Use of Vegetation Change Tracker, Spatial Analysis, and Random Forest Regression to Assess the Evolution of Plantation Stand Age in Southeast China

It is crucial to determine the spatio-temporal distribution patterns of forest ages across wide regions, as forest management plans and practices, and ecosystem carbon budgeting are highly dependent on these. However, given frequent deforestation events (e.g., harvesting) and rapid recovery of plantation stands in Southern China, field-based forest age measurements over wide regions are time-consuming, labour-intensive, and costly. In the current study, we mapped the spatio-temporal patterns of forest stand ages across three typical plantations in Southern China. This was accomplished by using two new feasible and accurate methods, 1) integrating vegetation change tracker (VCT) algorithm and spatial analysis (VCT-SA) for the pixels that were disturbed at least once from 1987 to 2017, and 2) integrating VCT and random forest (VCT-RF) for the pixels were not disturbed during the study period. The results revealed the spatio-temporal distribution of age structure, which indicated that the plantation stands in our large study area were increasingly aging.精准获取大范围区域内森林林分年龄的时空分布格局具有至关重要的价值，森林经营规划与实践、生态系统碳收支核算均高度依赖此类数据。然而，受中国南方频发的森林干扰事件（如采伐活动）以及人工林快速恢复的影响，通过野外实地测量获取大范围区域的森林林分年龄数据不仅耗时耗力，且成本高昂。本研究针对中国南方三类典型人工林，绘制了其林分年龄的时空分布格局。研究通过两种新颖可行且精度可靠的方法实现这一目标：1）针对1987年至2017年间至少发生过一次干扰的像元，整合植被变化追踪器（Vegetation Change Tracker, VCT）算法与空间分析（Spatial Analysis, SA）方法；2）针对研究期内未受干扰的像元，整合VCT算法与随机森林（Random Forest, RF）方法。研究结果揭示了林龄结构的时空分布特征，表明本研究大尺度研究区中的人工林林分正逐步趋于老龄化。