Forestry and Other Land Use

This page is about the intersection of forestry and machine learning in the context of climate change mitigation. For an overview of land use as a whole, please see the Wikipedia page on this topic.

A schematic of the ways that machine learning can support carbon negative agriculture, forestry, and land use.

Plants, microbes, and other organisms have been drawing CO2 from the atmosphere for millions of years. Most of this carbon is continually broken down and recirculated through the carbon cycle, and some is stored deep underground as coal and oil, but a large amount of carbon is sequestered in the biomass of trees, peat bogs, and soil. Our current economy encourages practices that are freeing much of this sequestered carbon through deforestation and unsustainable agriculture. On top of these effects, cattle and rice farming generate methane, a greenhouse gas far more potent than CO2 itself. Overall, land use by humans is estimated to be responsible for about a quarter of global GHG emissions(and this may be an underestimate). In addition to this direct release of carbon through human actions, the permafrost is now melting, peat bogs are drying, and forest fires are becoming more frequent as a consequence of climate change itself – all of which release yet more carbon.

The large scale of this problem allows for a similar scale of positive impact. According to one estimate, about a third of GHG emissions reductions could come from better land management and agriculture. ML can play an important role in some of these areas. Precision agriculture could reduce carbon release from the soil and improve crop yield, which in turn could reduce the need for deforestation. Satellite images make it possible to estimate the amount of carbon sequestered in a given area of land, as well as track GHG emissions from it. ML can help monitor the health of forests and peatlands, predict the risk of fire, and contribute to sustainable forestry. These areas represent highly impactful applications, in particular, of sophisticated computer vision tools, though care must be taken in some cases to avoid negative consequences via the Jevons paradox.

Background Readings

• Monitoring tropical forest carbon stocks and emissions using Planet satellite data
• Characterizing agricultural drought in the Karamoja subregion of Uganda with meteorological and satellite-based indices
• Remote Sensing Northern Lake Methane Ebullition

Community

Journals and conferences

• EARTHVISION is regularly held at computer vision conferences.
• Space and AI is organized by the ESA-CLAIRE AI Special Interest Group on Space.

Libraries and Tools

Some packages for working with remote sensing data are,

• eo-learn: A python package maintained by the European Space Agency, giving easy access to imagery from Sentinel satellites, as well as utilities for data processing
• robosat: A package mapbox.
• solaris: A package from CosmiQ Works (SpaceNet Challenge).

Data

Satellite imagery are often useful for monitoring land use. Some widely accessed resources include,

• Landsat
• Sentinel
• Earth Engine Data Catalog
• Methane detection from satellite

Forestry related data have also been the focus of machine learning competitions, including

• Planet: Understanding the Amazon from space
• IDTReeS: Integrating Data science with Trees and Remote Sensing