Search Results (131)

This paper investigates the impact of Environmental, Social, and Governance (ESG) performance on the financial outcomes of 68 European and 60 U.S. banks over the period 2010–2022 using a Panel Smooth Transition Regression (PSTR) framework. Unlike traditional linear models, the PSTR approach captures the nonlinear, regime-dependent effects of ESG engagement on bank profitability, measured by ROA and ROE, and financial stability, measured by the Z-score. Our empirical findings reveal a critical ESG threshold in both regions, above which banks experience substantial improvements in profitability and resilience. Comparative analysis indicates that while ESG enhances stability slightly more in European banks, U.S. banks tend to achieve marginally higher profitability gains. Control variables, including bank size, capital adequacy, leverage, and macroeconomic conditions, also play a significant role in shaping performance. These results underscore the importance for banks to attain a minimum ESG maturity to fully realize the benefits of sustainable practices. The study provides valuable insights for bank managers, investors, and policymakers seeking to promote a sustainable and resilient banking sector across Europe and the United States. Full article

Sustaining rice productivity under the dual constraints of freshwater scarcity and low-temperature stress represents a pressing challenge for high-latitude japonica rice systems worldwide. There is an urgent need to develop coupled irrigation–agronomic management strategies that jointly safeguard yield stability and water use efficiency (WUE) in cold-region rice production. In this study, a two-year field experiment was conducted in 2024–2025 on albic soil (Albic Luvisols, WRB; θfc 38.2% v/v, pH 5.80, clayey texture with poor permeability and a propensity for subsurface waterlogging) in the Sanjiang Plain, Heilongjiang Province, China (47°15′ N, 133°28′ E), with nine coupled “irrigation regime × auxiliary practice” treatments, comprising conventional continuous flooding, four-level controlled irrigation (CI) at lower thresholds of 60%, 70%, 75%, and 80% θfc, and their combinations with film mulching (FM) or a humic-acid-based soil amendment (SA). An interpretable machine-learning diagnostic framework was developed, with elastic net (EN) as the primary analytical model and random forest (RF) as a nonlinear control, to simultaneously identify core yield predictors and outlier treatments. The principal findings were: (i) The soil-amendment-coupled 75% θfc CI treatment (SACI) increased grain yield by 12.3% and reduced water input by 17.0% relative to conventional continuous flooding, with WUE reaching 1.801 kg m⁻³, a 35.3% gain over the control (p < 0.05); these improvements were consistent across both individual years (year × treatment interaction: p = 0.601; inter-year rank correlation ρ = 0.967). Lowering the CI threshold below 75% θfc significantly reduced grain yield through diminished effective-panicle retention. (ii) Multi-method consensus analysis (Kendall’s W = 0.871, p < 0.01) identified root volume at the milk stage as the most strongly and consistently associated statistical predictor of yield formation, with convergent mechanistic support from independent rhizosphere evidence (Eh, TTC reductive activity). Definitive causal validation awaits isotope-tracing experiments. (iii) The film-mulching × continuous-flooding treatment (FMCG) was diagnosed as a yield-response outlier (permutation test p = 0.003), three in situ rhizosphere measurements (redox potential, root TTC-reducing activity, and rhizosphere temperature) supported the proposed mechanism of hot–anoxic rhizospheric inhibition. Methodologically, this study develops a four-level evidence convergence framework that integrates intra-model self-consistency, cross-model (EN vs. RF) consensus, independent rhizosphere evidence, and distribution-free permutation testing, with Jackknife+ conformal prediction and companion Monte Carlo simulations (1000 replicates) used to quantify the reliability boundaries under small-sample conditions (n = 27). These findings provide an evidence-based irrigation–soil co-management strategy for cold-region rice production in Northeast China, and the proposed diagnostic paradigm offers a generalizable, reliability-quantified methodological template for interpretable small-sample modeling in multifactorial coupled field experiments. Full article

Global supply chains are increasingly exposed to multi-source uncertainties, ranging from geopolitical tensions to climate extremes, making the accurate and interpretable prediction of disruptions an urgent operational priority. Existing predictive models often rely on either shallow statistical learners, which struggle with high-dimensional interactions, or deep neural networks, which trade off interpretability for marginal performance gains. To address this gap, we propose an interpretable machine learning framework that couples a feature-attention mechanism with a gradient-boosted decision tree ensemble for early warning of shipment-level disruption events. First, a dedicated attention module is trained to assign importance weights to 14 heterogeneous risk factors, generating an interpretable feature ranking that highlights pivotal signals such as lead-time volatility and geopolitical risk. The reweighted features are then fed into a gradient boosting classifier, which effectively captures non-linear patterns and interaction effects. Evaluated on a publicly available dataset of 5000 international freight records available on Kaggle, the proposed framework achieves an AUC of 0.8213 (±0.0002 over three independent runs), matching the best-performing baseline (standard gradient boosting, 0.8212 ± 0.0001) and surpassing logistic regression (0.777), random forest (0.806), and a standalone feature-attention network (0.805). The attention module preserves full predictive accuracy while adding an interpretability layer that conventional black-box implementations lack. Notably, the framework preserves the predictive accuracy of gradient boosting while enhancing interpretability through attention-based feature ranking and dual-perspective importance analysis, achieving a precision of 0.770 and a balanced F1-score of 0.781. The convergence of attention-based interpretability and ensemble learning efficiency provides supply chain managers with a transparent decision-support tool—distinguishing genuine “tipping points” from “false alarms” and enabling targeted risk mitigation under deep uncertainty. Full article

Accurate prediction of pavement performance is essential for sustainable pavement management, especially in flood-prone regions where environmental stressors accelerate deterioration. This study develops a machine learning-based comparative framework to evaluate the contributions of baseline pavement condition, maintenance and rehabilitation (M&R) activities, and environmental exposure to predicting changes in Pavement Condition Index (ΔPCI) across 11,214 matched pavement segments in Southeast Texas from 2019 to 2023. Three nested modeling scenarios were evaluated using Linear Regression, Random Forest, and XGBoost, with performance evaluated using R², MAE, and RMSE. Baseline variables alone showed limited predictive capability, whereas adding M&R history produced the largest improvement. Environmental and flood-related variables provided further gains, particularly for nonlinear ensemble models. XGBoost achieved the highest predictive performance in the fully integrated scenario (R² = 0.65, MAE = 10.63, RMSE = 14.02). SHAP analysis identified SDI2019 and PCI2019 as the strongest predictors, while selected M&R and environmental variables also contributed meaningfully. The findings demonstrate that integrating treatment history and environmental exposure substantially improves pavement performance prediction and supports more sustainable, climate-resilient pavement management and helps agencies prioritize maintenance and allocate resources more effectively. Full article

Accurate assessment of carbon storage dynamics and their driving factors is important for ecological sustainability and land management on the Loess Plateau under China’s dual carbon goals. In this study, the InVEST and PLUS models were integrated to evaluate carbon storage changes from 2000 to 2020 and simulate future carbon storage patterns for 2030 under four development scenarios, including natural development (ND), rapid development (RD), cropland protection (CP), and ecological protection (EP). In addition, the XGBoost-SHAP framework was employed to identify the dominant drivers and nonlinear response relationships controlling spatial variation in carbon storage. During 2000–2020, ecosystem carbon storage across the Loess Plateau generally increased, rising from 5.780 Pg to 5.893 Pg. Spatially, carbon storage displayed a pronounced pattern characterized by higher levels in the southeast and lower levels in the northwest, aligning with forest–grassland restoration belts. Scenario simulations showed that EP produced the largest carbon storage gain, with total carbon storage projected to reach 5.962 Pg in 2030. In contrast, RD reduced carbon storage to 5.858 Pg because of intensive construction land expansion. XGBoost-SHAP results identified net primary productivity (NPP) as the most influential factor controlling spatial variation in carbon storage, accounting for 57.3% of the total explanatory importance, whereas soil erosion (SE) exhibited a strong negative effect on carbon storage. Population density (POPD) also exerted a negative effect, whereas gross domestic product (GDP) showed positive contributions in economically developed counties. These findings enhance understanding of the spatial response characteristics of carbon storage under environmental gradients and human disturbance across the Loess Plateau. They further provide scientific support for differentiated ecological management and regionally adapted carbon mitigation planning. Full article

Resource allocation for cognitive Vehicle-to-Everything (V2X) networks is challenging due to dynamic spectrum sharing, strong interference coupling, and stringent latency constraints for safety-critical Vehicle-to-Vehicle (V2V) traffic. Although recent Multi-Agent Reinforcement Learning (MARL) approaches report promising gains, many evaluations are conducted at limited and fixed network scales, which restricts insights into scalability under dense spectrum reuse. This paper investigates cooperative multi-agent learning for interference-aware and deadline-constrained V2X resource management. We propose a Q-value Transformation (QTRAN)-based value decomposition framework under centralized training with decentralized execution (CTDE) for joint resource-block and power allocation among V2V agents. The proposed approach is implemented in a realistic V2V/V2I simulator incorporating Manhattan grid mobility, fast fading, explicit cross-tier and co-channel interference, and per-link payload/deadline dynamics. Beyond communication-level performance, improved timely delivery of V2V safety messages can support cooperative maneuvering, collision avoidance, platooning, and infrastructure-assisted traffic management. Extensive simulations across varying numbers of V2V agents benchmark QTRAN against independent learning baselines including MARL and centralized single-agent learning (SARL). Results show that QTRAN improves performance compared with the selected learning baselines and enhances the throughput–reliability trade-off under interference-coupled spectrum reuse. For instance, at $N_{\mathrm{V}2\mathrm{V}}=20$, QTRAN achieves a V2V rate of $0.194\pm 0.004$ and a V2I rate of $9.117\pm 0.213$, while reaching a V2V success rate of $0.812\pm 0.017$ with a low Deadline Miss Ratio of $0.001\pm 0.000$. At higher density ($N_{\mathrm{V}2\mathrm{V}}=50$), QTRAN sustains strong reliability (V2V success rate of $0.719\pm 0.006$ and Completion Ratio of $0.716\pm 0.006$) while maintaining competitive infrastructure throughput (V2I rate of $9.251\pm 0.114$). These results indicate that QTRAN effectively captures non-linear interference interactions, enabling coordinated decentralized spectrum and power decisions under the adopted density-based evaluation setting, thereby enhancing V2V reliability and throughput in cognitive Internet of Vehicles. Full article

This study investigates whether government spending stimulates economic growth by applying the Keynesian theoretical framework across varying economic conditions. The analysis uses annual data from 1980 to 2024 to explore how fiscal dynamics change over time and across regimes. It employs the NARDL model to evaluate asymmetric effects, the STAR model to capture regime dependence, and threshold Granger causality tests to assess causal relationships across spending regimes. These approaches enable a detailed examination of asymmetry, structural breaks, and nonlinear adjustment in the spending–growth relationship. The results show that Keynesian effects remain present across economic regimes but operate only in the short run without generating sustained long-term output gains. The absence of long-run cointegration is consistent with the presence of short-run dynamic multipliers, because these multipliers reflect temporary adjustments rather than permanent effects. The findings indicate that increases and decreases in government spending have proportionate effects on output, confirming a symmetrical Keynesian response. Government debt demonstrates a consistently negative and statistically robust influence on short-run growth. Corruption, measured using an index capturing governance quality, heightens policy ineffectiveness during periods of high public expenditure. Threshold causality tests reveal that government spending Granger causes economic growth in both low and high spending regimes, confirming the short-run stimulative potential of fiscal policy. Consequently, the study supports countercyclical fiscal interventions while emphasising the importance of prudent debt management and governance reforms to reduce fiscal risks. Full article

The inclusion of the cement industry into China’s national carbon emissions trading system in 2025 has fundamentally altered the compliance environment for high-emission enterprises, transforming carbon allowances from passive regulatory instruments into dynamic assets whose management directly affects financial performance. We develop a multi-scenario carbon asset management decision model tailored to the intensity-based benchmarking mechanism adopted by the national market. The model centres on the quota surplus-deficit variable EA4, which is computed from enterprise-level emission intensity relative to the industry benchmark, and decomposes the management problem into sequential selling and buying subproblems linked by coupled decision boundaries. A systematic parameter framework is constructed, and the model is applied to two cement enterprises—Enterprise A, a leading producer with a clear allowance surplus, and Enterprise B, a mid-tier producer operating near the benchmark boundary—through historical backtesting over the 2024–2025 period. Three principal findings emerge. First, the intensity benchmarking mechanism creates a dual-leverage effect whereby a 1.4% improvement in emission intensity (from 0.8112 to 0.8000 t/t) increases the quota surplus by 27%, a nonlinearity not captured by conventional compliance-cost models. Second, the model-driven strategy outperforms traditional experience-based approaches by 36.8% (baseline scenario, +95.20 vs. +69.58 MRMB) and 37.3% (risk scenario, −44.55 vs. −71.08 MRMB), with the improvement rate remaining consistent across both enterprises, suggesting that trading timing outweighs instrument selection in determining compliance cost outcomes. Third, dynamic CEA–CCER allocation captures an incremental 2.33 MRMB through the exploitation of a transient price inversion, a gain invisible to single-instrument strategies. Sensitivity analysis confirms that the relative advantage is robust to carbon price variations (±30%) and CCER offset caps (2–10%), while emission intensity and carry-over allowances represent the most consequential parameters for strategy direction, with EA4 crossing zero near the industry benchmark (I ≈ 0.85). The framework provides actionable decision support for cement and other high-emission enterprises navigating the unified carbon market, and contributes a quantitative methodology to the emerging field of environmental management accounting. This study contributes to Sustainable Development Goal 13 (Climate Action), Goal 7 (Affordable and Clean Energy), and Goal 9 (Industry, Innovation, and Infrastructure) by providing operational tools for decarbonisation in carbon-intensive industries. Full article

Nonlinear Model Predictive Control (NMPC) has garnered significant attention in autonomous systems due to its ability to predict future states and manage complex vehicle dynamics. However, the adaptability of existing NMPC methods is constrained by having to manually set the weight coefficients in the NMPC cost function. This study aims to explore a novel approach that integrates NMPC with Reinforcement Learning (RL), specifically employing Proximal Policy Optimization (PPO), to dynamically adjust NMPC weight matrices. The investigation begins by establishing a physics-based model for a two wheeled differential drive vehicle. A PPO model is then trained and deployed in real time to adapt to the NMPC weight matrices, achieving a 71% reduction in tracking error compared with the NMPC baseline. Importantly, the performance gain arises from PPO’s ability to reshape the NMPC cost function in real time, amplifying both orientation and lateral penalties in curves while relaxing them on straights, thereby enabling adaptive trade-offs between accuracy and control effort that static-weight NMPC cannot achieve. To enhance safety, the controller is integrated with a Control Barrier Function (CBF) layer for real-time obstacle avoidance, while PPO’s real-time weight adaptation contributes to improved tracking performance relative to NMPC+CBF. Finally, robustness evaluations under friction uncertainty, sensor noise, and path disturbances demonstrate that the PPO+NMPC+CBF method maintains reliable tracking accuracy and safety margins. Full article

The China Containerized Freight Index exhibits multi-scale periodicity and nonlinear responses to uncertainty, which challenge traditional forecasting methods. This study proposes a dynamic multi-stage deep learning framework with COVID-19 as an interval node to construct event windows. Breakpoint detection identifies shipping-related events. A three-stage procedure, including Maximal Information Coefficient, Boruta, and Granger causality, selects uncertainty risk indicators as core features, while K-shape clustering groups the exogenous variables. The proposed hybrid model integrates a Temporal Convolution Kolmogorov–Arnold Network with a Warped Fourier and Shock Kernel. Prophet decomposition supplies baseline and residual terms. Temporal Convolution Kolmogorov–Arnold Network unifies local temporal feature extraction and universal nonlinear approximation under sparse samples. The Warped Fourier component adapts to drifting and superimposed seasonality, and the Shock Kernel quantifies uncertainty shock intensity and decay. A gating fusion mechanism suppresses noise and enhances information efficiency. Comparative experiments demonstrate competitive accuracy and robustness, with statistically significant gains in several benchmark comparisons; ablation studies confirm incremental contributions of each component. Empirical analysis shows that under event-driven uncertainty, demand-side policy variables show stronger predictive relevance to China Containerized Freight Index fluctuations, while simultaneously transmitting effects to the carbon market and accelerating the green energy cost transition. These findings provide insights for freight rate forecasting and shipping market risk management. Full article

Traditional credit scoring models treat lending decisions as static classification, ignoring the dynamic evolution of borrower risk and long-term profit optimisation. This paper reinterprets credit risk management as a discrete-time stochastic optimal control problem and integrates the Hamilton–Jacobi–Bellman (HJB) framework with deep reinforcement learning. Theoretically, we establish the equivalence between a discrete Markov decision process and the HJB equation, prove the existence and uniqueness of the optimal value function, derive the closed-form Riccati solution under linear-quadratic assumptions, and provide a convergence analysis of neural network value iteration. Empirically, using LendingClub loan data (2016–2018), we implement a PPO-based dynamic credit policy. The proposed model achieves an average reward of 1.6726 and a total reward of 867,613, significantly outperforming static baselines as well as a DQN baseline. Ablation experiments show that replacing the policy network with a linear mapping reduces the average reward by 40.8%, confirming the necessity of nonlinear function approximation. Sensitivity analysis and statistical tests (p < 0.001) confirm the robustness and significance of the gains. This work provides a rigorous mathematical foundation and empirical evidence for shifting credit scoring from static classification to dynamic optimisation. Full article

The tension of a marine winch rope depends on the hydraulic pressure supplied to its input hydraulic motor. Traditionally, winches employ a relief valve to control the oil pressure of hydraulic motors. Owing to the inherent control characteristics of the relief valve, this control mode leads to continuous fluctuations in the system oil pressure, causing severe variations in the rope tension during operation. In this study, a direct-acting three-way proportional pressure-reducing valve was used to control the oil pressure of the winch, ensuring that the input pressure to the hydraulic motor was maintained at a set value, thereby mitigating the risk of drastic fluctuations in rope tension during vessel mooring. However, proportional pressure-reducing valve control exhibits shortcomings, such as static nonlinearities, insufficient dynamic response, and poor anti-interference stability, leading to oscillations in the outlet oil pressure and resulting in rope tension fluctuations in the winch. Based on the force and flow balance equations of the proportional pressure-reducing valve and in conjunction with the load characteristics of the winch, a mathematical model of the winch control system was established. An operating point for the pressure-reducing valve was determined, and the control system model was linearized. According to the Bode plot and frequency-domain index analysis, four key parameters affecting the outlet pressure fluctuation of the pressure-reducing valve were identified (valve port flow gain coefficient, viscous damping coefficient, transient hydraulic damping coefficient, and hydraulic spring stiffness). From the perspective of winch operation management, the working parameters of the hydraulic system were adjusted accordingly, and their effects on the four key parameters were analyzed. The results, in combination with model linearization and Bode plot analysis, indicate that appropriately lowering the operating temperature of the hydraulic oil can effectively improve the frequency-domain indices and stability margin of the control system, significantly enhancing the relative stability of the marine winch rope tension. Full article

Irrigation water use efficiency (IWUE) is a core indicator for assessing agricultural water use efficiency. However, existing studies predominantly focus on linear relationships between IWUE and individual correlates, with insufficient attention to the nonlinear interactions among multiple factors and the staged pathways of IWUE improvement. Taking 153 large- and medium-sized irrigation districts in Anhui Province as a case study, this research identifies seven key influencing factors—including canal lining rate (CLR), proportion of water-saving irrigation area (WSIR), and water price (WP)—and employs a random forest model coupled with SHAP (SHapley Additive exPlanations) interpretability analysis to uncover the driving mechanisms and enhancement pathways of IWUE. The results reveal that CLR, WSIR, and WP are the top three correlates, collectively contributing 67.80% to IWUE variation, with CLR being the most influential (28.75%). Their effects exhibit strong nonlinearity and threshold behavior: the marginal benefit of CLR diminishes significantly beyond approximately 75%; the optimal incentive range for WP lies between 0.09 and 0.14 CNY/m³; and precipitation exerts a persistent negative constraint. Moreover, IWUE improvement follows a sequential hierarchy: CLR serves as the foundational prerequisite; once CLR reaches a certain threshold, advancing WSIR becomes essential; and further gains require synergistic interaction between WSIR and WP after both attain sufficient levels. This study elucidates the nonlinear response mechanisms and stage-dependent driving patterns of IWUE, offering scientific insights and quantitative support for targeted, precision-oriented upgrades of irrigation infrastructure in Anhui Province and analogous humid/semi-humid regions, thereby contributing to sustainable agricultural water management. Full article

Distributed Electric Propulsion aircraft have gained significant attention for advancing green aviation. However, their application is constrained by the limited energy density of batteries, resulting in weight compensation and flight range limitation. Current research on DEP energy management predominantly focuses on thrust allocation during the cruise phase while largely neglecting the energy regeneration potential during the descent phase. Conventional all-motors active energy recovery strategies force the multi-motor array to operate within a low-efficiency region, since the required drag torque is small under low aerodynamic drag conditions. To solve this issue, this paper proposes an energy recovery strategy that dynamically adjusts the number of activated motors during the descent phase of aircraft. The proposed N-Active strategy can adaptively regulate the number of operating motors, shifting motor operating points from the low-efficiency region to the high-efficiency region, which effectively decouples energy regulation within the longitudinal symmetry plane and maximizes energy recovery benefits. In this study, a high-fidelity simulation platform is established, including nonlinear aerodynamic characteristics and propeller windmilling motor efficiency models. Moreover, the optimal performance of the N-Active multi-motor cooperative energy recovery optimization strategy is verified based on the constructed platform. Simulation results demonstrate that compared with the traditional all motors active strategy, the proposed method improves battery state of charge by 11.96% and reduces virtual weight of battery. This method can effectively alleviate the weight compensation effect of distributed electric propulsion aircraft without additional physical weight increment, thereby enhancing the loading capacity of aircraft. Full article

Predictive Maintenance (PdM) approach in Combined Sewer Systems (CSS) is gaining momentum due to advances in sensor technology, affordability and availability of data, and the rise of machine learning and data analytics. This study aims to characterize the general behavior of CSS under Dry and Wet weather conditions. To achieve this, 10 min resolution precipitation and water level data were collected from nearby SIAS stations and AMAP radar water level sensors, installed at the outlet chamber of the CSS, respectively. Precipitation data was used to segment continuous time series data into Dry Weather Flow (DWF) and Wet Weather Flow (WWF). DWF analysis exhibited unique flow patterns that strongly correlated with water consumption behaviors of households. For wet weather, a comparison was made between key rainfall parameters (depth, intensity) and peak water level data, and nonlinear relationships were observed that highlight the complex rainfall–runoff process. These findings underscore the need for separate predictive models tailored to DWF and WWF characteristics. Integrating high-resolution sensor data with machine learning models such as Long Short-Term Memory (LSTM) networks and anomaly detection, Autoencoders can enhance PdM, improving CSS management and reducing risks of blockage events and infrastructure failures. Full article