A carbon credit is issued by analyzing the difference between the actual result and the counterfactual baseline, assuming a scenario where the project is not implemented. With regard to forest carbon credits, the concept of dynamic (or ex-post) baseline has been discussed to overcome the criticism of junk carbon credit, while an ex-ante baseline is still necessary in terms of project finance and risk assessment. We have developed a Bayesian state-space SCM (Synthetic Control Method), which integrates both ex-ante and ex-post baseline estimation in a time-series causal inference framework. Our approach has been accepted by NeurIPS 2022 Climate Change AI workshop and selected as the best paper that is most likely to have a meaningful impact. Our own algorithm will play an important role for potential credit buyers during their early financing process to support nature-based carbon projects, and help them evaluate delivery risk in anticipation of PCU (Projected Carbon Unit).
Forest Parameter Estimation
We use multiple space-borne observations, such as optical and radar satellite imageries, and satellite LiDAR with field observations. The data fusion of information collected thanks to such techniques makes it possible to accurately estimate forest parameters and quantify these uncertainties. Our state-of-the-art Bayesian-based technique for the data fusion of multiple earth observation data allows us to have a more accurate DTM (digital terrain model), which is critical for the forest biomass estimation of ARR projects. Our R&D activity includes active engagement in the anticipation of upcoming satellite missions, as shown by our participation in the early engagement program of NASA’s NISAR (next generation L-band radar satellite mission, which is expected to increase accuracy for space-borne vegetation monitoring) and HISUI (hyperspectral satellite mission).
We will actively contribute to the development of natural capital and biodiversity assessment methods. These include proprietary satellite imagery analysis and causal inference-based reference condition estimation technology. Our technology, designed in this context, could also be used for ALM (Agricultural Land Management) project development for companies in the agricultural commodity-related sector. We have partnered with NIES (National Institute for Environmental Studies) and Hitotsubashi University, which are two of the leading institutions that focus on biodiversity, forest, and social studies in Japan (see this partnership here) to collaborate on the creation of high-quality forest carbon credits. We were also selected as active members of the TNFD Data Catalyst Initiative (for more information, refer to the participants list here). ※ TNFD, known as the Taskforce on Nature-Related Financial Disclosures, is an international initiative to provide a framework for how organizations can address environmental risks and opportunities with the ultimate goal of channeling capital flows into positive action.
National Institute for
CareersThe following positions are
CTO (Chief Technical Officer) Candidate/ Senior Software Engineer
Data scientist / Applied scientist
Business Development Manager