Rapid urban expansion has seriously threatened ecological security and the natural environment on a global scale, thus, the simulation of dynamic urban expansion is a hot topic in current research. Existing urban expansion simulation models focus on the mining of spatial neighborhood features among driving factors, however, they ignore the over-fitting, gradient explosion, and vanishing problems caused by the long-term dependence of time series data, which results in limited model accuracy. In this study, we proposed a new dynamic urban expansion simulation model. Considering the long-time dependence issue, long short term memory (LSTM) was employed to automatically extract the transformation rules through memory units and provide the optimal attribute features for cellular automata (CA). This study selected Lanzhou, which is a semi-arid region in Northwest China, as an example to confirm the validity of the model performance using data from 2000 to 2020. The results revealed that the overall accuracy of the model was 91.01%, which was higher than that of the traditional artificial neural network (ANN)-CA and recurrent neural network (RNN)-CA models. The LSTM-CA framework resolved existing problems with the traditional algorithm, while it significantly reduced complexity and improved simulation accuracy. In addition, we predicted urban expansion to 2030 based on natural expansion (NE) and ecological constraint (EC) scenarios, and found that EC was an effective control strategy. This study provides a certain theoretical basis and reference value toward the realization of new urbanization and ecologically sound civil construction, in the context of territorial spatial planning and healthy/sustainable urban development.

The siting of Municipal Solid Waste (MSW) landfills is a complex decision process. Existing siting methods utilize expert scores to determine criteria weights, however, they ignore the uncertainty of data and criterion weights and the efficacy of results. In this study, a coupled fuzzy Multi-Criteria Decision-Making (MCDM) approach was employed to site landfills in Lanzhou, a semi-arid valley basin city in China, to enhance the spatial decision-making process. Primarily, 21 criteria were identified in five groups through the Delphi method at 30 m resolution, then criteria weights were obtained by DEMATEL and ANP, and the optimal fuzzy membership function was determined for each evaluation criterion. Combined with GIS spatial analysis and the clustering algorithm, candidate sites that satisfied the landfill conditions were identified, and the spatial distribution characteristics were analyzed. These sites were subsequently ranked utilizing the MOORA, WASPAS, COPRAS, and TOPSIS methods to verify the reliability of the results by conducting sensitivity analysis. This study is different from the previous research that applied the MCDM approach in that fuzzy MCDM for weighting criteria is more reliable compared to the other common methods.

Single-frame infrared small target (SIRST) detection is crucial for both military and civilian applications, but remains challenging due to low resolution and small target sizes. Most existing methods model the detection task as a semantic segmentation task, which requires high-resolution feature maps and incurs significant computational costs. Moreover, manual annotations often struggle to achieve pixel-level precision, and the inherent ambiguity in the annotations can affect the training outcomes. This paper treats the SIRST detection task as a bounding box regression problem and proposes a novel target detection network architecture, named adaptive fusion bounding box regression network (ABRNet). Specifically, to address the challenges posed by complex and changeable backgrounds, we design an adaptive receptive field module. This module utilizes spatial selection masks to choose feature maps with varying receptive field sizes, thereby leveraging the unique prior knowledge inherent in different scenarios. In addition, we introduce a cross-scale feature encoding fusion structure to alleviate the network’s low tolerance to bounding box perturbations. The module fuses multi-scale local and global features to capture the fine details of small targets. By combining high-dimensional features with detailed features, it facilitates accurate bounding box regression, thereby improving detection performance. Additionally, we employ linear interval mapping to achieve dynamic balancing of hard samples. Experimental results on public datasets demonstrate ABRNet’s superiority over state-of-the-art methods.

Ammonia (NH₃) is an important precursor of secondary inorganic aerosols that affect air quality and human health. Livestock production is an essential source of NH₃ emissions, which exceeded half of the total NH₃ emissions in China. However, our understanding of the livestock point NH₃ emissions is still limited, due to the lack of both monitoring and statistical data. In this study, we established a satellite-based approach to estimating livestock point NH₃ emissions by combining satellite observations and digital maps of points-of-interest (POI). Taking a case study in Hebei province over China, 1267 livestock points were identified. The point livestock NH₃ emissions in 2020 ranged from 16.8 to 126.6 kg N ha⁻¹ yr⁻¹, with an average emission of 42.0 kg N ha⁻¹ yr⁻¹. The livestock NH₃ emissions in Hebei showed an overall increasing trend, with a growth rate of 5.8% yr⁻¹ between 2008 and 2020. In terms of seasonal changes, high livestock NH₃ emissions mainly occurred in spring and summer, while low NH₃ emissions were generally in autumn and winter. Satellite-derived point livestock NH₃ emissions in Hebei were 2–4 times that of bottom-up NH₃ emissions (EDGAR), suggesting that current used bottom-up emissions underestimated point livestock NH₃ emissions. This study proposed a framework for the satellite-based estimation of livestock NH₃ emissions, which is of great significance for relevant N management and NH₃ emission reduction policy formulation.