consistent maps for directing additional carbon storage under current and future climate, as well as a framework for determining how that storage could be gained through restoration, improved management, or maintenance of woody biomass and soil organic matter. Our estimates provide an upper bound on how improved land stewardship can mitigate the climate crisis.
The dataset was constructed by combining the most reliable publicly available datasets and overlying them with the ESA CCI landcover map for the year 2010 [ESA, 2017], assigning to each grid cell the corresponding above-ground biomass value from the biomass map that was most appropriate for the grid cell’s landcover type.
"In this paper, we present ReforesTree, a benchmark dataset of forest carbon stock in six agro-forestry carbon offsetting sites in Ecuador. Furthermore, we show that a deep learning-based end-to-end model using individual tree detection from low cost RGB-only drone imagery is accurately estimating forest carbon stock within official carbon offsetting certification standards. Additionally, our baseline CNN model outperforms state-of-the-art satellite-based forest biomass and carbon stock estimates for this type of small-scale, tropical agro-forestry sites."
Main author is the founder of Tanso.io: Carbon Accounting and Management for Industrial Companies