With the progress in chemo-biological imaging technology, accurate molecular site segmentation and ligand detection with rare data has become an essential mission in drug screening, protein engineering, and early-stage disease detection. Traditional deep networks require extensive annotated data and fail to generalize well with multiple modalities jointly. In this work, we present the Few-shot Multimodal Chemo-Biological Imaging Framework (CMA-FSL), which combines chemical mass spectrometry and biological microscopy by cross-modal attention and adopts metric-based prototypical learning to rapidly learn with only a few data points. Experiment results on the ChemoBio-FS dataset show that our model outperforms state-of-the-art methods in terms of Dice score, IoU score, and Top-1 accuracy with more than 6% improvement in 5-way 5-shot evaluation settings, with results of 82.4%, 76.8%, and 86.9% respectively, validating the practicability and efficacy of multimodal learning in chemo-biological imaging with only a few data points, and opening an new thought and paradigm on small sample molecular diagnostic and intelligence drug discoveries.

In response to the dual carbon goals, industrial parks, as the main force of energy consumption, accelerating the substitution of green electricity is the key to emission reduction. However, the two-way fluctuations in the supply and demand of green electricity make it more difficult to predict the gap. The uncertainty of supply and demand makes it hard for traditional experience-based dispatching to accurately match supply and demand, which may lead to the abandonment of green electricity due to excess or the reliance on thermal power for supplementation. This not only affects the emission reduction effect but also increases energy consumption costs. Therefore, there is an urgent need for high-precision green power supply and demand gap prediction methods to support dispatching decisions. This paper proposes the DE-Transformer-BiLSTM regression algorithm. Firstly, correlation analysis and violin plot analysis are carried out, and then it is compared with various machine learning algorithms such as tree models, neural networks, linear regression, SVR and decision trees. The results show that the algorithm performs better overall in terms of mean square error, root mean square error, mean absolute error, mean absolute percentage error and coefficient of determination, providing effective technical support for industrial parks to precisely schedule the supply and demand of green electricity, improve the utilization efficiency of green electricity, reduce energy costs and promote the implementation of the dual carbon goals.

Fire-resistant oil boom is a special equipment used for emergency response to marine oil spill accidents. Its core function is to intercept floating oil while resisting high-temperature flames, preventing the spread of fire and oil pollution, and ensuring marine environmental safety. To verify the fire resistance performance of fire-resistant oil booms in actual fire environments, it is necessary to conduct continuous fire resistance tests to evaluate their structural integrity, thermal insulation efficiency, and flame retardancy. Based on standard fire resistance test requirements, this study designed and built a land-based water tank simulation test environment. The test site layout, flame loading method, temperature monitoring point arrangement, and data collection method were elaborated in detail, and the deformation, ablation, and failure processes of the oil boom under high-temperature combustion were systematically recorded. The test results show that the fire-resistant oil boom can still maintain key performance indicators in line with specification requirements under long-term flame action, verifying its fire resistance reliability. This study realizes the fire resistance test of fire-resistant oil booms under land-based water tank conditions for the first time, solving the problems of high cost and uncontrollability of marine tests. Meanwhile, through multi-parameter data monitoring, it provides data support for material optimization and failure mechanism analysis of fire-resistant oil booms, which has important reference value for improving marine oil spill fire emergency equipment.

The global energy transition process is continuously accelerating. As a core pillar of clean, low-carbon and renewable energy, the installed capacity and operation scale of wind power equipment based on machine learning algorithms are steadily increasing. The prediction of the remaining service life of wind turbine gearboxes is crucial for the safe operation and maintenance of equipment. However, existing machine learning algorithms generally have problems such as feature redundancy, which limits the generalization performance of the model, and insufficient accuracy in capturing complex degradation trends. To enhance the prediction effect, this paper proposes the FVIM-XGBoost regression algorithm. Firstly, the features are optimized through correlation analysis, and then comparative experiments are conducted with GBDT, ExtraTrees, random forest, CatBoost, decision tree and BP neural network. The results show that the proposed model has the best comprehensive prediction performance. Its coefficient of determination R² reaches 0.947, which is significantly higher than that of other comparison models, and the fitting effect is the best. The mean square error of 1855.454, the root mean square error of 43.075, and the mean absolute error of 29.958 are all lower than those of the other models, and the prediction accuracy is better. Only the mean absolute percentage error of 62.113 is slightly higher than that of ExtraTrees, GBDT and BP neural networks. This algorithm provides a more reliable prediction scheme for the remaining service life of wind power gearboxes, which is of great practical significance for ensuring the stable operation of wind power equipment, reducing operation and maintenance costs, and promoting global energy transformation and low-carbon development. High-precision prediction of remaining service life

Urban air pollution has evolved into one of the most severe environmental problems in Asia, driven by rapid industrialization, urbanization and complex climate interactions. This study is a synthesis of the spatiotemporal patterns, driving forces and governing responses of air quality in major Asian cities. Distinct interannual and seasonal trends were identified: air quality is improving in East Asia, stagnating in South Asia and fluctuating in Southeast Asia; pollution peaks in dry or winter months and eases in wet or summer seasons. These variations arise from the combined effects of emissions intensity, meteorological dynamics, and regional climate regimes of different regions. Socioeconomic factors such as energy structure, land-use change and urban morphology influence local patterns of pollutant production and exposure inequalities. Despite the continued implementation of policies aimed at improving air quality, persistent ozone pollution and transboundary haze exposure highlight deficiencies in co-governance. Improving air quality will ultimately depend on greater cooperation between the Asian cities and regions in the 2030 agenda, synergistic PM₂.₅-O₃ control interactions, optimized monitoring networks, and more inclusive public participation. This review, drawing on 577 studies provides a detailed overview of how Asian megacities have changed, the mechanistic and management processes at play. It provides insights into designing multi-pollutant management approaches.

The pore structure of early freezing cement mortar was tested by mercury intrusion porosimetry. The pore size distribution and compressive strength of mortar with different water-cement ratio, curing period, age and temperature were studied. The effects of pore size distribution on the compressive strength with early freezing conditions were discussed. The results showed that both the short-term strength loss and the long-term strength loss were not serious in the negative temperature environment, and the negative temperature made the pore of 10-100nm increased, while reducing the 100-2000nm; The pore above 2000nm had little effect on the compressive strength and the pore of 10-2000nm played a major role in the effect of compressive strength, besides, the pore of 100-2000nm affected the long-term strength growth; Curing period affected the pore above 2000nm, the shorter the curing time, the higher the porosity in this range, and superplasticizer could significantly increase the pore above 2000nm.

Grapevine trunk diseases in subtropical climates show complex patterns of multi-pathogen co-infection and spatial clustering, while current diagnosis still relies mainly on expert judgement with limited quantification and functional testing. This study investigated an 18-acre vineyard in south-eastern Queensland and used 7,440 vine records from 744 plots to build quantitative indices for symptoms and cross-section necrosis, followed by comprehensive characterisation of 46 fungal isolates through isolation, microscopy, physiological assays and greenhouse pathogenicity tests. Analyses identified three spatial disease regions, with wedge- and semi-ring-shaped necrosis strongly enriched in high-disease plots, and showed that Botryosphaeriaceae and Phomopsis groups dominated the pathogen community and had much higher composite pathogenicity indices than other fungi. Even without molecular data, the integrated pipeline of disease quantification, microscopic and physiological traits, pathogenicity testing and computational analysis allowed robust identification of dominant pathogen combinations in a subtropical vineyard and provided a methodological basis for regional risk assessment and targeted management.

A zinc-containing metal-organic framework, formulated as [Zn (IPA)(tatrz)0.5(H2O)], was successfully constructed via a mixed-ligand strategy employing isophthalic acid (H2IPA) and an anthracene-functionalized triazole ligand (tatrz). Solid-state fluorescence spectroscopy reveals a distinct emission peak at 525 nm for the synthesized Zn‑MOF. Leveraging this pronounced luminescence, the material was engineered as a highly efficient dual-responsive fluorescent sensor capable of selective and sensitive detection toward Fe3+and Cr2O72-ions. The sensor demonstrates high sensitivity and a low detection limit, and its excellent selectivity in complex matrices was confirmed through systematic anti‑interference experiments. Mechanistic investigation indicates that the fluorescence quenching response originates primarily from an inner filter effect. In summary, the Zn‑MOF material shows promising potential as a high‑performance fluorescence sensing platform for monitoring environmental pollutants.

Aiming at the scaling problem of oilfield gathering and transportation pipelines, this paper conducts a systematic study through experiments and modeling. Orthogonal experiments are used to analyze the effects of temperature, pressure, flow rate and ion concentration on scaling rate, and the formation mechanism of scaling substances is explored. On this basis, a BP neural network prediction model optimized by the Chinese Pangolin Optimization (CPO) algorithm is established to realize nonlinear modeling and trend prediction of scaling rate. The results show that temperature, pressure and flow rate are the main controlling factors of scaling rate. The prediction error of the CPO-BP model is less than 15%, which can effectively predict the scaling trend. This study provides a theoretical basis for pipeline scaling prevention and control as well as operation optimization, and has broad application prospects.

Instances wherein energy storage systems are configuroid with rational precision and operated according to rigorously defined parameters,distinct phenomena concerning the accommodation of surplus renewable generation emerge. Absorbed may be the excess power output from renewables—fluctuation attenuation in system delivery is thus realized. Enhanced becomes the stability intrinsic to supplied electrical streams, while discrepancies observed between peak demand intervals and demand minima find themselves mitigated with greater efficacy by virtue of these storage implementations. Discernible from such scenarios is a critical function fulfilled by storage apparatus, these units assuming a centralizing role in microgrid integrity preservation throughout disruptions unanticipated in their arrival. Isolated operational states, resultant from faults whose anticipation eludes observers, frequently affect microgrids endowed with considerable renewable capacity; here, battery arrays maintained both judiciously and adaptively ascend to pivotal importance as auxiliary stabilizers under these conditions. Firstly, methodological formulations corresponding to battery cycle life alongside patterns of degrading capacity are constructed through mathematical description. Of no lesser significance is the subsequent optimization pertaining to the size and arrangement of storage systems enabling autonomous, temporally-bounded power supply for designated local loads. Lastly, adaptive switching among several operational modes for time-constrained battery storage discharge emerges as a subject necessitating careful algorithmic articulation—these transitions being tailored for demands unique to specific microgrid segments requiring limited-duration autonomy.