Monitoring
Supporting sustainable change in ways never seen before, from down-to-earth to sky-high.
Find out moreWhy remote sensing helps
Remote sensing isn't just a unique and technologically advanced part of our operations, it's what makes our mission possible in the first place. We're committed to delivering CRUs that are reliable, objective, and truthful. Reliable, as remote sensing allows us to trace every CRU back to its plot of origin. Objective, through the use of advanced machine learning models. And truthful, as they reflect already captured CO2 rather than a promise for the future. Through technology, we can issue true evidence-based CRUs that give back to the environment as well as to local communities.
First up: a deforestation check
Our mission is to help smallholder farmers as well as the environment. So we want to make sure that the work we do does not inadvertently result in deforestation. That's why we ensure that for any area eligible for participation, no deforestation has taken place five years prior to entering the program. This ensures that farmers do not clear their forest land just in order to take advantage of the program.
How it's done
Using open-source datasets, such as Global Forest Watch, we check if the plot was classified as forest prior to entering the program. If so, we verify if the existing trees five years ago are still present. Fortunately, that is usually the case. This also means that our CRUs are always based on new, additional trees, not on trees that were cut down just to be replanted.
Boots on the ground
We work closely with project coordinators who are actively involved in and experienced with the region. That's how we can gather a wealth of field data simply from local partners and observers visiting Acorn-associated farms. This includes measuring individual tree characteristics such as tree height and width, as well as making an inventory of the type of tree species and their age. This data, which we refer to as "ground truth", is converted to the biomass it suggests.
Measurements to models
Combined with satellite data, this information is used to train and validate our machine learning models for biomass estimation. These models are the key to the scalability of Acorn, and it's the ground truth data that informs the models in the first place.
Overview from afar: remote sensing
To monitor the growth and continuing existence of biomass, we use remote sensing. Remote sensing is a technique which refers to scanning of the earth's surface from a distance and obtaining information about it using sensors. These sensors are mounted on airplanes or satellites and work by capturing the light which is reflected or emitted by the earth. We're interested in forests and vegetation, so we use sensors specifically designed for monitoring these areas.
Using state-of-the-art technology and advances in data science, we are able to guarantee transparency and reproducibility of all our methods. If that sounds a little vague or too complex, we'll explain just what remote sensing entails when it comes to Acorn. First up: LiDAR.
A view from on high: LiDAR
LiDAR (an acronym for Light Detection and Ranging) is a sensor which creates a 3D representation of the object it measures. Placed on an airplane and flown over the agroforestry plots of interest, it creates a digital twin of these locations.
The added value
LiDAR helps us validate and enrich the data collected by the field officers. LiDAR helps us calibrate our models by 3D mapping agroforestry plots, allows us to get a better understanding of the ecological region, and enriches the ground truth data already gathered.
Next level: satellite imagery
The final piece of Acorn's high-tech approach is satellite data. The main source of data comes from the two Sentinel-2a and b satellites operated by the European Space Agency. Fused with other satellite data sources, for example satellite-borne LiDAR (GEDI) or radar data (Sentinel-1), gives us the unique opportunity to estimate biomass accurately and efficiently in a variety of locations around the world.
Good models matter
That data is added to the ground truth data and used to train machine learning models. These models are then independently validated. All this effort ensures that our models are able to make our process efficient, reliable, and scalable, while maintaining consistently high accuracy. So our geo-data models grow as Acorn does.
A treasure trove of geo-data
The key to our proposition is geo-data. Without it, we can't issue reliable carbon credits or encourage appropriate agroforestry strategies. Naturally, geo-data can be gathered in a multitude of ways. At Acorn, we have decided to focus on the most technologically advanced methods.
Bringing it together
That's why we work together with remote sensing partners (like Satelligence and Space 4 Good) to give us the biomass measurements for the plots in the Acorn program. The models are trained with the ground truth, LiDAR and Sentinel data of certain plots and then scaled. Based on our certified methodology, we establish the baseline biomass and next year's delta (or growth). We only measure above-ground biomass and use a root-shoot calculation for the below-ground biomass, with soil carbon not being part of the Acorn approach.
Crystal-clear carbon credits
The baseline is corrected for pre-existing trees on the land, and the delta of biomass is corrected using several correction factors (such as leakage, pre-project trees and uncertainty). After all that, the CO2 sequestration is calculated, finally enabling us to issue carbon removal credits. Credits that are based on technology: that are always trustworthy, transparent, and validated.
Subscribe to our newsletter
Stay updated on our Acorn activities and the latest carbon news