Forests are vital for our planet. They help fight climate change by absorbing a lot of carbon dioxide from the air, acting as major carbon sinks. They store large amounts of carbon in biomass and soil, estimated to absorb about 30% of human-caused CO2 emissions annually worldwide.
However, scientists and project managers must track forest health. They need to know how much carbon forests store. This helps ensure that efforts to protect or grow forests are effective. This is called measuring, monitoring, reporting, and verifying forest carbon, often shortened to MMRV.
Recently, Meta has developed an AI-powered canopy height map that offers unprecedented detail in tracking forest health and carbon storage. This open-source tool helps project developers monitor changes, verify carbon credits, and boost climate action.
Eyes in the Sky: How Remote Sensing Sees Forests Differently
Measuring carbon in forests is tricky and expensive. Usually, people go out into the forest and measure trees by hand, which takes a lot of time and effort. It’s hard to do this over large areas, especially in dense or remote forests.
This is where remote sensing comes in.
Remote sensing is a way to gather information about forests without going there in person. It uses satellites, airplanes, or drones equipped with cameras and sensors. This technology can take pictures and collect data. It helps scientists learn how tall trees are, how dense the forest is, and how much carbon it might store.
There are different kinds of remote sensing data:
- Optical imagery: like normal photos taken from space or planes, showing the tops of trees and land features.
- Radar: which uses radio waves and can see through clouds and work at night.
- Lidar: which uses lasers to map the exact height and shape of trees in 3D.
The Challenge with Remote Sensing Data
Each data type has strengths and weaknesses. Optical images are good and widely available, but they can’t see through clouds and only show forest surfaces. Radar can see through clouds but has trouble measuring details in dense forests. Lidar is very accurate but expensive and covers less area.
To get the best info, scientists combine different types of data using artificial intelligence (AI) and machine learning techniques. Machine learning helps computers find patterns in huge amounts of data to make better estimates.
Meta’s Canopy Height Map: AI-Powered Forest Intelligence
Meta developed a unique AI model that merges high-resolution satellite images with lidar data. This model maps tree canopy heights globally with great detail—less than one meter per pixel. This means it can see individual trees in many places.
The map and the AI model are open-source and freely available, so anyone can use them to help forest projects. They enable better planning, monitoring, and verification of forest carbon projects. Reza Rastegar, Senior Manager of Research Science at Meta, stated:
“When applied thoughtfully, we believe AI research and remote-sensing tools, particularly those that are open source, have the potential to revolutionize the transparency and accessibility of the carbon market.”
Meta’s model has been validated with mean absolute errors of 2.8 meters in U.S. forests and 5.1 meters in Brazil. This reflects a promising improvement in estimating canopy height at fine scales. These advanced datasets and models are helping to track natural regeneration, selective logging, and forest degradation more accurately, which is vital for credible MMRV of carbon credits.
What’s special about this model?
- It works globally with very fine detail.
- It can help identify important areas to protect or restore.
- It can make new maps for different times if good images are available.
- It helps detect small changes in forests, like selective logging (cutting some trees but not all).
- It supports methods from carbon credit standards. This is important for those who need dynamic baselining or updating project baselines with real data from nature.
RELATED: Meta and Microsoft Secured Long-Term Carbon Credit Deals to Support Olympic Rainforest
From Pixels to Carbon Credits: Turning Data into Climate Action
Forest carbon projects use different official methods to create and verify forest carbon credits. The three main methods Meta focuses on are:
- Verra VM0045 – for improved forest management (IFM).
- Verra VM0047 – for afforestation, reforestation, and revegetation (ARR).
- American Carbon Registry (ACR) IFM – a US-based improved forest management method.
Here’s how Meta’s canopy height map and AI model fit into these methods:
- In project planning, the map helps find good parcels of forest to include, determine project boundaries, and understand forest structure.
- For dynamic baselining, especially in ARR and ACR’s IFM methods, the AI model can help update baselines based on real forest growth or loss over time.
- For reversals monitoring (tracking if carbon gains are lost, e.g., due to fire or logging), the map gives better details to detect forest disturbances.
The Fine Print: What Meta’s Model Gets Right—and Where It Struggles
Many traditional satellite products can’t reliably measure forest height or biomass in dense forests or small areas. Meta’s model, because it uses very high-resolution images, helps overcome this.
Monitoring small or fragmented forests, river corridors, or areas with selective logging is crucial. These places are difficult to track using low-resolution data.
Meta’s canopy height model is a powerful tool for estimating forest structure, but it comes with limitations. It works best with high-quality imagery at 0.5–1 meter resolution. The global canopy height map uses images from 2009 to 2020. This means it might not show current forest conditions. So, there’s a need for updated maps.
Accuracy may also drop in underrepresented forest types, so local validation with field or lidar data is advised. Using the model requires significant computing power and technical expertise, which may limit adoption.
For forest carbon projects, remote sensing offers great promise but faces barriers. There is no universal agreement among registries, buyers, and developers on acceptable methods or datasets.
In addition, technical skills, computational capacity, and access to affordable, high-quality datasets remain limited. Uncertainty around accuracy—and lack of consensus on acceptable error levels—make trust and comparability difficult.
For the identified barriers, the report authors recommend the following:
Closing the Gap Between Innovation and Impact
Experts want clearer standards for how datasets can be used. They also seek better reporting on uncertainty and clearer rules for issuing carbon credits. A global benchmarking database with verified data and a central portal for quality datasets could help boost adoption.
Moreover, easier AI tools would make this process smoother. Integrating advanced models like Meta’s into accessible platforms, alongside collaborative standard-setting, will be crucial to scaling reliable forest carbon monitoring and verification.
Examples of New and Exciting Uses of Meta’s Model
- Counting trees in agroforestry projects to monitor performance.
- Mapping old-growth forests and biodiversity hotspots.
- Detecting subtle forest degradation, like selective logging.
- Monitoring reversals (losses of carbon stored) with greater accuracy.
- Supporting more accurate estimates of above-ground biomass.
Forests are vital to fighting climate change by storing carbon, but measuring how much carbon they hold and how this changes over time is tough. New technologies like remote sensing are making this easier, faster, and cheaper.
Meta’s AI-powered canopy height map is a cutting-edge tool offering very detailed, global forest height data that can help in planning, monitoring, and verifying forest carbon projects.
The post Meta’s AI Forest Map: The Game-Changer for Carbon Tracking appeared first on Carbon Credits.
The accounting differences that decide whether your nature investment shows up in inventory, in BVCM, or nowhere at all.
The question reaches a procurement team about three weeks before the next sustainability committee meeting. Someone has read about insetting. Someone else has just signed off on an offset purchase. The CSO wants to know if the two are interchangeable. The answer is no, and the GHG Protocol Land Sector and Removals Standard is the reason why.
This article walks through what each term means at audit-grade specificity, what the standards actually say about how each gets counted, and how to decide which tool fits which target. The insetting vs offsetting question is one of the most-searched in corporate climate strategy, and one of the most poorly answered. By the end of this piece, you should be able to brief a committee on the difference without notes.
The two definitions, in plain English
Offsetting means buying carbon credits generated outside your value chain and retiring them against your residual emissions. The reduction happens somewhere else, financed by you, and the credit is the receipt.
Insetting means investing in emission reductions or removals inside your own value chain, typically with suppliers, where the reduction is directly linked to the products and services you buy. The reduction happens inside the boundary of your Scope 3 inventory, and the accounting treatment is fundamentally different.
The shorthand from the University of Oxford’s Nature-based Insetting Initiative is useful: insetting is what you do with the supply chain you have; offsetting is what you do with the supply chain you do not have.
What the GHG Protocol Land Sector Standard actually says
The GHG Protocol Land Sector and Removals Standard, finalised in 2024 after a multi-year pilot, sets the rules for how land-based emission reductions and removals enter corporate inventories. The Standard distinguishes between inventory accounting (Scope 1, 2, and 3) and project or intervention accounting (a separate methodology for crediting).
For insetting, the practical implication is that supplier-level interventions, when properly measured and attributed, can reduce your Scope 3 category 1 (purchased goods and services) emissions in your inventory. The reduction is not a credit retired against the inventory; it is a lower inventory number, period.
For offsetting, the credit is retired separately. It can be reported as a contribution toward a net-zero claim under the SBTi Beyond Value Chain Mitigation framework or as part of a VCMI Carbon Integrity claim, but it does not lower the inventory number.
A practical consequence: if your Science Based Target requires a 50% absolute reduction in Scope 3 emissions by 2030, insetting moves you toward the target. Offsetting does not. This single point of difference reshapes the procurement decision.
When insetting counts toward Scope 3 (and when it does not)
Insetting counts toward Scope 3 only when several conditions are met:
- The intervention must occur with an entity in your value chain.
- The emissions reduction or removal must be measured against a defensible baseline.
- The reduction must be attributed to your share of that supplier’s output, not double-counted with other buyers.
- It must follow the inventory accounting rules in the GHG Protocol Land Sector Standard, not the project accounting rules used to generate credits.
The most common failure mode is double counting. If your supplier sells the same reduction as a credit on the voluntary market and also reports it to you as a Scope 3 reduction, the math breaks. The Standard requires you to address this risk, typically by purchasing and retiring the supplier-issued credit as part of your inventory or by contractual provisions that prevent the supplier from selling the reduction twice.
When insetting does not count toward Scope 3: when the intervention sits with a supplier you do not buy from, when the baseline is not defensible, when the attribution is unclear, or when the documentation does not survive audit. Those cases default to Beyond Value Chain Mitigation, which is still useful but operates on a different ledger.
The procurement and supplier engagement question
Insetting is harder than offsetting. That is the unfashionable truth most buyers eventually confront. Offsetting is a transaction; insetting is a relationship.
To run an insetting program, you need supplier mapping precise enough to know which farms or facilities sit at which Scope 3 boundary. You need an engagement model that gets suppliers to participate, which usually requires multi-year commitments and shared economics. You need an MRV architecture that measures the right things and produces audit-ready documentation. And you need a contractual structure that prevents double counting and protects both sides.
The trade-off you receive in return is significant. Reductions count against your inventory rather than your residual. Supplier relationships deepen, which protects sourcing continuity. Yield and quality improvements often follow regenerative interventions, which reduces your input cost over time. And the regulatory file, under CSRD, CSDDD, EUDR, and the SBTi FLAG Guidance, is materially stronger.
Choosing the right tool for the right target
A practical decision rule. If your target is a science-based Scope 3 reduction and you operate in a FLAG sector or source FLAG commodities, insetting is the structurally correct tool. If your target is a net-zero claim that includes neutralising hard-to-abate residual emissions outside your value chain, BVCM via high-integrity offsets is the structurally correct tool. Most companies with material Scope 3 exposure need both, in different proportions, sequenced over time.
The sequencing matters. Insetting takes longer to stand up but produces a permanent reduction in the inventory. Offsetting can be transacted faster but does not change the inventory and now sits under tighter claim restrictions. Treat them as complementary tools with different jobs, not as substitutes. The Accountability Framework Initiative and the IUCN Global Standard for Nature-based Solutions both provide useful guardrails for the insetting side, with biodiversity, human rights, and benefit-sharing requirements that go beyond carbon math.
If you are mapping a Scope 3 reduction roadmap and need to scope which interventions count toward your inventory versus which sit in Beyond Value Chain Mitigation, the carbon and sustainability experts at Carbon Credit Capital can help you structure a nature-based supply chain investment program that fits your FLAG exposure, your target architecture, and your audit horizon. Schedule a consultation.
Net zero is often described as a balancing act: cut what you can, account for the rest, and reach zero on the ledger. That framing is useful, but it leaves something out. It treats every tonne of carbon as interchangeable and every route to zero as equally sound, while the science tells a more specific story.
Malawi has lost a striking share of its forests over the past three decades. Woodlands that once covered well over a third of the country now cover less than a quarter, and the pressure on what remains is increasing. Behind those figures sit two practical questions: what is driving the loss, and what reverses it?
-
Climate Change1 year ago
Guest post: Why China is still building new coal – and when it might stop
-
Greenhouse Gases1 year ago
Guest post: Why China is still building new coal – and when it might stop
-
Greenhouse Gases2 years ago嘉宾来稿：满足中国增长的用电需求 光伏加储能“比新建煤电更实惠”
-
Climate Change2 years ago嘉宾来稿：满足中国增长的用电需求 光伏加储能“比新建煤电更实惠”
-
Climate Change2 years ago
Bill Discounting Climate Change in Florida’s Energy Policy Awaits DeSantis’ Approval
-
Renewable Energy10 months agoSending Progressive Philanthropist George Soros to Prison?
-
Greenhouse Gases1 year ago
嘉宾来稿：探究火山喷发如何影响气候预测
-
Carbon Footprint2 years agoUS SEC’s Climate Disclosure Rules Spur Renewed Interest in Carbon Credits