Search

The demographic transition that accompanies the urbanization transformation has a key impact on land use efficiency. This study applies the PVAR, SDM, and threshold models to investigate the influence of China’s demographic dividend composition on urban land use efficiency, aiming to provide guidance for the strategic management and allocation of demographic resources, thereby optimizing urban land resource utilization. The key findings are as follows: (1) Spatial effects reveal that the scale and structural dividends of the population size dividend significantly inhibit urban land use efficiency, whereas the technological dividend of the population quality dividend initially restrains but ultimately enhances it. The combined impact of quantitative and qualitative demographic dividends on land use efficiency is most pronounced in the west and least in the east. High population provinces see significant land use efficiency benefits, contrasting with medium and low population provinces. (2) Both population size and quality dividends exhibit a single-threshold effect on land use efficiency. In summary, cultivating diverse talents with superior technical skills is essential for fostering the upgrade of new industrialization models, ultimately significantly enhancing land use efficiency.

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.

Long-term stability is crucial in cropland for maintaining stable agricultural production and ensuring national food security. However, relatively few studies have been conducted on the long-term stability of cropland at the national level. This study assessed the long-term stability of cropland in China from 1990 to 2018 using a fine-resolution land use dataset. The experimental results indicated that the average area of unstable cropland in China from 1990 to 2018 amounted to 2.08 × 106 km2, 47.31% of the total. The Qinghai–Tibet Plateau exhibited the highest average proportion of unstable cropland at 65.9%, followed by the northern arid and semiarid region, Southern China, and the Yunnan–Guizhou Plateau. The quantity of unstable cropland in China initially declined before increasing, reaching a final growth rate of 5.09%. Furthermore, this study explored the relevant driving factors of cropland’s long-term stability from both natural factors and human activities based on artificial neural networks. The relative importance of distance to vegetation reached a value of 0.30, indicating that it had the most significant influence on the long-term stability of cropland, followed by relief amplitude and soil type. This phenomenon may be attributed to the inadequate execution of the Grain for Green Policy and the requisition–compensation balance of cropland policy, along with the depletion of young and middle-aged laborers due to urban migration from rural areas. Local governments should focus on addressing the unsustainable exploitation of sloped land in rural mountainous or hilly regions while preventing urban developers from appropriating fertile cropland to compensate for less fertile areas.

The unequal distribution of territorial space resources stands out as a leading cause of the human–land contradictions and environmental degradation. These issues are especially pronounced in the Minjiang River Basin, which exhibits significant regional disparities. In pursuit of solutions to these pressing problems and the identification of sustainable developmental pathways, this study presents an innovative territorial space double optimization simulation model. This model integrates quantity structure optimization and distribution pattern optimization, in order to comprehensively consider the optimization of territorial space allocation and build a new territorial space pattern for the Minjiang River Basin in 2030. On this basis, we employed the Patch-generating Land Use Simulation (PLUS) model and scenario analysis method to design the double optimization scenario and natural development scenario. By comparing these two scenarios, and calculating the ecological benefits (EB), economic benefits (ECB), carbon storage (CS), and comprehensive benefits (CB) achieved in different scenarios, the validity of the double optimization model was fully verified. The results indicated that: ① the loss of sub-ecological space (PeS) under the natural development scenario was significantly larger than that under the double optimization scenario, and the loss should be mainly attributed to the large expansion of production space (PS) and living space (LS); ② the area of ecological space (ES) has reduced since 2020, but less area was lost and the retention rate was higher under the double optimization scenario; ③ the natural development scenario made the research region gain more ECB, but it also resulted in the loss of more EB and CS, whereas the Minjiang River Basin under the double optimization scenario was able to effectively balance the relationship among the three, thus achieving the best CB. The research findings provide strong scientific support for alleviating the human–land contradictions, protecting the ecological security in the basin, and promoting the sustainable development of the region.

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).

The decoupling of cropland and livestock due to the industrialization of livestock production is a difficult problem for sustainable agricultural development in many global locations, including China. As population and urbanization increase, this decoupling is likely to become more serious. To date, the relationship between cropland and livestock has been mainly studied from a single perspective, and mostly at the regional and the local scales. Thus, the objective of our study is to systematically assess the coupling relationship between cropland and livestock from multiple aspects on a large scale. Here, we used a complex system covering cropland, livestock and environment subsystems to comprehensively analyze the spatio-temporal variation of the coupling coordination between cropland and livestock and its influencing factors in China over the past two decades. Elaborating on the data, we constructed a comprehensive system of evaluation indexes for cropland–livestock systems. We used a coupling coordination degree model to evaluate the coupling coordination relationship between cropland and livestock in 31 provinces of China during 2000–2020. The results show that the range of cropland–livestock and cropland–livestock–environment coupling coordination degree was 0.4–0.9. In most of the provinces, there was no risk of cropland and livestock decoupling; however, the coupling coordination degree needed to be increased. More attention should be paid to the coordinated development of cropland and livestock coupling in urbanized areas such as Beijing and Tianjin, where cropland and livestock decoupling was more likely to occur. Among the assessed 29 factors, 15 and 16 had an impact on the cropland–livestock and the cropland–livestock–environment coupling coordination degrees, respectively. Our study provides science-based evidence to support estimating the coupling relationship between cropland and livestock in the future.

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.

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.

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.

Increasing trends of atmospheric nitrogen (N) deposition resulting from a large number of anthropogenic emissions of reactive N are dramatically altering the global biogeochemical cycle of N. Nitrogen uptake by mosses mainly from the atmosphere, making a competent bio-indicator for N deposition. However, high uncertainties exist when using mosses to indicate N deposition, especially in choosing sampling period and sampling frequency. In this study, atmospheric N deposition and moss N content in the urban-agro-forest transition, a region with a high N deposition level of 27.46~43.70 kg N hm-2 yr-1, were monitored, and the method for atmospheric N deposition monitoring by mosses was optimized. We found that the optimal sampling frequency is within six months per time, and the optimal sampling time is autumn (October and November) and summer July and August), which gives us a better estimation for atmospheric N deposition than other scenarios. In addition, the moss N content could better indicate total N deposition than the deposition of specific N species. This study eventually allowed moss to be used more effectively and sensibly as an indicator of atmospheric N deposition and helped to improve the accuracy of the model of quantifying N deposition by using mosses. [ABSTRACT FROM AUTHOR]