The remote sensing time series change detection algorithm based on the pixel or single landscape patch ignores the change analysis of spatial structure information. Inspired by graph convolutional network (GCN) modeling, a set of landscapes (nodes) and their relationships (edges) are proposed. In this study, a parallel strategy in spatial-GCN and progressive strategy in temporal-GCN, called the hybrid GCN model network as a holistic framework, was proposed to accurately capture both spatial and temporal variations in landscape patterns based on yearly Landsat time series. A superpatch (i.e., fixed patch class surrounded by a one-hop neighbor patch) was selected as the input of the GCN network. First, a spatial-GCN model with three parallel graph convolutional layers was adopted to classify landscape pattern types. Three dominant categories of landscape patterns over the past three decades have been identified. Second, four landscape metrics in superpatches were proposed for the quantitative characterization of changes in landscape patterns. Finally, a temporal-GCN model with two progressive graph convolutional layers was used to detect six types of patch changes, which were applied to continuously detect the landscape pattern evolution processes. Regardless of the spatial-GCN and temporal-GCN, they provided satisfactory performance using the training and validation sets with overall accuracy >92% and Kappa coefficient $>0.90$ , and loss values converging to 0.049 and 0.128, respectively, based on NLLLoss function until 500 epochs. It is believed that the hybrid GCN model has great potential for mining possible implicit spatiotemporal relationships and future evolution of landscape patterns.

中文翻译：

---

用于从长期遥感图像中检测景观模式演变的混合时空图卷积网络

基于像素或单个景观斑块的遥感时间序列变化检测算法忽略了空间结构信息的变化分析。受图卷积网络（GCN）建模的启发，提出了一组景观（节点）及其关系（边）。在这项研究中，提出了一种空间-GCN 中的并行策略和时间-GCN 中的渐进策略，称为混合 GCN 模型网络作为一个整体框架，以基于年度 Landsat 时间序列准确捕捉景观模式的空间和时间变化。选择一个超级补丁（即，由单跳邻居补丁包围的固定补丁类）作为 GCN 网络的输入。首先，采用具有三个平行图卷积层的空间 GCN 模型对景观图案类型进行分类。在过去的三十年里，三种主要的景观模式已经被确定。其次，提出了超斑块中的四个景观指标，用于定量表征景观格局的变化。最后，使用具有两个渐进图卷积层的 temporal-GCN 模型来检测六种类型的斑块变化，用于连续检测景观格局演变过程。无论空间-GCN 和时间-GCN，它们使用训练和验证集都提供了令人满意的性能，总体准确率 > 92% 和 Kappa 系数 具有两个渐进图卷积层的时间 GCN 模型用于检测六种类型的斑块变化，用于连续检测景观模式演变过程。无论空间-GCN 和时间-GCN，它们使用训练和验证集都提供了令人满意的性能，总体准确率 > 92% 和 Kappa 系数 具有两个渐进图卷积层的时间 GCN 模型用于检测六种类型的斑块变化，用于连续检测景观模式演变过程。无论空间-GCN 和时间-GCN，它们使用训练和验证集都提供了令人满意的性能，总体准确率 > 92% 和 Kappa 系数 $>0.90$ ，并且损失值分别收敛到 0.049 和 0.128，基于 NLLLoss 函数直到 500 个 epoch。相信混合 GCN 模型在挖掘可能的隐含时空关系和景观模式的未来演变方面具有巨大潜力。