Search Results (143)

The carbon emission allowance (CEA) market is a complex socio-technical and environmental-management system in which regulatory design, trading activity, liquidity conditions, and price volatility interact dynamically. Accurate systems-level tail-risk forecasting and early warning remain challenging because carbon-market losses are affected by nonlinear dependence, episodic liquidity stress, and time-varying volatility. This study proposes an Interpretable Quantile Temporal Network (IQTN) as a systems-oriented risk-monitoring framework for China’s national CEA market. By integrating a feature-gating mechanism, a causal temporal convolutional encoder, and a non-crossing quantile output layer, IQTN directly models the conditional tail distribution of future carbon-market losses. The framework produces multi-horizon Value-at-Risk (VaR) and Conditional Value-at-Risk (CVaR) forecasts for 1-day, 5-day, and 10-day horizons and converts predicted tail risk into operational early-warning signals. Compared with historical simulation, EWMA, GARCH-type models, machine-learning quantile models, and deep temporal benchmarks, IQTN achieved the lowest 95% VaR pinball loss across all horizons, with values of 0.1765, 0.3958, and 0.5732. VaR backtesting showed empirical exceedance rates of 5.23%, 6.04%, and 6.94%, closest to the nominal 5% level. Interpretability analysis identified rolling volatility, maximum loss, intraday range, trading value, and illiquidity as key risk drivers. The temporal importance results also show that recent observations dominated the risk forecasts, suggesting that the risk state of the CEA market is highly sensitive to short-term market information. This supports the use of a short-horizon temporal network as a systems-oriented tool for carbon-market tail-risk monitoring and early warning. Full article

The European Common Agricultural Policy (CAP) commits, in its Treaty foundation, to a fair standard of living for the agricultural community and, in its post-2014 architecture, to enhanced territorial cohesion. Yet repeated reform cycles have left the regional concentration of payments in many Member States visibly untouched. This paper asks why. We document the persistence of the territorial concentration of CAP transfers across the 13 Greek NUTS-2 regions over the 2010–2025 period (€47.65 bn cumulative), identify the CAP design mechanisms that mechanically reproduce it, and quantify how much of the observed aggregate stationarity is the artefact of compositional shifts versus genuinely offsetting forces. Using the universe of payment disbursements aggregated to 13 NUTS-2 regions and 51 NUTS-3 prefectures, we (i) test for σ- and β-convergence and Lorenz dominance, (ii) decompose Theil-T between and within regions and across Pillar I/Pillar II, and (iii) run four counterfactual simulations: Pillar II share held at its 2010 level, Article: 17-style capping at a 12–15% NUTS-2 ceiling, an Article: 29-style lower-tail floor, and a concentration-elasticity perturbation of the top region. The territorial distribution of support proves strikingly stable: standard inequality measures stay within a narrow band for sixteen consecutive years, and the ranking of regions barely changes, so formal convergence tests detect no narrowing over time. Three messages follow. First, this persistence is not accidental but built into the architecture of the CAP—through historical-reference entitlement values, the per-hectare logic of the Basic Payment Scheme, the geographic concentration of coupled support in cotton and livestock, and the cadastral fragmentation of the island prefectures. Second, the apparent stability conceals two large and opposing forces: the post-2014 expansion of Pillar II has reduced regional disparities, while a widening of the Pillar I distribution has increased them by almost the same amount, so aggregate stationarity reflects policy effort cancelling out, not the absence of it. Third, the instruments already in the CAP toolbox have real redistributive power: capping the largest region’s envelope and redistributing the surplus to lagging regions, or introducing a lower-tail floor, would roughly halve measured inequality. Therefore, the spatial concentration of CAP transfers in Greece is a designed equilibrium rather than an unsolved residual, and reducing it requires instruments that act asymmetrically on the top of the distribution. Full article

Highway construction projects face interacting risks that affect time, cost, regulatory compliance, and delivery resilience, all of which are closely linked to sustainable infrastructure development. This study develops a hybrid decision-analytical and machine learning framework for sustainability-oriented risk assessment in highway construction under limited-data conditions. The framework combines (i) the Analytic Hierarchy Process (AHP) and tabular Generative Adversarial Networks (GANs) to structure and stress-test expert judgement, and (ii) Probability-Impact (P-I) scoring with a Bayesian Networks (BNs) to model dependencies and derive posterior weights for probability of occurrence, impact on time, and impact on cost across four headline risk factors: weather-related risks, lack of labour, design-related risks, and permitting/regulatory risks. AHP provides transparent and auditable priorities with consistency checks, while GAN-generated synthetic tables support diagnostics for central tendency (P50) and tail behaviour (P90) under data scarcity. The calibrated P-I scores parameterise BN conditional probability tables, enabling the updating of BN scores; and factor-level decomposition of expected contributions. The framework produces model-ready posterior weights that support early planning, contingency allocation, mitigation prioritization, scenario analysis, and subsequent simulation and optimization studies. In sustainability terms, the proposed approach helps project teams improve climate resilience, strengthen regulatory and environmental preparedness, and reduce inefficient use of time, cost, and project resources in data-constrained settings. The results show that permitting/regulatory risks have the highest contribution to probability of occurrence and time impact, while weather-related risks exert the greatest cost impact. The framework therefore offers a practical tool for supporting more resilient, transparent, and sustainable highway project delivery when large historical datasets or questionnaire surveys are unavailable. Full article

High-frequency FY-4B aerosol optical depth (AOD) observations provide useful spatiotemporal constraints for dust nowcasting, but their application over bright deserts is limited by retrieval gaps and high-AOD uncertainty. This study develops a physics-informed spatiotemporal learning framework for 15–60 min FY-4B AOD nowcasting over the Taklimakan Desert. Historical FY-4B AOD, valid masks, ERA5 dynamic fields, model-level diagnostics, and surface constraints are organized on a unified 48 × 64 grid. An LSTM–TCN–Transformer temporal backbone is combined with spatial-context encoding, mask-aware observation encoding, and structured source–transport prediction heads to represent both temporal evolution and spatial plume structures. A physics encoder represents boundary-layer mixing, vertical wind shear, source-region emission, upwind transport, and deposition loss. Mask-aware encoding and structured prediction heads are used to handle missing retrievals, source and transport increments, high-AOD tails, and low-confidence regions. Results show that FY-4B AOD constrains the main dust-belt position and spatial extent within 1 h, with skill decreasing from 15 to 60 min. High-coverage samples show more stable spatial structures, whereas low-coverage and extreme high-AOD cases have larger peak underestimation and boundary errors. The proposed framework improves high-AOD event detection and spatial-structure preservation compared with persistence, advective persistence, ConvLSTM, and ST-UNet baselines. An additional case-based comparison with MODIS MAIAC AOD and MERRA-2 dust optical depth shows partial spatial colocation between predicted high-value footprints and independent aerosol-enhancement references; however, the reported skill scores should still be interpreted mainly as spatiotemporal consistency with the FY-4B AOD product field rather than direct validation of true atmospheric dust loading. Full article

This study investigates the electrical properties of gold mine tailings from the Soweto mining region to assess their potential as a low-cost and sustainable backfill material for grounding systems. Samples were collected from historical mine dumps, oven-dried at 70 °C for 24 h to determine dry density and baseline moisture content, and reconstituted to controlled moisture levels of 5–25% by mass. Bulk electrical resistivity was measured using the Wenner four-electrode method in accordance with ASTM G57-06. The results reveal a strong inverse correlation between moisture content and resistivity. At low moisture content (≈5%), resistivity exceeded measurable limits, indicating poor ionic conduction, whereas increasing moisture content led to a substantial reduction in resistivity, reaching an average value of approximately 10 Ω at 25% moisture due to improved pore water continuity and ionic mobility. These findings demonstrate that moisture-conditioned gold mine tailings can achieve electrical performance comparable to that of conventional grounding enhancement materials while offering notable economic and environmental benefits. Owing to their local availability and waste re-utilisation potential, the tailings present a technically feasible and environmentally responsible solution for improving earthing performance in high-resistivity soils. Further work should examine long-term field performance, corrosion effects, and leaching behaviour. Full article

The switch in land use of abandoned tailings can precondition their reuse as newly built parks. This study investigated the feasibility of reusing a remediated mercury (Hg) retorting site in Wanshan, Guizhou Province, China, as a functional urban park by assessing residual heavy metal risks and associated vegetation responses. Field investigations were conducted across 31 park sites distributed along an east–west geographical gradient from the former mining area to urban parks, using replicated plots to sample the surface soils and dominant plant species. The concentrations of arsenic (As), cadmium (Cd), mercury (Hg), manganese (Mn), and lead (Pb) in soil and plant tissues were quantified using inductively coupled plasma–mass spectrometry, and vegetation structure and diversity were evaluated using standard community indices. The results showed significant spatial variability in soil and plant metal concentrations, with higher levels generally observed near historically impacted areas of the mine. However, all soil metal concentrations were below the national safety thresholds. Plant tissues exhibit controlled metal accumulation within normal or regulated ranges, reflecting the effective screening of tolerant and hyperaccumulating species. Increasing heavy metal concentrations were associated with reduced vegetation coverage, height, and diversity along the gradient. Overall, the findings indicate that the reclaimed Hg retorting site almost met ecological safety requirements, but more data on deep soils, groundwater, and long-term observations are needed to draw more conclusive conclusions. Full article

Solitary fibrous tumor/hemangiopericytoma (SFT/HPC) of the central nervous system is a rare mesenchymal neoplasm with a propensity for late recurrence and distant metastasis. Pancreatic metastasis from intracranial SFT/HPC is exceptionally uncommon and may mimic primary pancreatic neoplasms, particularly pancreatic neuroendocrine tumor (PanNET). We report a 52-year-old man with a documented history of recurrent intracranial SFT/HPC, historically diagnosed as hemangiopericytoma, who developed a hypervascular pancreatic tail lesion 11 years after the initial intracranial tumor diagnosis. Contrast-enhanced imaging and endoscopic ultrasound-guided fine-needle aspiration initially suggested a primary pancreatic neoplasm, including solid pseudopapillary neoplasm or PanNET, and a definitive preoperative diagnosis could not be established. Following laparoscopic resection, histopathological examination revealed a spindle-cell tumor with a rich vascular pattern. Immunohistochemistry documented STAT6 positivity, together with vimentin and Bcl-2 positivity, supporting the diagnosis of pancreatic metastasis from SFT/HPC. The patient later developed unresectable recurrent pancreatic disease and underwent stereotactic radiotherapy, showing radiological disease control at follow-up. This case highlights that pancreatic metastasis from intracranial SFT/HPC, although extremely rare, may occur after a prolonged latency period and mimic a hypervascular primary pancreatic neoplasm. In patients with a history of intracranial SFT/HPC, late metastatic disease should be considered, and definitive diagnosis relies on histopathological examination and targeted immunohistochemistry. Full article

Accurate tail-risk measurement in carbon markets is challenging because carbon allowance prices are shaped not only by heavy-tailed return dynamics, but also by policy changes that can alter the underlying risk dynamics. Models that ignore such structural shifts may perform reasonably well in normal periods while still understating downside risk when market conditions change. To address this issue, this paper proposes a break-regime generalized autoregressive score model with Student-t innovations, denoted as BR-GAS-t, for one-step-ahead forecasting of Value-at-Risk and Expected Shortfall. Using daily spot data from China’s carbon market, we compare BR-GAS-t with historical simulation, GARCH-N, GARCH-t, and regime-free GAS-t benchmarks. The results show that carbon returns are strongly heavy-tailed and that the post-break regime is characterized by stronger shock sensitivity, lower persistence, and a higher long-run conditional scale. Out-of-sample evidence further indicates that BR-GAS-t delivers the strongest overall VaR backtesting performance and the lowest average Fissler–Ziegel (FZ) loss in joint VaR–ES evaluation. Its advantage is most pronounced at the 2.5% and 1% tails, where downside risk is hardest to forecast. Robustness checks based on alternative break dates, window lengths, recursive schemes, and distributional assumptions confirm that the main conclusion is stable. The findings suggest that explicitly incorporating observed policy breaks improves tail-risk forecasting in policy-driven carbon markets. Full article

The paradigm transition of the life cycle management of physical assets in the railway sector demands new maintenance models that imply the conventional predictive approaches to be surpassed. This paper proposes an innovative methodology that integrates Building Information Modelling (BIM) with predictive maintenance (PdM) systems to be applied to rolling stock and, in this way, be enhanced by Generative Artificial Intelligence (GenAI). The research focuses on the autonomous synchronisation of the Rolling Stock Digital Twin (DT). Unlike static BIM models, the proposed solution enables the use of GenAI algorithms to process continuous data streams from integrated sensors, allowing the digital model to evolve autonomously as physical wear occurs. In this framework, GenAI (via Generative Adversarial Networks—GANs) is essential for data augmentation, enabling the simulation of rare “long-tail” failure events that are scarce in real-world historical data. By synthesising these degradation scenarios, the model learns complex mechanical collapse patterns that otherwise would be ignored by traditional PdM approaches. GenAI is employed to synthesise degradation scenarios, perform real-time parametric updates within the IFC (Industry Foundation Classes) schema, and optimise maintenance workflows. The application of this framework demonstrates a significant reduction in diagnostic latency and optimises the rolling stock’s operational life cycle by automating updates and reducing the need for manual data entry. This study concludes that the convergence among BIM, PdM, and GenAI establishes a robust framework for railway fleet management. While the current validation focuses on bogie systems using Random Forest and LLMs, it paves the way for a future Industrial Metaverse where immersive diagnostics can be integrated into the maintenance lifecycle. Full article

Dynamic knowledge representation in curved manifolds conventionally relies on integer-order Markovian sequence encoders, intrinsically yielding exponential memory decay. This paradigm fails to model the anomalous diffusion and heavy-tailed historical dependencies inherent in complex evolutionary networks and dense physical environments. This manuscript proposes the Fractional–Temporal Lorentz Graph Convolutional Network (FTL-GCN), formalizing temporal evolution as a continuous fractional geometric flow explicitly defined on the tangent bundle of the Lorentz manifold. Analytical derivations demonstrate that the discrete Grünwald–Letnikov memory kernel establishes a non-exponential, power-law lower bound for historical state retention, preventing topological manifold collapse over extended temporal horizons. Empirical evaluations demonstrate that FTL-GCN achieves competitive forecasting accuracy against the latest 2025–2026 state-of-the-art discrete models within specific temporal windows, while uniquely mitigating predictive degradation by up to 52% in long-horizon dependency stress tests and maintaining sub-millisecond latency for physical control. The architecture is subsequently deployed within an in silico biophysical simulation for autonomous micro–nano robotic navigation in the Tumor Microenvironment (TME). By establishing a physical-mathematical structural analogy—mapping the empirical fractional viscoelasticity of the extracellular matrix to the cognitive network’s fractional derivative order—FTL-GCN sustains continuous-space navigation policies in dense anomalous environments where standard integer-order models experience mechanical slip. Full article

Energy-intensive refrigeration systems require predictive models that remain informative under counterfactual control trajectories, not only on archived operation. This paper develops a control-oriented multi-step state model and a nonlinear model predictive control framework for an indoor ice-rink refrigeration system. Historical state, control, and exogenous variables are encoded jointly with an admissible future control trajectory, and a normalized thermal-balance residual is added to the training objective. A lightweight conditioned transformer predicts ice temperature, return-glycol temperature, supply-glycol temperature, and compressor power over a 30 min horizon. The selected weakly regularized model with regularization coefficient ${\lambda }_{phys}= 0.001$ decreases the normalized thermal-balance root-mean-square error on the horizon tail by 30.29% relative to the base model while increasing the average ice-temperature root-mean-square error by only 1.90%. In a surrogate-based counterfactual four-day evaluation, the resulting nonlinear model predictive controller reduces predicted daily energy by 4.84%, terminal violation share by 17.32%, mean absolute terminal ice-temperature deviation by 18.74%, and the mean objective value by 30.82% relative to historical admissible setpoint tracking. The mean full control cycle time is 0.0311 s, confirming real-time feasibility for a 5 min supervisory update interval. All controller results are surrogate-based rather than field-deployed and therefore represent receding-horizon benchmark results under learned-model evaluation, not realized field savings. Full article

In insurance portfolios, classifying customers without a prior history at a given company is particularly challenging due to the absence of historical behavior, extreme class imbalance, heavy-tailed loss distributions, and strict operational constraints. Traditional machine learning approaches, including the baseline methodology proposed in previous studies, typically optimize global predictive accuracy and therefore fail to capture business-critical outcomes, especially the identification of high-risk clients. This study extends the existing approach by evaluating two complementary business-aware classification strategies: (i) a balanced bagging ensemble specifically designed to handle class imbalance and maximize expected profit under explicit customer-omission constraints, and (ii) a lightweight Transformer-based architecture capable of learning richer feature representations. Both approaches incorporate the asymmetric financial cost structure of insurance and operate under operational selection limits. The empirical analysis is conducted on a proprietary large-scale auto insurance dataset comprising 51,618 customers and is complemented by validation on nine synthetic datasets to assess robustness. Model performance is evaluated using statistical tests (ANOVA, Friedman, and pair-wise comparisons) together with business-oriented metrics. The results show that both proposed approaches consistently outperform the baseline methodology (p < 0.001) in terms of profit, with the ensemble offering a better balance of performance and efficiency, while the Transformer shows stronger robustness and generalization under data perturbations. The balanced ensemble provides the most favourable trade-off between predictive performance, robustness, interpretability, and computational efficiency, making it suitable for deployment in regulated insurance environments, while the Transformer achieves competitive results and exhibits stronger generalization under data perturbations. The proposed approach aligns machine learning with actuarial portfolio optimization by explicitly integrating profit-driven objectives and operational constraints, offering two practical and scalable solutions for risk-based decision-making in real-world insurance settings. Full article

Changes in aviation turbulence at cruise altitudes have important implications for aviation safety under global warming scenarios in the future. Using projections from the NorESM2-MM model within the CMIP6 framework, this study evaluates changes in clear-air turbulence (CAT) at 250 hPa over Southwest China during the twenty-first century based on an ensemble of 15 diagnostic indices. The results show: (1) Historical moderate-or-greater (MOG) CAT peaks in a zonal belt near 30–35° N, with annual frequencies up to 1.6% over the Hengduan and Karakoram Mountains. Future increases remain focused in this belt, are stronger and more extensive under SSP5-8.5, peak in winter and spring, and weaken over much of the Plateau interior in summer. (2) Future changes are intensity-dependent: stronger categories show larger relative increases, and PDF changes are concentrated in the right tail, indicating amplified extreme turbulence. The 19-year moving-average time series shows that MOG-CAT increases by 28.3% and 36.5% under SSP2-4.5 and SSP5-8.5, respectively, by the mid-twenty-first century, and by 26.0% and 69.4% by the late twenty-first century. (3) Along the Chengdu–Lhasa corridor, winter MOG-CAT increases in all three segments. Under SSP5-8.5, median increases are about 50% in the Basin and Plateau segments and about 85% in the Transition segment, with most diagnostics ranging from 50% to 180%. (4) High-emission scenarios are more likely to cause turbulence and instability in the southwestern region, potentially posing greater challenges for aviation turbulence warning and safety assurance. Full article

Strategic bidding for wind–battery hybrid systems is increasingly critical as electricity spot markets transition toward market-oriented mechanisms, particularly in Chinese pilot regions. However, dual uncertainties—wind generation variability and volatile locational marginal prices (LMPs)—expose market participants to significant financial tail risk. This study develops a risk-constrained reinforcement learning framework for optimal bidding of wind–storage hybrid systems. We employ soft actor–critic (SAC) for continuous action control and integrate conditional value-at-risk (CVaR) into reward design to explicitly penalize low-probability, high-loss outcomes. The framework incorporates realistic operational constraints, including linearized battery degradation costs and a market-compatible single-bid abstraction for hourly settlement. Using one-year historical operational data from a 150 MW wind farm (with a 91-day test period), we find that storage integration increases annual profit by 108.4–114.2% relative to wind-only operation. Critically, the SAC–CVaR policy (η = 0.35) preserves 97.3% of risk-neutral profit ($7.71 M vs. $7.93 M) while substantially mitigating downside risk: CVaR@95% improves by 42.4% (−$549 vs. −$952) and VaR@95% improves by 30.1% (−$275 vs. −$393). The trained policy achieves sub-millisecond inference (0.262 ms per decision, ~3820 decisions/s), corresponding to a 3.8 × 10⁴–5.7 × 10⁴× speedup over optimization-based solvers (10–15 s per decision), enabling real-time deployment. Behavioral analysis reveals that the agent learns adaptive, forecast-normalized bidding strategies with more conservative reporting in high-price regimes and counter-cyclical battery dispatch patterns, demonstrating effective coordination between profitability and risk control under volatile market conditions. Full article

Accurate tail risk forecasting in emerging markets is frequently compromised by the nonlinear dynamics and time-varying long memory of high-frequency volatility. In this study, we employ multifractal detrended fluctuation analysis (MF-DFA) to decode the complex market behavior, revealing pronounced multifractality and strong persistence that defy the static assumptions of classical linear models. The multifractal analysis is only used for research motivation and model design, not as input features for the model. To bridge the gap between fractal diagnostics and predictive modeling, we propose an attention-based dynamically reweighted SA-HAR-J-Net framework. This architecture uniquely integrates HAR-style multi-horizon inputs with a bidirectional LSTM (BiLSTM) encoder and a temporal self-attention mechanism. Crucially, the attention module functions as a dynamic reweighting system, allowing the model to adaptively emphasize historical patterns that receive higher attention weights under changing market conditions, thereby mimicking the time-varying correlations inherent in multifractal processes. Furthermore, we incorporate jump proxies and realized higher moments to enhance the capture of extreme tail dynamics. Utilizing a strict expanding-window out-of-sample protocol, the proposed method achieves significantly lower quantile loss and superior calibration relative to established econometric and machine learning benchmarks for Value-at-Risk (VaR) forecasting. This work provides a robust framework for tail risk monitoring by effectively aligning deep learning architectures with the stylized facts of multifractal markets. Full article