AI-powered monitoring at previously unobtainable speed and scale
The world is changing rapidly. Every day, cities grow, crops are planted, forests are harvested, droughts and floods are on the rise … and all of this affects the infrastructure, food systems, water supplies, and natural resources that we depend on. IO Monitor enables decision makers to understand risks and anticipate change, in near-real-time.Order Now
Spotlighting change in the areas you care about
Impact Observatory’s innovative AI-powered methods automate and accelerate Land Use Land Cover mapping and monitoring in near-real-time. IO Monitor uses a unique deep learning approach to classify land use and land cover categories globally using state-of-the-art Copernicus Sentinel-2 imagery. Custom land use and land cover change maps are available for any area of interest, over user-specified time periods, beginning in 2018, up to the present (refreshed daily). Results have an average accuracy of 85%, which has been independently assessed in a peer-reviewed scientific study as the most accurate global maps currently available [ref: Venter et al. 2022].
Images of Earth collected by the Sentinel-2 satellite constellation observe the world as trillions of pixels, each showing a 10 meter by 10 meter patch of ground. IO turns millions of these satellite images collected throughout the year into maps that label every pixel into one of nine categories of major land use and land cover. Since the release of our first global map in June 2021, we have been thrilled to receive over 1,000,000 visitors accessing and downloading our annual maps via Esri Living Atlas, Microsoft Planetary Computer, and the AWS Registry of Open Data.
Results have an average accuracy of 85% (compared to human expert labels).
Maps available reflecting satellite data from as recently as this month.
You define your area of interest and the time period you want to monitor.
Early Access Program pricing as low as $1/km2 allows you to access data easily and within budget.
Timely, actionable data for insights and decisions
Agricultural expansion can lead to deforestation, soil degradation, loss of biodiversity, and water pollution, and unhealthy crops can create food insecurity. IO Monitor can help assess risks to food systems as well as the surrounding ecosystems by comparing the amount of land under agricultural production to previous growing seasons. One example is the expansion of agricultural land into rainforest areas of South America, clearly visible in this sample data from Bolivia.
Deforestation is a significant contributor to climate change and a challenge for corporations and governments around the world. For organizations committed to being Deforestation Free, IO Monitor can help identify where supply chains impact tree loss, and provide quarterly change results in the regions where companies operate.
Cities around the world are growing at incredible rates. IO Monitor can help to verify the magnitude and spatial patterns of this rapid urban expansion. In the span of a few months, land at the edge of Las Vegas shows the initial construction of a new housing development. This same growth can be seen in cities around the world such as New Cairo (Egypt), The Line (Saudi Arabia), and Xiong'an (China).
Forests act as natural water filters, improving the quality of water by removing pollutants and sediment. Trees also help reduce the risk of both floods and droughts. IO Monitor can help assess where forest loss has occurred and might lead to an impact on critical watersheds and downstream communities. Customers use this data to assess risks and prioritize action plans. Tree loss due to conflict increases risk to the downstream Dnipro Reservoir in Ukraine, which can be seen in these results.
Get additional information through our product documentation.
For more information about ongoing subscriptions, volume discounts, and future products contact our sales team.
Get help with issues during your map creation through our technical support.
Help us improve our product by contacting us with your feedback.