With space-based lasers and artificial intelligence, scientists are revolutionizing how we measure the carbon held in our forests—and it could reshape climate change strategies worldwide.
Key Points at a Glance
- Satellite-based LiDAR and AI used to map forest biomass in Arkansas
- New method improves speed and accuracy of carbon cycle tracking
- Study combines NASA GEDI, Sentinel satellites, and machine learning
- Gradient boosting algorithm delivered the best predictions
- Better data helps shape climate policies and forest conservation
Forests are Earth’s lungs—but until now, we’ve struggled to measure how well they breathe. Thanks to a high-tech mix of space lasers, satellite imagery, and artificial intelligence, geospatial scientist Hamdi Zurqani has pioneered a faster, smarter way to assess forest biomass—crucial for tracking the carbon cycle at the heart of climate change research.
Zurqani, an assistant professor at the Arkansas Forest Resources Center, led a project that combines satellite data with machine learning algorithms to estimate how much carbon is stored in forests. His work produced the first high-resolution forest canopy cover map for the entire state of Arkansas, offering a new lens for managing forests and informing environmental policy.
Why is this important? Forests hold about 80 percent of the world’s terrestrial carbon. But accurately estimating this carbon—also known as aboveground biomass—has traditionally relied on ground-based surveys that are slow, expensive, and geographically limited. Zurqani’s method eliminates those limitations using open-access satellite data and artificial intelligence.
The core of his innovation lies in blending data from NASA’s GEDI LiDAR system—three lasers mounted on the International Space Station—with optical data from the European Space Agency’s Sentinel-1 and Sentinel-2 satellites. LiDAR, or light detection and ranging, provides precise 3D models of forest canopies. When combined with Sentinel imagery and vegetation indices, the dataset becomes a rich source of insight for machine learning.
Zurqani tested four AI algorithms to crunch the numbers: gradient tree boosting, random forest, classification and regression trees (CART), and support vector machines. Gradient tree boosting stood out, offering the most accurate biomass predictions with the lowest error rates. This demonstrates that while AI is a powerful tool, the choice of algorithm matters greatly in environmental applications.
Beyond scientific validation, the real impact lies in how this data can be used. Better biomass maps mean better understanding of how forests sequester carbon—and how much carbon is released when they’re cut or burned. This directly influences global efforts to mitigate climate change, especially as countries and corporations seek to balance carbon emissions with offsets through forest preservation.
Zurqani notes that this approach is especially useful in remote or hard-to-access areas. And while challenges like weather interference and limited LiDAR coverage remain, the roadmap is clear: future research will likely dive into deep learning and neural networks to further refine these models.
“Technology like this will be indispensable in safeguarding our forests and the planet,” Zurqani emphasizes. As environmental crises accelerate, tools that bring speed, accuracy, and scale to forest monitoring could become our best defense—and greatest hope.
Source: Arkansas Agricultural Experiment Station
Enjoying our articles?
We don’t show ads — so you can focus entirely on the story, without pop-ups or distractions. We don’t do sponsored content either, because we want to stay objective and only write about what truly fascinates us. If you’d like to help us keep going — buy us a coffee. It’s a small gesture that means a lot. Click here – Thank You!
