查看更多>>摘要：By a News Reporter-Staff News Editor at Robotics & Machine Learning Daily News Daily News – New research on Machine Learning is th e subject of a report. According to news reporting from Moscow, Russia, by NewsR x journalists, research stated, “Remote sensing of forests is a powerful tool fo r monitoring the biodiversity of ecosystems, maintaining general planning, and a ccounting for resources. Various sensors bring together heterogeneous data, and advanced machine learning methods enable their automatic handling in wide territ ories.” The news correspondents obtained a quote from the research from the Skolkovo Ins titute of Science and Technology, “Key forest properties usually under considera tion in environmental studies include dominant species, tree age, height, basal area and timber stock. Being proxies of stand productivity, they can be utilized for forest carbon stock estimation to analyze forests’ status and proper climat e change mitigation measures on a global scale. In this study, we aim to develop an effective machine learning-based pipeline for automatic carbon stock estimat ion using solely freely available and regularly updated satellite observations. We employed multispectral Sentinel-2 remote sensing data to predict forest struc ture characteristics and produce their detailed spatial maps. Using the Extreme Gradient Boosting (XGBoost) algorithm in classification and regression settings and management-level inventory data as reference measurements, we achieved quali ty of predictions of species equal to 0.75 according to the F1-score, and for st and age, height, and basal area, we achieved an accuracy of 0.75, 0.58 and 0.56, respectively, according to the R. We focused on the growing stock volume as the main proxy to estimate forest carbon stocks on the example of the stem pool. We explored two approaches: a direct approach and a hierarchical approach. The dir ect approach leverages the remote sensing data to create the target maps, and th e hierarchical approach calculates the target forest properties using predicted inventory characteristics and conversion equations. We estimated stem carbon sto ck based on the same approach: from Earth observation imagery directly and using biomass and conversion factors developed for the northern regions. Thus, our st udy proposes an end-to-end solution for carbon stock estimations based on the co mplexation of inventory data at the forest stand level, Earth observation imager y, machine learning predictions and conversion equations for the region.”
NETL
NSTL