Data development

Scanning forests

Summary of Data Sources

At forestmap.ai, we rely on a range of advanced remote sensing technologies to provide comprehensive insights into tropical forests. We can recommend which data will best help to answer your questions. Here’s a summary of the primary data sources we use:

1. Satellite Imagery

  • Overview: Satellites provide large-scale, global coverage of forested areas with regular revisits.

  • Key Uses: Monitoring deforestation, forest cover changes, and carbon stocks over time.

  • Pros: Global coverage, frequent revisits, and long-term historical data.

  • Limitations: Lower spatial resolution and potential interference from cloud cover in tropical regions.

2. Unmanned Aerial Vehicles (UAVs)

  • Overview: UAVs, or drones, are used for high-resolution, localized data collection.

  • Key Use: Monitoring individual trees, detecting subtle changes in growth, mortality, and forest health.

  • Pros: High spatial resolution, detailed mapping at the tree or branch level, low cost.

  • Limitations: Limited to smaller areas and requires frequent flights for time-series data.

3. LiDAR (Light Detection and Ranging)

  • Overview: LiDAR uses laser pulses to generate 3D models of forest structure.

  • Key Uses: Estimating forest biomass, mapping canopy structure, and tracking changes in tree height and density.

  • Pros: Provides highly detailed, 3D structural data that can penetrate through canopies.

  • Limitations: Expensive and requires specialized equipment, limited temporal transferability.

4. Hyperspectral Imaging

  • Overview: Hyperspectral sensors capture data in hundreds of narrow spectral bands, allowing detailed analysis of vegetation properties.

  • Key Uses: Mapping tree species, detecting biodiversity patterns, and assessing vegetation health/traits.

  • Pros: Identifies species-specific traits, providing rich information about biodiversity.

  • Limitations: Expensive and requires large computational resources for processing.

5. Multispectral Imaging

  • Overview: Between hyperspectral and RGB imaging. Few broad spectral bands, often including visible, near-infrared, and shortwave infrared.

  • Key Uses: Assessing vegetation health, land use, and forest cover changes.

  • Pros: More affordable and easier to implement than hyperspectral imaging, useful for large-scale analysis.

  • Limitations: Less detailed than hyperspectral data.

6. Ground-Truth Data

  • Overview: Collected through field surveys and forest plot networks, providing on-the-ground measurements.

  • Key Use: Calibrating and validating remote sensing data to ensure accuracy.

  • Pros: Provides essential reference data to validate and refine remote sensing models.

  • Limitations: Time-consuming, labor-intensive, and limited in spatial scale.

Through our knowledge of how to expertly combine these data sources, forestmap.ai delivers precise, multi-scale insights into tropical forest dynamics, ensuring accurate monitoring of forest health, biodiversity, and carbon storage.

Always rooted in the latest science.

Read more in these peer reviewed articles:

  1. Morley, R. J. (2000). Origin and evolution of tropical rain forests. John Wiley & Sons.

  2. Dirzo, R., & Raven, P. H. (2003). Global state of biodiversity and loss. Annual Review of Environment and Resources, 28(1), 137-167.

  3. Saatchi, S. S., et al. (2011). Benchmark map of forest carbon stocks in tropical regions across three continents. Proceedings of the National Academy of Sciences, 108(24), 9899-9904.

  4. Pan, Y., et al. (2011). A large and persistent carbon sink in the world’s forests. Science, 333(6045), 988-993.

  5. Artaxo, P., et al. (2022). The effects of Amazon deforestation on atmospheric composition and climate. Nature Communications, 13, 204.

  6. Williams, M., et al. (2003). Climate change and the productivity of Amazonian forests. Nature, 426(6968), 234-237.

  7. IPCC (2022). Sixth Assessment Report: Climate Change 2022. Intergovernmental Panel on Climate Change.

  8. Mitchard, E. T. A. (2018). The tropical forest carbon cycle and climate change. Nature, 559, 527-534.

  9. Hubau, W., et al. (2020). Asynchronous carbon sink saturation in African and Amazonian tropical forests. Nature, 579(7797), 80-87.

  10. Baccini, A., et al. (2017). Tropical forests are a net carbon source based on aboveground measurements of gain and loss. Science, 358(6360), 230-234.

  11. Gatti, L. V., et al. (2021). Amazonia as a carbon source linked to deforestation and climate change. Nature, 595(7867), 388-393.

  12. Franca, F. M., et al. (2020). Climate change versus deforestation: risks to Amazonian biodiversity. Science Advances, 6(16), eaaz4794.

  13. Chave, J., et al. (2014). Improved allometric models to estimate the aboveground biomass of tropical trees. Global Change Biology, 20(10), 3177-3190.

  14. Brienen, R. J., et al. (2015). Long-term decline of the Amazon carbon sink. Nature, 519(7543), 344-348.

  15. Jenkins, C. N., et al. (2013). Global patterns of terrestrial vertebrate diversity and conservation. Proceedings of the National Academy of Sciences, 110(28), E2602-E2610.

  16. Hubbell, S. P. (2001). The unified neutral theory of biodiversity and biogeography. Princeton University Press.

  17. Ter Steege, H., et al. (2013). Hyperdominance in the Amazonian tree flora. Science, 342(6156), 1243092.

  18. Fauset, S., et al. (2015). Hyperdominance in Amazonian tree communities: the importance of regional and landscape scales. Journal of Ecology, 103(4), 973-981.

  19. Rohde, K. (1992). Latitudinal gradients in species diversity: the search for the primary cause. Oikos, 65(3), 514-527.

  20. Wright, S. J. (2006). The future of tropical forests. Annals of the New York Academy of Sciences, 1064(1), 1-2.

  21. Keenan, R. J. (2013). Forests and forest ecosystems: roles in the climate system. Environmental Science & Policy, 10(6), 549-563.

  22. Poorter, L., et al. (2016). Biomass resilience of Neotropical secondary forests. Nature, 530(7589), 211-214.

  23. Saleska, S. R., et al. (2016). Amazon forests maintain high photosynthetic capacity during the dry season. Nature, 531(7594), 221-224.

  24. Beer, C., et al. (2010). Terrestrial gross carbon dioxide uptake: global distribution and covariation with climate. Science, 329(5993), 834-838.

  25. Samanta, A., et al. (2010). Amazon forests did not green-up during the 2005 drought. Geophysical Research Letters, 37(5).

  26. Morton, D. C., et al. (2014). Amazon forests maintain consistent canopy structure and greenness during the dry season. Nature, 506(7487), 221-224.

  27. Zhu, X. X., et al. (2017). Deep learning in remote sensing: A comprehensive review and list of resources. IEEE Geoscience and Remote Sensing Magazine, 5(4), 8-36.

  28. Brodrick, P. G., et al. (2019). Deep learning for detection of selective logging from satellite images. Remote Sensing of Environment, 221, 569-582.

  29. Hansen, M. C., et al. (2013). High-resolution global maps of 21st-century forest cover change. Science, 342(6160), 850-853.

  30. Saatchi, S. S., et al. (2011). Benchmark map of forest carbon stocks in tropical regions across three continents. Proceedings of the National Academy of Sciences, 108(24), 9899-9904.

  31. Sun, Z., et al. (2021). UAV remote sensing for urban green infrastructure planning: A review. Urban Forestry & Urban Greening, 64, 127308.