Satellite image time series (SITS) classification is a challenging application concurrently driven by long-term, large-scale, and high spatial-resolution observations acquired by remote sensing satellites. The focus of current SITS classification research is to exploit the richness of temporal information in SITS data. In the literature, self-attention mechanism-based networks, which are capable of capturing global temporal attention, have achieved state-of-the-art results in SITS classification. However, these methods lack attention to local temporal information, which is also significant for SITS classification tasks. To explore the potential of different scales of temporal information in SITS data, a global–local temporal attention encoder (GL-TAE) is proposed in this paper. GL-TAE has two submodules set up in parallel, one of which is a lightweight temporal attention encoder (LTAE) for extracting global temporal attention and the other is lightweight convolution (LConv) for extracting local temporal attention. Compared with methods exploring global-only or local-only temporal features, the proposed GL-TAE can achieve better performance on two public SITS datasets, which proves the effectiveness of hybrid global–local temporal attention features. The experiments also demonstrate that GL-TAE is a lightweight model, which achieves the same performance as other models but with fewer parameters.

Land use segmentation is a fundamental yet challenging task in remote sensing. Most current methods mainly take images as input and sometimes cannot achieve satisfactory results due to limited information. Inspired by the inherent relations between land cover and land use, we investigate land use segmentation using additional land cover data. The topological relations among land cover objects are beneficial for bridging the semantic gap between land cover and land use. Specifically, these relations are usually depicted by a geo-object-based graph structure. Deep convolutional neural networks (CNNs) are capable of extracting local patterns but fail to efficiently explore topological relations. In contrast, contextual relations among objects can be easily captured by graph convolutional networks (GCNs). In this study, we integrated CNNs and GCNs and proposed the CNN-enhanced HEterogeneous Graph Convolutional Network (CHeGCN) to incorporate local spectral-spatial features and long-range dependencies. We represent topological relations by heterogeneous graphs which are constructed with images and land cover data. Afterwards, we employed GCNs to build topological relations by graph reasoning. Finally, we fused CNN and GCN features to accomplish the inference from land cover to land use. Compared with other homogeneous graph-based models, the land cover data provide more sufficient information for graph reasoning. The proposed method can achieve the transformation from land cover to land use. Extensive experiments showed the competitive performance of CHeGCN and demonstrated the positive effects of land cover data. On the IoU metric over two datasets, CHeGCN outperforms CNNs and GCNs by nearly 3.5% and 5%, respectively. In contrast to homogeneous graphs, heterogeneous graphs have an IoU improvement of approximately 2.5% in the ablation experiments. Furthermore, the generated visualizations help explore the underlying mechanism of CHeGCN. It is worth noting that CHeGCN can be easily degenerated to scenarios where no land cover information is available and achieves satisfactory performance.

In the rapidly developing field of wireless communications, the precise classification of modulated signals is essential for optimizing spectrum utilization and improving communication quality. However, existing networks face challenges in robustness against signals containing phase shift keying and computational efficiency. This paper introduces TCN-GRU, a lightweight model that combines the advantages of multiscale feature extraction of the temporal convolutional network (TCN) and global sequence modeling of gated recurrent unit (GRU). Compared to the state-of-the-art MCLDNN, TCN-GRU reduces parameters by 37.6%, achieving an accuracy of 0.6156 and 0.6466 on the RadioML2016.10a and RadioML2016.10b, respectively (versus MCLDNN’s 0.6101 and 0.6462). Furthermore, TCN-GRU demonstrates superior ability in distinguishing challenging modulations such as QAM16 and QAM64, and it improves classification accuracy by about 10.5% compared to MCLDNN. These results suggest that TCN-GRU is a robust and efficient solution for enhancing AMC in complex and noisy environments.

The extensive amount of Satellite Image Time Series (SITS) data brings new opportunities and challenges for land cover analysis. Many supervised machine learning methods have been applied in SITS, but the labeled SITS samples are time- and effort-consuming to acquire. It is necessary to analyze SITS data with an unsupervised learning method. In this paper, we propose a new unsupervised learning method named Deep Temporal Iterative Clustering (DTIC) to deal with SITS data. The proposed method jointly learns a neural network’s parameters and the resulting features’ cluster assignments, which uses a standard clustering algorithm, K-means, to iteratively cluster the features produced by the feature extraction network and then uses the subsequent assignments as supervision to update the network’s weights. We apply DTIC to the unsupervised training of neural networks on both SITS datasets. Experimental results demonstrate that DTIC outperforms the state-of-the-art K-means clustering algorithm, which proves that the proposed approach successfully provides a novel idea for unsupervised training of SITS data.

Satellite Image Time Series (SITS) record the continuous temporal behavior of land cover types and thus provide a new perspective for finer-grained land cover classification compared with the usual spectral and spatial information contained in a static image. In addition, SITS data is becoming more accessible in recent years due to newly launched satellites and accumulated historical data. However, the lack of labeled training samples limits the exploration of SITS data, especially with sophisticated methods. Even with a straightforward classifier, such as k-nearest neighbor, the accuracy and efficiency of the SITS similarity measure is also a pending problem. In this paper, we propose SKNN-LB-DTW, a seeded SITS classification method based on lower-bounded Dynamic Time Warping (DTW). The word “seeded” indicates that only a few labeled samples are required, and this is not only because of the lack of labeled samples but also because of our aim to explore the rich information contained in SITS, rather than letting training samples dominate the classification results. We use a combination of cascading lower bounds and early abandoning of DTW as an accurate yet efficient similarity measure for large scale tasks. The experimental results on two real SITS datasets demonstrate the utility of the proposed SKNN-LB-DTW, which could become an effective solution for SITS classification when the amount of unlabeled SITS data far exceeds the labeled data.