Month: April 2023

By: Jamie Tolan, Camille Couprie, and Tracy Johns

The increase in atmospheric carbon dioxide levels and associated climate change has had a dramatic impact on the Earth’s biosphere, ranging from drought and wildfires to the loss of biodiversity. Forests play a central role in the carbon dioxide cycle, pulling carbon dioxide from the atmosphere and storing the carbon in their biomass. Forests also contain the majority of Earth’s terrestrial biodiversity. Despite this central role, the magnitude of the carbon dioxide absorbed every year by forests around the world is still largely unclear, due in part to the coarse resolution of global carbon models.

The United Nations Intergovernmental Panel on Climate Change (IPCC) has clarified that carbon removal is a crucial part of limiting global warming to levels of 1.5º C in comparison with pre-industrial temperatures. Forest management is recognized by the IPCC as one of the most important ways to achieve carbon removal at scale, and over the past decade, forest management has become the main source of carbon offsets in the voluntary market.

In 2020, Meta set a goal to reach net zero emissions across our value chain in 2030. As part of this, we are developing new technology solutions to mitigate our own carbon footprint and making these openly available to enable a broader impact on climate change (for example, read more on how we use AI to reduce concrete’s carbon footprint). In this article, we describe how we leveraged internal state-of-the-art AI technology and collaborated with the World Resources Institute (WRI) to develop a method to map forests, tree by tree, across areas the size of continents. As an example, we mapped the U.S. state of California and São Paulo, Brazil, and are making the data public and freely available.

How improved mapping helps achieve net zero

To achieve net zero emissions, Meta is focused on reducing our emissions by prioritizing efficiency and circularity in our business decisions, embracing low-carbon technology, and engaging with our suppliers to help them set climate targets. Some emissions from hard-to-abate sectors will remain difficult to completely eliminate by the end of this decade. For those emissions we cannot avoid, we will remove an equivalent amount of carbon dioxide by purchasing credits from carbon removal projects, including nature-based solutions that can be deployed now, as well as emerging technologies that need our support to scale. Forests are critical to achieving the global scale of carbon removal needed as outlined by the IPCC, and the market for high-quality, forest-based carbon removal needs to grow significantly to achieve this scale.

We believe that by improving measurement, reporting, and verification (MRV) of forest-based carbon removal projects, we can improve the quality and accelerate the growth of nature-based climate solutions. First, by lowering the barrier to forest monitoring solutions, we can enable small landowners to access carbon markets and increase the number of community-led carbon removal projects. Smaller, distributed tree growth (e.g., in agroforestry) lacks affordable and scalable monitoring solutions, which can hamper the development of such projects in smaller communities. Second, nature-based solutions can use more reliable data of the carbon stock in forests for both the baselining and the monitoring of forest carbon. Improved, freely available high-resolution data could potentially be used in standardized verification methodologies for certain projects. Both of these challenges can be addressed by improving fine-grained knowledge of forests at a global scale and making the data publicly available.

Description of our method

In order to make our mapping methodology useful for MRV of carbon projects, we set the following criteria: detect single trees (as small trees as possible) and be globally applicable. We also require that the method be applicable to different sources of imagery to allow for frequent updates of the canopy height maps.

Leveraging recent advances in self-supervised learning, namely the DINOv2 model we announced today, and our expertise in AI-based global mapping from high-resolution imagery, we have developed a machine learning approach that can detect canopy height with high fidelity from RGB imagery with a resolution of 0.5 m. We describe our model in detail in the preprint (link), which has been submitted for peer review. DINOv2 provides a self-supervised framework that’s trainable on any collection of licensed photos without needing any associated metadata. In this work, a DINOv2 model is trained on high-resolution (0.5 m) RGB satellite imagery from MAXAR Technologies in a self-supervised fashion. We then use aerial LIDAR data as a ground truth to learn canopy height maps (CHM). Since our ground truth is in North America and high-quality aerial LIDAR imagery is not globally available, we use spaceborne LIDAR data as a low-resolution and sparse but global data source to calibrate our model for global applicability.

Choosing the DINOv2’s self-supervised neural network learning allows for universal and generalizable features, which we believe facilitates global applicability of the model. The 0.5 m resolution allows us to map the canopy height of individual trees regardless of sparsity, undergrowth type, or species, which is crucial in achieving accurate biomass estimates. Leveraging our model, we create canopy height maps of California and São Paulo, Brazil (download the data here and view map here). We find that the model performs qualitatively well in Brazil, even though the high-resolution training data was from North America.

Since the model is trained on RGB imagery, it allows the analysis of generic RGB imagery resampled to the same 0.5 m resolution that the model has been trained on, so imagery collected by planes or drones, rather than by satellites, can also be used as input. This is particularly important since aerial RGB data is more widely available and allows for simple, cost-effective tracking of changes in canopy height over time.

As an example, we demonstrate that our model performs well on the aerial imagery of the NEON dataset, as shown in the figure above.

Conclusion

Our method enables large-scale analysis of high-resolution imagery, determining forest canopy height with sub-meter resolution. Accurate forest mapping in space and time will lead to more accountable forest-based carbon offsets and enable the development of more carbon projects, especially those on smaller pieces of land — two requirements for nature-based carbon offsets to achieve the scale and quality needed to meet net zero goals at a global scale.

Hey, hey, look! It’s here, it’s here! It’s been a long year-and-a-half, but we finally have the latest levelized cost of energy report from Lazard. I realize you may not be as excited about this as I am, but it’s one of my favorite nerdy climate reports, right up there with those from the Intergovernmental Panel on Climate Change. Click your brain into gear, because we are diving headfirst into the weeds.

Levelized Cost of Energy Explained

Here is Lazard’s webpage for the report and a direct link to the PDF. You’ll want to open up the PDF in a new tab and be ready to do some clicking back and forth. But first, let me explain what in the heck Lazard is doing when they publish these reports.

The levelized cost of energy (LCOE) refers to the average net present cost of producing energy in different ways. It can be expressed either as an average number or as a range of costs. In other words, when you see the LCOE of, for instance, offshore wind turbines, you are seeing what it generally costs to add that form of electricity generation to the grid. Because those costs are normalized per unit of energy, an LCOE report that looks at different forms of energy generation can tell you the relative costs of each form. Not surprisingly, LCOE analyses can range widely in different regions of the world, but Lazard’s 2023 report focuses specifically on LCOE in the United States.

The Cheapest Form of Energy, and Other Takeaways

Okay, let’s look first at page 5 of the report (numbered page 2 in the bottom right). This is the “main course” of the LCOE report, and it tells us the range of unsubsidized costs by generation type. Various forms of renewable energy are at the top, compared to the four types of nonrenewable energy at the bottom. When you see a dark blue bar, that’s a range of costs based on robust observable data. The gray bars for geothermal, nuclear, and coal are estimated ranges of costs, because we do not have sufficient new installations of these forms of energy generation to base their LCOE on recent data.

Here are my takeaways from this chart:

Onshore wind! It’s the winner here, with average costs that are clearly lower than combined cycle natural gas.Utility scale-solar is roughly cost competitive with natural gas, averaging a bit cheaper on its own and a bit pricier when you factor in storage.Rooftop solar is expensive, but it’s the orange compared to all of the other apples here. Most rooftop solar that is being installed is by homeowners, whereas the other forms of electricity are being installed by large businesses. If I want to generate electricity at my home, I can’t build a wind farm or a natural gas plant, so it’s not terribly relevant that rooftop solar costs more. And for many people, rooftop solar still pencils out with a positive return on investment at current prices.Do you see those three yellow diamonds on the lines for nuclear, coal, and natural gas? Those show the average cost of operating those forms of energy generation, as opposed to building new ones. Between wind and utility-scale solar, it’s fair to say that in some cases, it’s cheaper to build new renewable energy than to operate existing nonrenewable power plants.Admittedly, the cheapest renewables have the challenge of intermittency (because the wind doesn’t always blow and the sun doesn’t always shine). That emphasizes the importance of grid-scale storage technologies, because we will need robust energy storage to displace the forms of energy that provide baseload electricity. These charts show that renewables are now winning on cost, and we just need them to win on performance to make fossil fuel electricity fully obsolete.

A Layer Deeper in the LCOE Report

Okay, let’s go to the next chart (PDF page 6, numbered page 3 in the bottom right). That first chart showed unsubsidized costs, but we know that federal policies like the Inflation Reduction Act are providing “carrots” for the transition to a low-carbon economy. If you look at this chart, you see that federal tax subsidies make already-cheap renewables that much cheaper. The shift for rooftop solar is particularly large, and it further justifies my point above that the math for rooftop solar works for many individual homeowners.

Next, take a peak at PDF page 13, numbered page 10 in the bottom right. This shows the historical decline in the LCOE of wind and solar. It really is remarkable how much cost decline we have seen in a little more than a decade. Also, this report is the first time that Lazard has seen an increase in the LCOE of wind and solar. The high inflation of the last couple of years has definitely impacted these markets, but it’s also impacted other forms of electricity generation as well. Adjusted for inflation, I would expect wind and solar to continue seeing small, marginal declines in LCOE for the next several years.

Finally, take a look at PDF pages 15 and 16 (numbered 12 and 13 in the bottom right). These slides show the component parts of the LCOE for each generation type, with the first slide looking at the low end of costs and the second slide looking at the high end. What’s remarkable to me is just how significant the fuel costs are for nonrenewable sources of electricity. So let this be your friendly reminder that the sun and wind don’t charge us a cent for the energy they provide.

There’s a ton more to see in this LCOE report if you are so inclined. In particular, Lazard offers in-depth cost analysis of both energy storage technologies and hydrogen production technologies. Happy reading, and I’ll be sure to revisit Lazard’s LCOE reports in future years.