Chongqing Municipal Government

Traffic flow forecasting is crucial for effective urban planning and the development of intelligent transportation systems. However, accurately capturing the complex spatiotemporal dependencies in traffic flow data remains a significant challenge. Current approaches typically face two major limitations: (i) insufficient modeling of long-term historical traffic flow patterns, which hinders the capture of global trends and periodic behaviors; and (ii) inadequate consideration of spatial structures and temporal response heterogeneity, which limits the model’s representational capacity. To tackle these challenges, this paper proposes a novel forecasting framework named Spatiotemporal Memory Decoupled Transformer (STMDFormer). First, a spatiotemporal embedding module is designed to fuse topological node structures with multi-scale periodic information. Then, a spatial memory attention mechanism is introduced, incorporating a learnable historical memory bank and a biased adjacency matrix for dynamic modeling of long-term traffic flow patterns. Furthermore, a decoupled learning module is designed to separate spatial and temporal features through normalization techniques, while employing multi-head attention to better capture spatiotemporal heterogeneity. Extensive experiments on four real-world traffic datasets demonstrate that STMDFormer consistently outperforms various state-of-the-art baselines in forecasting accuracy, validating its effectiveness in dynamic spatiotemporal modeling.

Abstract Frequent droughts in the Sichuan Basin (SCB) have caused severe socioeconomic impacts and significantly altered the regional water cycle. However, the connection between these droughts and the atmospheric water cycle remains unclear. Here, we applied two process‐based models—the Dynamic Recycling Model (DRM) and the Hybrid Single Particle Lagrangian Integrated Trajectory (HYSPLIT) model—to investigate the characteristics and mechanisms of atmospheric water cycles during SCB summer droughts from 1979 to 2022. The results show that the climatological mean precipitation recycling ratios for June, July, and August were 12.92%, 13.04%, and 12.63%, respectively, indicating the SCB's strong dependence on externally transported moisture. Most droughts are linked to deficits in external moisture transport. However, in the later stages of the most severe droughts (e.g., August 2006 and 2022), the drought evolves from preceding external moisture reduction into an internal‐moisture‐depletion regime. This shift is driven by extreme soil moisture depletion, which markedly intensifies land–atmosphere coupling and ultimately leads to the collapse of local moisture recycling. Moisture tracking further reveals that droughts with external deficits are associated with reduced oceanic inflow, while those with internal deficits exhibit reduced terrestrial moisture contributions despite sufficient oceanic supply, reflecting low efficiency in converting available moisture into rainfall. Large‐scale circulation systems, especially the Western Pacific Subtropical High and mid‐latitude westerlies, play a key role in shaping these drought‐related anomalies by regulating moisture transport and precipitation efficiency, while land–atmosphere coupling further amplifies these anomalies. These findings provide new insights into summer drought dynamics in the SCB and inform improved drought prediction under a changing climate.

Abstract Tick distribution in China has significantly expanded with urbanization and climate change. Chongqing faces a significant risk of severe fever with thrombocytopenia syndrome (SFTS), but targeted prevention efforts are challenging due to unclear exposure pathways. This study combined generalized linear model (GLM), Bayesian networks, and Bayesian multivariate GLM to assess environmental, agricultural, and socioeconomic drivers of tick exposure in southwestern China. Direct tick exposure risks primarily arose from proximity to shrublands, forests, and cattle farming. Pet ownership also increased risk, while proximity to croplands reduced exposure, likely due to the pesticide/herbicide use and tillage. Bayesian networks revealed that socioeconomic factors indirectly mediated risk. Higher education levels reduced cattle farming likelihood and increased income tier, lowering exposure by altering land-use proximity and agricultural activities. Key factors showing no significant association included demographics (age/gender), grassland proximity, and crop cultivation. Bayesian methods resolved collinearity and mediation effects in GLM, clarifying township-level tick exposure mechanisms in Southwest China and mapping driver networks. Findings demonstrate that tick exposure stems from complex interactions among environmental, agricultural, and socioeconomic factors. Prevention in mountainous southwest China should prioritize the shrubland/forest–cattle farming ecological interface. Future studies should integrate geospatial data for enhanced risk mapping.

Malignant bone- and cartilage-forming tumors exhibit heterogeneous clinical behavior across various body regions. Understanding the mechanisms underlying these differences is essential for developing targeted diagnostic and therapeutic strategies. This review proposes the hypothesis that tissue stiffness heterogeneity contributes to the distinct progression and prognosis of tumors in the jaw and temporomandibular joint (TMJ) compared to peripheral skeletal sites, potentially through stiffness-mediated metabolic reprogramming. To evaluate this hypothesis, a conceptual framework is provided to guide future research. This review summarizes spatial and temporal variations in stiffness across the jaw, TMJ, and femur, and introduces potential mechanisms through which mechanical stiffness may influence tumor metabolism. Technical strategies and material considerations for designing scaffolds that mimic bone and cartilage stiffness are discussed, along with current applications of stiffness-biomimetic scaffolds for in vitro investigation of malignant bone- and cartilage-forming tumors. By integrating insights from mechanobiology, tumor metabolism, and scaffold engineering, this review aims to facilitate the development of targeted experimental approaches that may contribute to more effective treatment strategies.