The decline of cultivated land significantly threatens the food supply. In recent years, remote sensing change detection emerged as a valuable tool for monitoring non–agriculturalization. However, existing deep learning methods for change detection suffer from the problem of inadequate utilization of feature information during image feature extraction, leading to noisy or inaccurate change maps. To address these challenges, we propose a siamese network based on full-scale connected UNet (SNUNet3+), whose encoder extracts features from the original images at various levels. Then, it merges all fine-grained spatial information and coarse-grained semantic information into the decoder through full-scale skip connections to obtain the feature maps with complete information. The spatial and channel Squeeze & Excitation (scSE) attention mechanism is embedded within the decoder sub-network to enhance the discriminative power of the features. Additionally, a deep supervision module is introduced to improve the feature learning capability of the hidden layers and the quality of features. Moreover, accurate cultivated land change detection remains challenging because of the lack of fine-grained detection datasets. To enable the proposed method to achieve cultivated land change detection, we produced a cultivated land change detection dataset containing 5170 pairs of 256 × 256 bitemporal images with a spatial resolution of 1 m. The effectiveness and performance of the proposed method are evaluated on three high-resolution remote sensing change detection datasets. Extensive experimental results show that the proposed method outperforms other state-of-the-art methods, achieving the highest F1s of 72.90%, 90.36%, and 96.64% on the CLCD dataset, LEVIR-CD dataset, and PX-CLCD dataset, respectively.

User preferences are typically analyzed by recommendation systems for recommending items. However, in most existing restaurant recommendation methods, recommendation similarity (e.g., reviews, sentiment) is considered only from the perspective of users, whereas restaurant attributes and potential connections between restaurants are ignored. Furthermore, the dining interests of users are diverse and not fixed. For improved recommendations, the changes of user interests should be considered. To address these problems, this study proposed a recommendation approach that combines knowledge graphs and long-term and short-term interests of users. In the approach, user preferences were analyzed from the attributes of restaurant using the semantic structure of knowledge graphs to obtain long-term user representations. Next, we filtered recent historical restaurants based on time series to obtain short-term user representations through the gated recurrent unit. To integrate long- and short-term interests, a novel gated structure was designed to obtain dynamic interest weights. Extensive experiments on a real-world dataset revealed that the proposed approach outperformed baseline methods.

Carbon dioxide (CO₂) emissions are considered a significant factor that results in climate change. To better support the formulation of effective policies to reduce CO₂ emissions, specific types of important emission patterns need to be considered. Motivated by the flock pattern that exists in the domain of moving object trajectories, this paper extends this concept to a geographical flock pattern and aims to discover such patterns that might exist in CO₂ emission data. To achieve this, a spatiotemporal graph (STG)-based approach is proposed. Three main parts are involved in the proposed approach: generating attribute trajectories from CO₂ emission data, generating STGs from attribute trajectories, and discovering specific types of geographical flock patterns. Generally, eight different types of geographical flock patterns are derived based on two criteria, i.e., the high–low attribute values criterion and the extreme number–duration values criterion. A case study is conducted based on the CO₂ emission data in China on two levels: the province level and the geographical region level. The results demonstrate the effectiveness of the proposed approach in discovering geographical flock patterns of CO₂ emissions and provide potential suggestions and insights to assist policy making and the coordinated control of carbon emissions.