tells the story better than any pitch deck. Climate technology does not fail because the science is wrong. It fails when it solves problems people do not actually have. GreenAnt started with a compelling idea about ants and ended up with infrastructure that farmers queue up for.
The complexity is not in the algorithm. It lies in understanding what people truly need.
CuspAI, founded in 2024 and operating from Amsterdam and Cambridge, uses generative AI to design new materials that can be discovered up to ten times faster than through traditional methods. The company has raised $130 million to date and works with partners including ASML, Meta and Hyundai.
Rotterdam-based Crownstone is building an indoor positioning system using Bluetooth modules mounted behind power outlets that draw power from the electrical grid. The system localises people and objects at room level and targets applications in healthcare, safety and building management.
The Dutch healthcare and health sector counts 78 active startups in 2026, a large share of which deploy AI for diagnostics, hospital logistics and home care. Funding is concentrated among a handful of players; broad adoption and regulation remain the principal bottlenecks.
