Enterprise AI, in production.
    Four desks, one beat.

    PharmaNews

    Chloris Geospatial is Using Satellites and AI to Restore Trust in Carbon Markets

    They recently raised a $8.5 million Series A to scale technology and operations

    Last updated

    Chloris Geospatial is Using Satellites and AI to Restore Trust in Carbon Markets

    In the span of just two decades, the world has lost more than 100 million hectares of forest (an area roughly the size of Egypt) largely due to deforestation and degradation. The resulting release of carbon into the atmosphere has made forest preservation a central focus of global climate strategies. But efforts to invest in nature-based climate solutions have long been hampered by a critical problem: the lack of credible, consistent, and scalable data on what’s actually happening on the ground.

    Chloris Geospatial, a Boston-based climate-tech company, is tackling this head-on by combining satellite data, sensor fusion, and machine learning to deliver independent measurements of forest carbon from space. The company recently raised $8.5 million in Series A funding to scale its technology and operations, a vote of confidence from investors who believe Chloris could become a foundational platform in global carbon markets.

    A Science-First Approach to Forest Monitoring

    Chloris was co-founded by CEO Marco Albani and Dr. Alessandro Baccini, a leading researcher in remote sensing and forest carbon modeling. Dr. Baccini, who serves as Chief Science Officer, guided the development of the company’s core technology, which measures above-ground biomass and carbon stock dynamics with high spatial resolution, going back to the year 2000.

    Shifting away from traditional land cover mapping, Chloris delivers direct estimates of forest biomass and carbon change, relying on wall-to-wall data from satellites fused with airborne LiDAR and field measurements. The company’s proprietary machine learning models are trained on millions of biomass estimates and validated against independent datasets, allowing for scalable, pixel-level accuracy at resolutions as fine as 10 meters.

    About the author

    Deployed

    Related stories