Mapping Forest Types in China with 10 m Resolution Based on Spectral–Spatial–Temporal Features

Abstract

The comprehensive application of spectral, spatial, and temporal (SST) features derived from remote sensing images is a significant technique for classifying and mapping forest types. Facing limitations in the availability of detailed forest type identification processes for large regions, a forest type classification framework based on SST features was developed in this study. The advantages of Sentinel-2 and Landsat series imagery were used to extract SST forest type classification features, using red-edge bands, a gray-level co-occurrence matrix, and harmonic analysis, with the assistance of the Google Earth Engine platform. Considering four representative Chinese geographic regions—middle and high latitudes, complex mountainous areas, cloudy and rainy areas, and the N–S climate transition zone—our method was proven to be effective, with overall classification accuracies > 85%. The scheme to assess the importance of SST features for forest classification in various regions was designed using the Gini criterion in the random forest algorithm and revealed that spectral features were more effective in classifying forest types with complex compositions. Temporal features were found to be favorable for identifying forest types with obvious evergreen and deciduous growth patterns, while spatial features produced better classification results for forest types with different spatial structures, such as needle- or broad-leaved forests. The findings of this study can provide a reference for feature selection in remote sensing forest type classification processes, and identifying forest types in this way could provide support for the accurate and sustainable management of forest resources.

Relevance of Remote Sensing and its Applications in Forestry. A Critical Review

“…On the other hand, the nearly exponential rise that occurred between the years 2005-2010 and 2010-2015 can also be attributed to the growing quantity of airborne hyperspectral and LiDAR data, as demonstrated by the sensor-specific frequencies (rushed lines in Figure 4). Several studies (Dorren et al, 2003;Zhang et al, 2010;Zhu and Liu, 2014;Liu et al, 2018;Isuhuaylas et al, 2018;Pasquarella et al, 2018;Persson et al, 2018;Grabska et al, 2019;Cheng & Wang, 2019;and Cheng et al, 2021) Hościło and Lewandowska (2019) employed topographical information along with multitemporal Sentinel-2 data to provide an overview of their analysis of the broad mountain range of southern Poland. In this research, a map of forests and non-forests as well as the two types of forests (broadleaf and coniferous) were obtained using a random forest classifier algorism.…”

Annually Spatial Pattern Dynamics of Forest Types under a Rapid Expansion of Impervious Surfaces: A Case Study of Hangzhou City

“…On account of the comparatively finer spatial resolution with a long-time sequence, the Landsat series has become a popular data source for characterizing forest dynamics [12][13][14]. Furthermore, Google Earth Engine (GEE) is a powerful geo-big data computing platform that combines spatiotemporally spectral features for large-scale forest-type classification and produces a series of multi-scale maps [15][16][17]. Zhang et al [18] developed a Landsat-based global 30 m land-use map with a detailed classification system of forest types using the metric composite method on GEE and a multi-temporal random forest model, of which the overall accuracy is 82.5%.…”

Carbon storage through China’s planted forest expansion

“…However, currently available maps of China's planted forests have limitations in both spatial and temporal coverage 30,31 . These existing national maps and datasets were created through forest inventories or the digitization of forest inventory maps for specific years with coarse spatial resolutions 21,32 or only pertain to specific subtypes 23,33,34 , and are thus inadequate for tracking China's multi-decadal efforts in the planted forest area expansion 13,35,36 . Consequently, there is an urgent need to conduct high spatial resolution, national-scale research, and long-time-series assessments of C storage associated with the planted forest area expansion in China.…”