Agricultural land extraction is an essential technical means to promote sustainable agricultural development and modernization research. Existing supervised algorithms rely on many finely annotated remote-sensing images, which is both time-consuming and expensive. One way to reduce the annotation cost approach is to migrate models trained on existing annotated data (source domain) to unannotated data (target domain). However, model generalization capability is often unsatisfactory due to the limit of the domain gap. In this work, we use an unsupervised adversarial domain adaptation method to train a neural network to close the gap between the source and target domains for unsupervised agricultural land extraction. The overall approach consists of two phases: inter-domain and intra-domain adaptation. In the inter-domain adaptation, we use a generative adversarial network (GAN) to reduce the inter-domain gap between the source domain (labeled dataset) and the target domain (unlabeled dataset). The transformer with robust long-range dependency modeling acts as the backbone of the generator. In addition, the multi-scale feature fusion (MSFF) module is designed in the generator to accommodate remote sensing datasets with different spatial resolutions. Further, we use an entropy-based approach to divide the target domain. The target domain is divided into two subdomains, easy split images and hard split images. By training against each other between the two subdomains, we reduce the intra-domain gap. Experiments results on the “DeepGlobe → LoveDA”, “GID → LoveDA” and “DeepGlobe → GID” unsupervised agricultural land extraction tasks demonstrate the effectiveness of our method and its superiority to other unsupervised domain adaptation techniques.

Carbon emissions caused by economic growth are the main cause of global warming, but controlling economic growth to reduce carbon emissions does not meet China's conditions. Therefore, how to synergize economic growth and carbon emission reduction is not only a sustainable development issue for China, but also significant for mitigating global warming. The territorial spatial functional pattern (TSFP) is the spatial carrier for coordinating economic development and carbon emissions, but how to establish the TSFP of synergizing economic growth and carbon emission reduction remains unresolved. We propose a decision framework for optimizing TSFP coupled with the multi-objective fuzzy linear programming and the patch-generating land use simulation model, to provide a new path to synergize economic growth and carbon emission reduction in China. To confirm the reliability, we took Qionglai City as the demonstration. The results found a significant spatiotemporal coupling between TSFP and the synergistic states between economic growth and carbon emission reduction (q ≥ 0.8220), which resolves the theoretical uncertainty about synergizing economic growth and carbon emission reduction through the path of TSFP optimization. The urban space of Qionglai City in 2025 and 2030 obtained by the decision framework was 6497.57 hm² and 6628.72 hm² respectively, distributed in the central and eastern regions; the rural space was 60,132.92 hm² and 56,084.97 hm², concentrated in the east, with a few located in the west; and the ecological space was 71,072.52 hm² and 74,998.31 hm², mainly located in the western and southeastern areas. Compared with the TSFP in 2020, the carbon emission intensity of the TSFP obtained by the decision framework was reduced by 0.7 and 4.7 tons/million yuan, respectively, and realized the synergy between economic growth and carbon emission reduction (decoupling index was 0.25 and 0.21). Further confirming that TSFP optimization is an effective way to synergize economic growth and carbon emission reduction, which can provide policy implications for coordinating economic growth and carbon emissions for China and even similar developing countries.

Land-use and land-cover changes (LUCCs) significantly impact carbon sequestration by modifying the structure and function of terrestrial ecosystems. This study utilized GIS and remote sensing techniques to forecast future LUCC patterns and their influence on regional carbon budgets, which is essential for sustainable development. We devised a coupled system dynamics (SD) model integrated with a patch-generating land-use simulation (PLUS) model to simulate LUCCs under diverse future scenarios using multisource environmental data. Additionally, the InVEST model was employed to quantify carbon storage in terrestrial ecosystems. By establishing three scenarios—ecological priority (EP), highly urbanized (HU), and coordinated development (CD)—this study’s aim was to predict the LUCC patterns and carbon storage distribution of the Tuojiang River Basin (TRB), China, up to 2035. The results showed that (1) from 2000 to 2020, significant LUCCs occurred in the TRB, primarily involving the conversion of cultivated land into construction areas and forestland; (2) LUCCs had a substantial impact on carbon storage in the TRB, with the EP scenario demonstrating the highest carbon storage by 2035 due to extensive forest expansion, while the HU scenario indicated a decline in carbon storage associated with rapid urbanization; and (3) the mountainous regions of the TRB, dominated by forestland, consistently exhibited higher carbon storage, whereas the Chengdu Plain region in the upper basin displayed the lowest. In conclusion, we recommend prioritizing the CD scenario in future development strategies to balance economic growth with ecological protection while simultaneously enhancing carbon storage. Our findings offer valuable insights to shape future LUCC policies in the Tuojiang River Basin, underscoring the adaptability of the coupled model approach to a wide range of geographic scales and contexts.

In recent years, convolutional neural networks (CNNs) have been widely used in hyperspectral image (HSI) classification. However, feature extraction on hyperspectral data still faces numerous challenges. Existing methods cannot extract spatial and spectral-channel contextual information in a targeted manner. In this paper, we propose an encoder–decoder network that fuses spatial attention and spectral-channel attention for HSI classification from three public HSI datasets to tackle these issues. In terms of feature information fusion, a multi-source attention mechanism including spatial and spectral-channel attention is proposed to encode the spatial and spectral multi-channels contextual information. Moreover, three fusion strategies are proposed to effectively utilize spatial and spectral-channel attention. They are direct aggregation, aggregation on feature space, and Hadamard product. In terms of network development, an encoder–decoder framework is employed for hyperspectral image classification. The encoder is a hierarchical transformer pipeline that can extract long-range context information. Both shallow local features and rich global semantic information are encoded through hierarchical feature expressions. The decoder consists of suitable upsampling, skip connection, and convolution blocks, which fuse multi-scale features efficiently. Compared with other state-of-the-art methods, our approach has greater performance in hyperspectral image classification.

Semantic segmentation of Polarimetric SAR (PolSAR) images is an important research topic in remote sensing. Many deep neural network-based semantic segmentation methods have been applied to PolSAR image segmentation tasks. However, a lack of effective means to deal with the similarity of object features and speckle noise in PolSAR images exists. Thisstudy aims to improve the discriminative capability of neural networks for various intensities of backscattering coefficients while reducing the effects of noise in PolSAR semantic segmentation tasks. Firstly, we propose pre-processing methods for PolSAR image data, which consist of the fusion of multi-source data and false color mapping. Then, we propose a Multi-axis Sequence Attention Segmentation Network (MASA-SegNet) for semantic segmentation of PolSAR data, which is an encoder–decoder framework. Specifically, within the encoder, a feature extractor is designed and implemented by stacking Multi-axis Sequence Attention blocks to efficiently extract PolSAR features at multiple scales while mitigating inter-class similarities and intra-class differences from speckle noise. Moreover, the process of serialized residual connection design enables the propagation of spatial information throughout the network, thereby improving the overall spatial awareness of MASA-SegNet. Within the decoder, it is used to accomplish the semantic segmentation task. The superiority of this algorithm for semantic segmentation will be explored through feature visualization. The experiments show that our proposed spatial sequence attention mechanism can effectively extract features and reduce noise interference and is thus able to obtain the best results on two large-scale public datasets (the AIR-POlSAR-Seg and FUSAR-Map datasets).

Three-dimensional fluorescence is currently studied by methods such as parallel factor analysis (PARAFAC), fluorescence regional integration (FRI), and principal component analysis (PCA). There are also many studies combining convolutional neural networks at present, but there is no one method recognized as the most effective among the methods combining convolutional neural networks and 3D fluorescence analysis. Based on this, we took some samples from the actual environment for measuring 3D fluorescence data and obtained a batch of public datasets from the internet species. Firstly, we preprocessed the data (including two steps of PARAFAC analysis and CNN dataset generation), and then we proposed a 3D fluorescence classification method and a components fitting method based on VGG16 and VGG11 convolutional neural networks. The VGG16 network is used for the classification of 3D fluorescence data with a training accuracy of 99.6% (as same as the PCA + SVM method (99.6%)). Among the component maps fitting networks, we comprehensively compared the improved LeNet network, the improved AlexNet network, and the improved VGG11 network, and finally selected the improved VGG11 network as the component maps fitting network. In the improved VGG11 network training, we used the MSE loss function and cosine similarity to judge the merit of the model, and the MSE loss of the network training reached 4.6 × 10⁻⁴ (characterizing the variability of the training results and the actual results), and we used the cosine similarity as the accuracy criterion, and the cosine similarity of the training results reached 0.99 (comparison of the training results and the actual results). The network performance is excellent. The experiments demonstrate that the convolutional neural network has a great application in 3D fluorescence analysis.