Explore the vast range of titles available.

In recent years, machine learning, especially deep learning, has developed rapidly and has shown remarkable performance in many tasks of the smart grid field. The representation ability of machine learning algorithms is greatly improved, but with the increase of model complexity, the interpretability of machine learning algorithms is worse. The smart grid is a critical infrastructure area, so machine learning models involving it must be interpretable in order to increase user trust and improve system reliability. Unfortunately, the black-box nature of most machine learning models remains unresolved, and many decisions of intelligent systems still lack explanation. In this paper, we elaborate on the definition, motivations, properties, and classification of interpretability. In addition, we review the relevant literature addressing interpretability for smart grid applications. Finally, we discuss the future research directions of interpretable machine learning in the smart grid.

The variability of renewable energy sources presents major challenges for accurately evaluating the maximum dispatchable capacity of the Virtual Power Plant (VPP). This study proposes a scenario-driven framework to assess the maximum dispatchable capacity of a VPP under combined wind, solar, gas, and storage. First, a hybrid deep learning model combining Adaptive Graph Convolutional Networks (AGCN), Convolutional Neural Networks (CNN), and Long Short-Term Memory (LSTM) is used to forecast short-term wind speed and solar irradiance. Load uncertainty is modeled by applying random perturbations to a typical winter daily profile. Second, the forecast results are used to construct a probabilistic ensemble of source–load trajectories, which is statistically reduced to a compact set of representative scenarios while preserving the key temporal variability of renewable generation and its correlation with demand. A multi-scenario stochastic optimization model is then used to evaluate dispatch feasibility across all reduced scenarios. Finally, a binary search strategy combined with feasibility screening is employed to determine the maximum dispatchable capacity that can be reliably committed across all uncertainty conditions. Simulation results confirm the effectiveness of the proposed method in supporting reliable, economically feasible capacity planning for the VPP under uncertainty.

Prostaglandin E2 (PGE2) plays an important role in vascular homeostasis. Its receptor, E-prostanoid receptor 4 (EP4) is essential for physiological remodeling of the ductus arteriosus (DA). However, the role of EP4 in pathological vascular remodeling remains largely unknown. We found that chronic angiotensin II (AngII) infusion of mice with vascular smooth muscle cell (VSMC)-specific EP4 gene knockout (VSMC-EP4−/−) frequently developed aortic dissection (AD) with severe elastic fiber degradation and VSMC dedifferentiation. AngII-infused VSMC-EP4−/− mice also displayed more profound vascular inflammation with increased monocyte chemoattractant protein-1 (MCP-1) expression, macrophage infiltration, matrix metalloproteinase-2 and -9 (MMP2/9) levels, NADPH oxidase 1 (NOX1) activity, and reactive oxygen species production. In addition, VSMC-EP4−/− mice exhibited higher blood pressure under basal and AngII-infused conditions. Ex vivo and in vitro studies further revealed that VSMC-specific EP4 gene deficiency significantly increased AngII-elicited vasoconstriction of the mesenteric artery, likely by stimulating intracellular calcium release in VSMCs. Furthermore, EP4 gene ablation and EP4 blockade in cultured VSMCs were associated with a significant increase in MCP-1 and NOX1 expression and a marked reduction in α-SM actin (α-SMA), SM22α, and SM differentiation marker genes myosin heavy chain (SMMHC) levels and serum response factor (SRF) transcriptional activity. To summarize, the present study demonstrates that VSMC EP4 is critical for vascular homeostasis, and its dysfunction exacerbates AngII-induced pathological vascular remodeling. EP4 may therefore represent a potential therapeutic target for the treatment of AD.

Background Mumps remains a major public health challenge in China, exhibiting distinct seasonal peaks in spring and notable spatial heterogeneity in incidence patterns. These spatiotemporal characteristics necessitate advanced analytical methods to identify driving factors and inform targeted intervention strategies. Methods We integrated space-time scanning statistics and geographically and temporally weighted regression (GTWR) to analyze mumps incidence across China (2005–2020). This approach overcomes the limitations of traditional methods by simultaneously assessing economic development, education level, population structure, and healthcare resources factors. Results National incidence exhibited a fluctuating decline from 27.60 (2005) to 10.09 per 100,000 (2020), peaking in 2012 (38.49 per 100,000). Space-time scanning identified persistent high-risk clusters in western China and transient clusters in northeastern regions. GTWR modeling revealed significant spatiotemporal variations in risk factors: illiteracy rate and population density showed transitioning impacts reflecting improved health education, while household size effects strengthened, emphasizing close-contact transmission. Healthcare resources exhibited opposing effects, being protective in eastern regions but risk-enhancing in western areas. GDP per capita demonstrated protective effects in western and southeastern China but was associated with elevated risk elsewhere. Conclusions The findings underscore the need for regionally tailored prevention strategies and precision interventions accounting for local socioeconomic contexts. This study provides a methodological framework for spatiotemporal disease surveillance and evidence-based policy-making to reduce mumps transmission in China.

The widely distributed “Step-type” landslides in the Three Gorges Reservoir (TGR) area have caused serious casualties and heavy economic losses. The prediction research of landslide displacement will be beneficial to the establishment of local geological hazard early warning systems for the realization of scientific disaster prevention and mitigation. However, the number of observed data like landslide displacement, rainfall, and reservoir water level in this area is very small, which results in difficulties for the training of advanced deep learning model to obtain more accurate prediction results. To solve the above problems, a Two-stage Combined Deep Learning Dynamic Prediction Model (TC-DLDPM) for predicting the typical “Step-type” landslides in the TGR area under the condition of small samples is proposed. The establishment process of this method is as follows: (1) the Dynamic Time warping (DTW) method is used to enhance the small samples of cumulative displacement data obtained by the Global Positioning System (GPS); (2) A Difference Decomposition Method (DDM) based on sequence difference is proposed, which decomposes the cumulative displacement into trend displacement and periodic displacement, and then the cubic polynomial fitting method is used to predict the trend displacement; (3) the periodic displacement component is predicted by the proposed TC-DLDPM model combined with external environmental factors such as rainfall and reservoir water level. The TC-DLDPM model combines the advantages of Convolutional Neural Network (CNN), Attention mechanism, and Long Short-term Memory network (LSTM) to carry out two-stage learning and parameter transfer, which can effectively realize the construction of a deep learning model for high-precision under the condition of small samples. A variety of advanced prediction models are compared with the TC-DLDPM model, and it is verified that the proposed method can accurately predict landslide displacement, especially in the case of drastic changes in external factors. The TC-DLDPM model can capture the spatio-temporal characteristics and dynamic evolution characteristics of landslide displacement, reduce the complexity of the model, and the number of model training calculations. Therefore, it provides a better solution and exploration idea for the prediction of landslide displacement under the condition of small samples.

The increasing integration of weather-dependent renewable energy sources into Virtual Power Plants (VPPs) introduces significant uncertainty in short-term dispatch planning. This paper develops a comprehensive decision-making framework that jointly optimizes credible capacity allocation and operational dispatch under forecast uncertainty. We first compare three probabilistic forecasting methods—Bayesian Neural Networks (BNN), Quantile Regression Forests (QRF), and Gradient Boosted Decision Trees (GBDT)—to quantify wind and solar variability, using metrics such as root mean square error (RMSE), continuous ranked probability score (CRPS), and empirical coverage. BNN is selected as the primary forecasting tool due to its superior calibration and robustness across both resource types. A distributionally robust optimization (DRO) model is then formulated using a Wasserstein ambiguity set and a Conditional Value-at-Risk (CVaR) objective to hedge against worst-case renewable output scenarios. Empirical data from a stylized VPP system comprising 340 kW of installed renewables and urban mixed loads is used to evaluate the framework. Results indicate that the proposed DRO model reduces expected shortfall by up to 78% compared to deterministic baselines, and outperforms quantile-based models in both cost consistency and energy-not-supplied metrics. Scenario-based dispatch simulations reveal that increasing the CVaR confidence level from 90 to 99% improves system reliability from 95.1 to 99.7%, albeit with a 5.7% decline in expected profit. The analysis also quantifies the relative contribution of wind, solar, and load forecast errors to overall dispatch uncertainty. This work highlights the value of integrated probabilistic modelling and risk-aware optimization in enabling reliable and economically efficient VPP operations.

Spermiogenesis is considered to be crucial for the production of haploid spermatozoa with normal morphology, structure and function, but the mechanisms underlying this process remain largely unclear. Here, we demonstrate that SPEM family member 2 ( Spem2 ), as a novel testis-enriched gene, is essential for spermiogenesis and male fertility. Spem2 is predominantly expressed in the haploid male germ cells and is highly conserved across mammals. Mice deficient for Spem2 develop male infertility associated with spermiogenesis impairment. Specifically, the insufficient sperm individualization, failure of excess cytoplasm shedding, and defects in acrosome formation are evident in Spem2 -null sperm. Sperm counts and motility are also significantly reduced compared to controls. In vivo fertilization assays have shown that Spem2 -null sperm are unable to fertilize oocytes, possibly due to their impaired ability to migrate from the uterus into the oviduct. However, the infertility of Spem2 −/− males cannot be rescued by in vitro fertilization, suggesting that defective sperm–egg interaction may also be a contributing factor. Furthermore, SPEM2 is detected to interact with ZPBP, PRSS21, PRSS54, PRSS55, ADAM2 and ADAM3 and is also required for their processing and maturation in epididymal sperm. Our findings establish SPEM2 as an essential regulator of spermiogenesis and fertilization in mice, possibly in mammals including humans. Understanding the molecular role of SPEM2 could provide new insights into future therapeutic treatment of human male infertility and development of non-hormonal male contraceptives.

Accurate wind power forecasting is essential for grid stability and energy market efficiency, yet traditional prediction methods often neglect the relative ordering and temporal consistency of outputs—factors critical for ranking-based decisions in grid dispatch, bidding, and reserve management. To address these shortcomings, this paper introduces a novel wind power forecasting framework that embeds ranking consistency and temporal smoothness directly into the learning objective. The proposed model employs a composite multi-objective loss that simultaneously minimizes point-wise prediction errors, maximizes rank alignment across forecasted values, and enforces temporal rank regularization to avoid instability in ordered outputs. A deep neural architecture based on attention mechanisms is trained end-to-end using historical wind speed, direction, turbulence, and meteorological covariates as inputs. To validate the model, we construct a high-resolution dataset comprising 12 wind farms over 24 months with synchronized SCADA, meteorological, and geographic information. Multiple wind regimes—including low, ramping, and saturation scenarios—are explicitly labeled to facilitate regime-aware evaluation. Extensive numerical experiments demonstrate that the proposed model outperforms baseline methods such as LSTM, Transformer, and LambdaMART in terms of MAE, RMSE, and normalized discounted cumulative gain (NDCG), particularly under high-fluctuation regimes. Moreover, we introduce a Temporal Rank Stability Index (TRSI) to quantify the consistency of ordinal outputs across time, with our model achieving up to 35% improvement over state-of-the-art alternatives. This study offers three core contributions: (1) a theoretically grounded multi-objective loss for ranking-aware and temporally robust wind forecasting, (2) a novel wind regime-labeled dataset supporting both prediction and ranking evaluation, and (3) a suite of visualization tools and metrics that reveal deeper dynamics in ordinal wind forecasting tasks. The results suggest new directions for learning-to-rank in renewable energy forecasting and demonstrate the practical feasibility of incorporating rank-sensitive intelligence into grid-scale forecasting pipelines.

Climate changes influence lake hydrodynamics and radiation levels and thus may affect the fate and transport of waterborne pathogens in lakes. This study examines the impact of climate change on the fate, transport, and associated risks of four waterborne viruses in Lake Geneva. We used a coupled water quality‐microbial risk assessment model to estimate virus concentrations and associated risks to recreational water users for each month in 2019 and 2060. Long‐term hydrodynamic simulations suggested that although the annual hydrodynamic transport pattern of Lake Geneva will remain relatively stable, a 1.9°C increase of lake surface water temperature can be expected, while a slight decrease in lake current velocity may occur. The subsequent effect on the fate and transport of the four enteric viruses was found to vary by time of year. During warmer periods, the increase of virus inactivation due to higher water temperature and stronger solar radiation at the earth's surface will compensate for the additional virus discharge brought about by population growth over the time period considered, whereas during winter the virus concentration near the lake shore and the associated infection probabilities risks are likely to increase due to population growth. Additionally, the current estimation of virus inactivation rate shows significant variability, which has a more substantial effect on enteric virus concentrations in the lake compared with changing climate parameters. Overall, the study suggests that future risks posed by enteric viruses with recreational water users near popular beaches around Lake Geneva will likely remain similar to current risks and accurate estimation of the environmental inactivation of viruses is crucial for predicting the fate of enteric viruses in the aquatic system. Plain Language Summary This study investigates the impact of climate change on the fate, transport, and associated risks of four waterborne viruses in Lake Geneva, Switzerland, using a coupled water quality‐microbial risk assessment model. The results indicate that the influence of changing environmental conditions on the fate and transport of enteric viruses varies by time of year. Additionally, the current estimation of virus inactivation rate shows significant variability, which has a more substantial effect on enteric virus concentrations in the lake compared with changing climate parameters. Overall, the study suggests that the risks posed by enteric viruses with recreational water users near popular beaches around Lake Geneva in 2060 will likely remain similar to current risks. However, accurate estimation of the environmental inactivation of viruses is crucial for predicting the fate of enteric viruses in aquatic systems in the future. Key Points Climate change affects lake hydrodynamics as well as fate and transport of waterborne pathogens in Lake Geneva Enhanced inactivation due to higher water temperature and solar radiation compensates for increasing viral loads due to population growth Infection risks to recreational water users in Lake Geneva in 2060 will likely be similar to the present situation

As a major source of carbon emissions, the carbon-based power generation industry requires a scientifically robust environmental performance evaluation system to facilitate its green transition and sustainable development. Focusing on unique transition dynamics across four carbon-based power generation formats, this study compares environmental dimension indicators across typical ESG evaluation frameworks and proposes an innovative evaluation index model of environmental performance based on common metrics, with a particular emphasis on their contribution potential to the “Dual Carbon Goals”. The framework’s core innovation lies in its Dual Carbon-focused indicator system, which evaluates three critical indicators overlooked by mainstream ESG methodologies. It extends to include upstream/downstream processes, addressing gaps in current evaluation systems. The findings reveal that core environmental issues, such as climate change, pollution emissions, and resource utilization, exhibit broad commonality in ESG evaluations. Among the assessed indicators, carbon emission intensity carries the highest weight, underscoring its centrality in each power generation sector’s efforts to align with the Dual Carbon Goals. Furthermore, the analysis demonstrates that underground coal gasification combined cycle power generation has a relatively favorable environmental performance, ranking slightly below natural gas combined cycle but above shale gas combined cycle power generation. In contrast, traditional coal-fired power generation exhibits significantly poorer environmental outcomes, highlighting both the efficacy of technological upgrades in reducing emissions and the urgent need for transitioning away from conventional coal-based power.