Assessing Forest-Change-Induced Carbon Storage Dynamics by Integrating GF-1 Image and Localized Allometric Growth Equations in Jiangning District, Nanjing, Eastern China (2017–2020)

Abstract

Forest and its dynamics are of great significance for accurately estimating regional carbon sequestration, emissions and carbon sink capacity. In this work, an efficient framework that integrates remote sensing, deep learning and statistical modeling was proposed to extract forest change information and then derive forest carbon storage dynamics during the period 2017 to 2020 in Jiangning District, Nanjing, Eastern China. Firstly, the panchromatic band and multi-spectral bands of GF-1 images were fused by using four different methods; Secondly, an improved Mask-RCNN integrated with Swin Transformer was devised to extract forest distribution information in 2020. Finally, by using the substitution strategy of space for time in the 2017 Forest Management and Planning Inventory (FMPI) data, local carbon density allometric growth equations were fitted by coniferous forest and broad-leaved forest types and compared, and the optimal fitting was accordingly determined, followed by the measurements of forest-change-induced carbon storage dynamics. The results indicated that the improved Mask-RCNN synergizing with the Swin Transformer gained an overall accuracy of 93.9% when mapping the local forest types. The carbon storage of forest standing woods was calculated at 1,449,400 tons in 2020, increased by 14.59% relative to that of 2017. This analysis provides a technical reference for monitoring forest change and lays a data foundation for local agencies to formulate forest management policies in the process of achieving dual-carbon goals.

Real-Time Object Classification on an Enamel Paint Coating Conveyor Line Using Mask R-CNN

“…The FPN plays an important role in extracting features from an image that form part of the CNN backbone, as shown in Figure 1. The feature extractor performs the task of taking a single image of an unknown scale as the input image and outputs feature maps at multiple levels [31,32]. The low-level feature maps includes information such as edges, colour and textures while high-level feature maps includes information such as the object parts or the object itself.…”