Land cover change affects the carbon emissions of ecosystems in some way. The qualitative and quantitative understanding of carbon emissions from human activities (e.g., land cover change, industrial production, etc.) is highly significant for realizing the objective of carbon neutrality. Therefore, this paper used GlobeLand30 land cover maps, annual average normalised difference vegetation index (NDVI) data, annual average net ecosystem productivity (NEP) data and statistical yearbook data from 2000 to 2020 to explore the relationship between land cover change and carbon emissions. Specifically, it included land cover change, carbon storage changes influenced by land cover change, spatial and temporal analysis of carbon sources and sinks, land use intensity change and anthropogenic carbon emissions. The results of the study show that the main land cover changes in Shandong province during 2000–2020 was cultivated land conversion to artificial surfaces. Among them, the area of cultivated land converted to artificial surfaces from 2000 to 2010 was 4930.62 km², and the proportion of cultivated land converted to artificial surfaces from 2010 to 2020 was as high as 78.35%. The total carbon stock of vegetation affected by land cover change decreased by 463.96 × 10⁴ t and 193.50 × 10⁴ t in 2000–2010 and 2010–2020 respectively. The spatial and temporal distribution of carbon sources and sinks differed more markedly from 2000 to 2020, and land use intensity changes in Shandong Province showed an upward trend. Of the total energy production, industry has the largest energy consumption, followed closely by total energy consumption in transportation, storage and postal services.

Unsupervised domain adaptation (UDA) is an important solution to reduce the bias between the labeled source domain and the unlabeled target domain. It has attracted more attention for optical remote sensing image scene classification and retrieval. Currently, most of the previous work is devoted to closed-set UDA. In fact, the target domain often contains unknown classes. Moreover, some open UDA methods mine structural information of the target domain directly from the type knowledge of the source domain, and less directly from the unlabeled data of the target domain. In this paper, we propose a new self-supervised-driven open-set UDA method combining contrastive self-supervised learning with consistency self-training for optical remote sensing scene classification and retrieval. Specifically, a contrastive self-supervised learning network is introduced to learn discriminative features from the unlabeled target domain data. Moreover, a novel open-set class learning module is developed based on two-level confidence rules and the consistency self-training strategy, which can obtain reliable unknown class samples for co-training. Finally, an open-set dataset including six cross-domain scenarios is constructed based on three public datasets and several experiments are conducted with eleven state-of-the-art domain adaptation methods. Experimental results demonstrate that our proposed method achieves superior performances on the six open-set cross-domain scenarios in both scene classification and retrieval. Especially, our method improves the overall classification accuracies by 9.72% to 24.06% and improve mean average retrieval precisions by 8.06% to 16.21% on the complex UCMD (source domain) → NWPU (target domain) scenario, compared with the other eleven state-of-the-art methods.

Automatically extracting buildings from remote sensing images with deep learning is of great significance to urban planning, disaster prevention, change detection, and other applications. Various deep learning models have been proposed to extract building information, showing both strengths and weaknesses in capturing the complex spectral and spatial characteristics of buildings in remote sensing images. To integrate the strengths of individual models and obtain fine-scale spatial and spectral building information, this study proposed a stacking ensemble deep learning model. First, an optimization method for the prediction results of the basic model is proposed based on fully connected conditional random fields (CRFs). On this basis, a stacking ensemble model (SENet) based on a sparse autoencoder integrating U-NET, SegNet, and FCN-8s models is proposed to combine the features of the optimized basic model prediction results. Utilizing several cities in Hebei Province, China as a case study, a building dataset containing attribute labels is established to assess the performance of the proposed model. The proposed SENet is compared with three individual models (U-NET, SegNet and FCN-8s), and the results show that the accuracy of SENet is 0.954, approximately 6.7%, 6.1%, and 9.8% higher than U-NET, SegNet, and FCN-8s models, respectively. The identification of building features, including colors, sizes, shapes, and shadows, is also evaluated, showing that the accuracy, recall, F1 score, and intersection over union (IoU) of the SENet model are higher than those of the three individual models. This suggests that the proposed ensemble model can effectively depict the different features of buildings and provides an alternative approach to building extraction with higher accuracy.

Recent advances in deep learning have dramatically improved the performance of content-based remote sensing image retrieval (CBRSIR) with the same distribution of training set (source domain) and test set (target domain). In fact, their distributions are inconsistent in most cases, which can lead to a dramatic decrease in retrieval performance. Currently, some unsupervised domain adaptation (DA) methods for other remote sensing applications have been proposed to eliminate the inconsistency. However, the current unsupervised DA methods do not make full use of the target domain’s distribution characteristics when delineating its decision boundary. This tends to degrade the cross-domain retrieval performance. In this paper, a pseudo-label consistency learning-based unsupervised DA method (PCLUDA) is proposed for cross-domain CBRSIR. Our PCLUDA method minimizes the difference in probability distribution between the target domain and its perturbed output by a pseudo-label self-training and consistency regularization strategy, followed by adjusting the target domain’s decision boundaries to the low-density region. Besides, minimize class confusion is introduced to reduce negative transfer caused by large intra-class variance of remote sensing images. Two cross-domain datasets with twelve cross-domain scenarios are constructed based on six open access datasets to measure DA methods. Experimental results show that our PCLUDA method achieves superior retrieval performances with average retrieval precision improvement by 4.9%-32.3% compared with eight state-of-the-art DA approaches in complex cross-domain scenarios. Furthermore, other experimental results indicate that our PCLUDA can also reach optimal retrieval performances in different kinds of deep learning networks (i.e., vision transformer and convolutional neural networks).

Benchmark datasets are essential to develop and evaluate remote sensing image retrieval (RSIR) approaches. However, there are no two datasets with different remote sensing image sources, an approximate equal number of images, the same classification system, and image size in the existing public benchmark datasets. This may affect the evaluation of the universality and robustness of RSIR approaches for the same category in different datasets, and even hinder the development of new cross-source RSIR approaches that require remote sensing images from different sources. We therefore present two new large-scale datasets from ArcGIS and Bing World Imagery, respectively. Similar to the PatternNet dataset from Google Earth Imagery, both two new collected datasets contain 38 classes using the same classification system and each class has at least 1,500 images. We conduct experiments using five handcrafted low/mid-level feature methods and six deep learning high-level feature methods on the two datasets. Results show that our datasets are effective for evaluating different RSIR approaches and the results can be served as the baseline for future research. We also perform the comparison and the cross analysis compared with other large-scale datasets. Results indicate that our datasets are more inclusive, richer variations and better intra-class diversity. Besides, other experimental results show that our new datasets and the VGoogle (extracted by volunteers from Google imagery) dataset can be merged into one dataset for larger-scale remote sensing image retrieval.

The discriminative ability of image features plays a decisive role in content-based remote sensing image retrieval (CBRSIR). However, the widely-used convolutional neural networks cannot focus on the discriminative features of important scenes, resulting in unsatisfactory retrieval performance in complex contexts. In this article, an attention-enhanced end-to-end discriminative network with multiscale learning for CBRSIR is proposed to solve this issue. First, a multiscale dilated convolution module is embedded into some of ResNet50’s residual blocks to increase the perceptual field and capture the multiscale features of remote sensing image scenes. Then, a lightweight and efficient triplet attention module is added behind each residual block to capture the salient features of remote sensing images and establish the interdimensional dependencies using residual transform. In addition, the end-to-end training approach is performed using an online label smoothing loss to reduce the intraclass variance of features and enhance interclass differentiability. Experimental results on four publicly available remote sensing image datasets show that our network achieves state-of-the-art or competitive performance, especially on complex scene dataset UCMD with an average retrieval precision improvement of 3.23% to 29.35% compared to other new methods.