• Corpus ID: 236318278

Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery

@article{Reiersen2021TacklingTO,
  title={Tackling the Overestimation of Forest Carbon with Deep Learning and Aerial Imagery},
  author={Gyri Reiersen and David Dao and Bj{\"o}rn L{\"u}tjens and Konstantin Klemmer and Xiaoxiang Zhu and Ce Zhang},
  journal={ArXiv},
  year={2021},
  volume={abs/2107.11320}
}
Forest carbon offsets are increasingly popular and can play a significant role in financing climate mitigation, forest conservation, and reforestation. Measuring how much carbon is stored in forests is, however, still largely done via expensive, timeconsuming, and sometimes unaccountable field measurements. To overcome these limitations, many verification bodies are leveraging machine learning (ML) algorithms to estimate forest carbon from satellite or aerial imagery. Aerial imagery allows for… 
1 Citations

Figures and Tables from this paper

Application of a Panel Data Quantile-Regression Model to the Dynamics of Carbon Sequestration in Pinus kesiya var. langbianensis Natural Forests

Even though studies on forest carbon storage are relatively mature, dynamic changes in carbon sequestration have been insufficiently researched. Therefore, we used panel data from 81 Pinus kesiya

References

SHOWING 1-10 OF 27 REFERENCES

Machine Learning-based Estimation of Forest Carbon Stocks to increase Transparency of Forest Preservation Efforts

An increasing amount of companies and cities plan to become CO2-neutral, which requires them to invest in renewable energies and carbon emission offsetting solutions. One of the cheapest carbon

Individual Tree-Crown Detection in RGB Imagery Using Semi-Supervised Deep Learning Neural Networks

This semi-supervised deep learning approach demonstrates that remote sensing can overcome a lack of labeled training data by generating noisy data for initial training using unsupervised methods and retraining the resulting models with high quality labeled data.

Estimating Mangrove Tree Biomass and Carbon Content: A Comparison of Forest Inventory Techniques and Drone Imagery

Mangroves provide many ecosystem services including a considerable capacity to sequester and store large amounts of carbon, both in the sediment and in the above-ground biomass. Assessment of

Benchmark map of forest carbon stocks in tropical regions across three continents

A “benchmark” map of biomass carbon stocks over 2.5 billion ha of forests on three continents, encompassing all tropical forests, for the early 2000s is presented, which will be invaluable for REDD assessments at both project and national scales.

Mapping forest tree species in high resolution UAV-based RGB-imagery by means of convolutional neural networks

Accurate estimation of forest carbon stocks by 3-D remote sensing of individual trees.

A methodology for estimating carbon stocks of a Japanese cedar forest by using a high-resolution, helicopter-borne 3-dimensional scanning lidar system that measures the 3-D canopy structure of every tree in a forest to accurately estimate carbon stocks at a stand scale is presented.

High-Resolution Global Maps of 21st-Century Forest Cover Change

Intensive forestry practiced within subtropical forests resulted in the highest rates of forest change globally, and boreal forest loss due largely to fire and forestry was second to that in the tropics in absolute and proportional terms.

Using ICESat-2 to Estimate and Map Forest Aboveground Biomass: A First Example

An initial look at the ability of ICESat-2 to estimate forest aboveground biomass (AGB) and suggest the possibility for applying well-developed methods for modeling AGB with airborne light detection and ranging (lidar) data, using processed ICES at-2 data.

Estimating above ground biomass in a Salix plantation using high resolution UAV images

In forest biomass estimations, three dimensional (3D) canopy structure data derived from images captured by unmanned aerial vehicles (UAVs), also known as drones, has shown potential due to the

Satellites could soon map every tree on Earth.

The field of terrestrial remote sensing is placed on the threshold of a mental leap forward: from focusing on aggre­ gate landscape­scale measurements to having the potential to map the location and canopy size of every tree over large regional or global scales.