Search Results (6)

Ensuring the consistency of recurring ETL processes is a critical challenge in large-scale financial analytics, where upstream data changes—such as variable redefinitions, unit conversions (e.g., from days past due to number of overdue installments or currency changes), or erroneous submissions following source system updates—can silently degrade model reliability. These risks are amplified in automated modeling environments, where dozens of models are retrained monthly for each financial institution and the number of serviced institutions is expected to grow. This study presents an automated statistical monitoring framework for continuous quality assurance of monthly ETL outputs used in model development. The approach quantifies drift between a reference dataset and successive data deliveries using descriptive univariate and bivariate statistics combined with a normalized Canberra-based drift score, aggregated into interpretable variable-level stability measures. Sensitivity is evaluated through controlled noisification experiments with increasing Gaussian perturbations, demonstrating a monotonic decline in stability scores and consistent directional shifts in complementary metrics such as the Gini coefficient and Kolmogorov–Smirnov statistic. The results show that the framework effectively detects both subtle and large-scale distributional changes, providing a scalable, interpretable, and reproducible monitoring diagnostics suitable for fully automated financial data pipelines, with flexibility for extension. Full article

The upper Yellow River basin is a classic ecologically vulnerable area, characterized by acute human–land conflicts. The rapid pace of urbanization drives landscape fragmentation, which severely threatens regional sustainability and ecological security. Given the difficulty of using a single indicator to fully diagnose the relationship between ecological function and risk, this research establishes a spatial diagnostic framework that uses ecosystem service value (ESV) to measure functional output and landscape ecological risk (LER) to indicate structural vulnerability. Utilizing land use data from 1990 to 2020, we quantified, for the first time at a 250 m grid scale, the spatiotemporal evolution of ESV and LER in the riparian zone of the Lanzhou–Baiyin metropolitan area (LBMA). The findings reveal concurrent declining trends in both ESV and LER, which signal not ecological improvement but rather systemic degradation towards lower functionality and lower ecological risk. Bivariate LISA clustering was used to identify four categories of ecological regulation zones, offering a spatial foundation for implementing differentiated governance. Building on the four-zone typology, this research further proposes a tiered control strategy encompassing strict protection, urgent restoration, and built-up area optimization, highlighting its advantages compared to conventional single-indicator management. This framework links spatial pattern diagnosis with ecological governance actions and also provides an analytical tool for understanding and managing the security of riparian ecosystems under similar pressures. Full article

This paper investigates the planning problem of AC-integrated wind–photovoltaic–hydro–storage (WPHS) bundled transmission systems. To effectively capture the uncertainty and interdependence in renewable power outputs, a Copula-enhanced distributionally robust optimization (DRO) framework is developed, enabling a unified treatment of stochastic and correlated renewable generation within the system planning process. First, a location and capacity planning model based on DRO for WPHS generation bases is formulated, in which a composite-norm ambiguity set is constructed to describe the uncertainty of renewable resources. Second, the Copula function is employed to characterize the nonlinear dependence structure between wind and photovoltaic (PV) power outputs, providing representative scenarios and initial probability distribution (PD) support for the construction of a bivariate ambiguity set that embeds coupling information. The resulting optimization problem is solved using the column and constraint generation (C&CG) algorithm. In addition, an evaluation metric termed the transmission corridor utilization rate (TCUR) is proposed to quantitatively assess the efficiency of external AC transmission planning schemes, offering a new perspective for the evaluation of regional power transmission strategies. Finally, simulation results validate that the proposed model achieves superior performance in terms of system economic efficiency and TCUR. Full article

This study presents a novel bivariate-output deep learning framework based on LeNet-5 for the simultaneous prediction of urban flood susceptibility and inundation depth in Seoul, South Korea. Unlike previous studies that relied on single-output models, the proposed approach jointly learns classification and regression targets through a shared feature extraction structure, enhancing consistency and generalization. Among six tested architectures, the Le5SD_CBAM model—integrating a Convolutional Block Attention Module (CBAM)—achieved the best performance, with 83% accuracy, an Area Under the ROC Curve (AUC) of 0.91 for flood susceptibility classification, and a mean absolute error (MAE) of 0.12 m and root mean squared error (RMSE) of 0.18 m for depth estimation. The model’s spatial predictions aligned well with hydrological principles and past flood records, accurately identifying low-lying flood-prone zones and capturing localized inundation patterns influenced by infrastructure and micro-topography. Importantly, it detected spatial mismatches between susceptibility and depth, demonstrating the benefit of joint modeling. Variable importance analysis highlighted elevation as the dominant predictor, while distances to roads, rivers, and drainage systems were also key contributors. In contrast, secondary terrain attributes had limited influence, indicating that urban infrastructure has significantly altered natural flood flow dynamics. Although the model lacks dynamic forcings such as rainfall and upstream inflows, it remains a valuable tool for flood risk mapping in data-scarce settings. The bivariate-output framework improves computational efficiency and internal coherence compared to separate single-task models, supporting its integration into urban flood management and planning systems. Full article

The aim of this work is to introduce an innovative methodology for performing risk attribution within a multifactor risk framework. We applied this analysis to the assessment of systemic, climate, and geopolitical risks relative to a representative sample of Eurozone banks between 2011 and 2022. Comparing the results to the output of a bivariate approach, we found that contemporaneous tail crises generate combined equity losses exceeding partial analysis estimates. We then attributed the combined risk to each factor and to the effect of their interaction by employing our proposed frequency-based approach. For our computations, we used multivariate GARCH, Monte Carlo simulations, and a suite of Eurozone-specific factors. Our results show that total combined risk is on average 18% higher than traditional systemic risk estimates, that climate risk more than doubled in our period of analysis, and that geopolitical risk surged to over 5% of total combined risk. Our climate risk estimate is in line with the results of the 2022 European Central Bank climate stress test, and our geopolitical risk measure shows a positive correlation with the GPRD and Threats index. Full article

Climate change’s impact on water availability has been widely studied, including its impact on very rare values quantified by return levels using the statistical extreme value theory. However, the application of this theory to estimate extreme low flows is barely justified due to a large temporal dependency and a physically highly bounded lower tail. One possible way of overcoming this difficulty is to simulate a very large sample of river flow time series consistent with the observations or the climate projections in order to enable empirical rare percentile estimations. In this paper, such an approach based on simulation is developed and tested for a small mountainous watershed in the French Alps. A bivariate generator of daily temperature and rainfall, developed in collaboration with Paris-Saclay University and based on hidden Markov models, is used to produce a large number of temperature and rainfall time series, further provided as input to a hydrological model to produce a similarly large sample of river flow time series. This sample is statistically analyzed in terms of low flow occurrence and intensity. This framework is adapted to the analysis of both current climate conditions and projected future climate. To study historical low flow situations, the bivariate temperature and rainfall model is fitted to the observed time series while bias-adjusted climate model outputs are used to calibrate the generator for the projections. The approach seems promising and could be further improved for use in more specific studies dedicated to the climate change impact on local low flow situations. Full article