Sustainable biomass resources are promising precursors for carbon electrodes in supercapacitors because of their wide availability, affordability, and environmental compatibility. Nevertheless, the commonly used KOH activation method has strong corrosiveness and processing risks, which is detrimental to green and sustainable development. To address this issue, potassium oxalate (K2C2O4), a relatively low-corrosive potassium-salt activating reagent, was selected to activate coconut shell through a one-step thermal treatment, thereby producing carbon materials with abundant porous structures. At the optimized heating rate of 7.5 degrees C min-1, CSAC-7.5 delivered 366.3 F g-1 at 0.5 A g-1, with 93% of its initial capacitance preserved over 20,000 cycles. A symmetric device assembled from CSAC-7.5 achieved 13.15 Wh kg-1 when operated at 300 W kg-1. These findings indicate that heating-rate regulation can improve K2C2O4-assisted biomass carbon activation and guide the design of sustainable carbon electrodes.
The lateral expansion–contraction register error in water-based ink paper printing exhibits significant strong coupling and nonlinearity—a key factor restricting high-quality printing. To address issues such as long manual adjustment times and severe material waste, this paper proposes a lateral expansion–contraction register control method based on an improved Elman neural network. First, a linear circular register error detection color mark is designed, and actual printing condition data is collected to construct a lateral expansion–contraction register error dataset. Based on this, the mapping relationship between paper lateral expansion–contraction register error and oven temperature/fan air volume is studied. A lateral expansion–contraction register control method based on the Elman neural network is proposed, and its parameters are optimized by introducing the Adaptive Genetic Algorithm (AGA). Finally, the improved Elman neural network is compared with BP and CNN neural networks to validate the effectiveness of different methods in controlling lateral expansion–contraction register error. Experimental results show that the proposed AGA-Elman method can effectively control the lateral expansion–contraction register error within ±0.1 mm, meeting the requirements for high-speed, high-precision printing on paper gravure machines.
Recent progress in prompt-driven vision transformers has markedly enhanced remote sensing image (RSI) mantic segmentation. However, existing methods often fail to incorporate fine-grained geometric structure and to effectively address the spatial heterogeneity present in complex aerial scenes. To overcome these limitations, we propose GeoMoE, a geometry-driven adaptive mixture-of-experts framework tailored for precise and efficient semantic segmentation. Building upon a frozen vision transformer backbone, GeoMoE introduces three novel components, 1) a token-field hybrid adapter (TFH-Adapter) that enables geometry-aware feature adaptation without modifying backbone parameters; 2) a geometry-contextual prompt generator (Geo-Prompt) that integrates multi-scale shape prototypes and contextual cues into expressive prompt embeddings; and 3) a geometry mixture of-complexity-experts (Geo-MoCE) decoder which dynamically routes spatial regions to specialized experts based on local geometric complexity. This unified architecture allows explicit modeling of geometric information and flexible allocation of decoding capacity, resulting in more accurate segmentation of structurally complex and heterogeneous regions. Extensive experiments on several benchmark remote sensing datasets demonstrate that GeoMoE achieves state-of-the-art performance in segmentation accuracy, model efficiency, and boundary delineation.
Urban floods pose a serious threat to human life, property safety, and socio-economic development. Urban flood modeling plays a vital role in disaster prevention and resilient infrastructure planning. Traditionally, one-dimensional (1D) drainage network and two-dimensional (2D) surface flow coupling models based on physical processes have been widely used to simulate urban flooding. However, such models require substantial computational resources and long execution times, making them unsuitable for real-time flood forecasting over large areas. This study proposes a CNN-Transformer model as an efficient surrogate for physical models in rapid urban flood forecasting. The model is trained using high-resolution gridded precipitation data and inundation simulation outputs generated by a calibrated 1D/2D hydrodynamic model, covering 5,475,655 grid cells within the study area. By integrating the spatial features of rainfall and the temporal dynamics of flood evolution, the model enables fast and reliable predictions. The study shows that the CNN-Transformer model closely matches the physical model in predicting flood depth, inundation extent, and flood volume, achieving a mean relative error below 10%, NSE >= 0.956, and R-2 > 0.958. Additionally, the model reduces computation time by approximately 287.4-308.8 times compared to the physical model, meeting the real-time requirements of flood emergency response. These results indicate that the proposed method significantly improves computational efficiency while maintaining high predictive accuracy. It contributes to the development of smarter and more sustainable urban decision-making systems and holds strong practical value for real-time flood risk management, infrastructure planning, and climate resilience enhancement.
In complex and diverse power grid fault scenarios, constructing a systematic fault handling knowledge system is an effective approach to enhancing the intelligence of fault handling. Therefore, we propose a knowledge graph construction method for power grid fault handling based on prompt learning and Low-Rank Adaptation (LoRA) fine-tuning. The proposed method extracts fault handling knowledge from multi-source documents such as fault handling operational regulations and historical cases and represents it in a structured form. The method first segments long documents to satisfy the input length constraint of large language models (LLMs), then designs a stepwise prompting strategy with schema constraints to guide the LoRA-fine-tuned LLM in extracting entities and triples, and finally achieves cross-document knowledge fusion through entity alignment and consistency maintenance to complete knowledge graph construction. Experiments are conducted on four open-source LLMs, namely QwQ-32B, DeepSeek-R1-Distill-Qwen-32B, GLM-4-32B, and gpt-oss-20B, and the results show that QwQ-32B achieves the best performance. After LoRA fine-tuning, the QwQ-32B-tuned model achieves F1 scores of 91.9% and 84.8% for entity and triple extraction, respectively. The constructed knowledge graph can provide decision support for power grid fault handling and serve as a practical reference for LLM-driven knowledge graph construction.
