Tianjin Energy Investment Group (China)

Timely and accurate decision-making is critical during gas tunnel emergencies, yet relevant knowledge is typically fragmented across unstructured reports, manuals, and case records, hindering rapid access. To address this challenge, a knowledge recommendation approach was proposed that synergistically combines knowledge graph (KG) and large language model (LLM). This method first constructs a domain-specific KG from heterogeneous emergency documents using prompt-optimized LLMs. During inference stage, it retrieves the most contextually relevant subgraph via semantic similarity-based vector search and re-ranks candidates to enhance precision. This retrieved knowledge dynamically augments the LLM, grounding its responses in verified domain facts and reducing hallucinations. Evaluations show that approach substantially outperforms both standalone LLMs and alternative architectures in accuracy, completeness, and coherence. The method proposed in the study improves the speed and quality of emergency response for gas tunnels, offering a structured and interpretable approach to knowledge-driven decision support in this specific high-risk context.

Against the backdrop of accelerating global climate change and urbanization, urban land cover change has emerged as a critical indicator for understanding the dynamic evolution of cities and the transformation of urban ecosystems. This study proposes a data-driven framework for fine-scale urban land cover change assessment based on the UASFNet model, enabling high-precision evaluation of urban land cover dynamics. The approach first performs preprocessing and co-registration of bi-temporal remote sensing images from the study area, and applies the trained UASFNet model to identify urban land cover types and extract land cover information for each temporal phase. The Analytic Hierarchy Process (AHP) is then employed to determine the weights of various indicator factors. By integrating building disturbance, greenbelt disturbance, and road disturbance indices, the framework quantitatively evaluates the intensity of land cover change at both pixel and regional scales. Experimental results across three benchmark datasets, consisting of high-resolution sub-meter RGB urban remote sensing imagery, demonstrate that UASFNet achieves superior segmentation accuracy, with mean Intersection over Union (mIoU) values of 91.52%, 93.31%, and 88.90%, substantially outperforming several state-of-the-art baseline models. Spatial analysis of the Langfang urban area (2017-2023) reveals a marked increase in impervious surface coverage (+16.86%) and a sharp decline in greenbelt (-40%), with the urban landscape exhibiting a multi-core, belt-like expansion pattern oriented toward newly developed districts. The proposed framework not only enhances the interpretability and generalization of remote sensing models in complex urban environments but also provides a scalable analytical tool to support urban spatial planning, ecological conservation, and sustainable city governance.

The widespread adoption of anion exchange membrane (AEM) water electrolysis is impeded by rapid performance decay, largely caused by catalyst layer detachment under low catalyst loading conditions. To overcome this, we present a structurally graded AEM design that establishes efficient transport pathways from the molecular level to the membrane/catalyst layer interface. At the bulk transport level, molecular dynamics simulations and experimental validation confirm that the designed polymer matrix, based on the C-F backbone and flexible cationic side chains, promotes favorable microphase separation. This leads to well-connected ionic nanochannels that facilitate superior bulk hydroxide conduction. At the membrane/catalyst interface, a biomimetic micro-nano pattern, inspired by aquatic plants, is engineered onto the membrane surface via an industrially scalable embossing calendaring process. The resulting patterned interface optimizes interfacial contact, enhancing catalyst adhesion and mass transfer. By integrating these two scales of transport, a highly efficient membrane electrode assembly is realized, enabling synergistic management of ions, water, and gas bubbles. The resulting AEM achieves a record-high hydroxide ion conductivity of 338.2 mS cm-1 at 80°C and exceptional ductility, with elongation of 162.0%, surpassing all previously reported AEMs. More importantly, the water electrolysis demonstrates markedly enhanced operational stability under various conditions.