Search Results (173)

Classical tools for time series dependence analysis are primarily designed for linear dependence and may fail to detect serial structure when a series is uncorrelated but not independent. To address this problem, we propose the auto ball covariance function and the corresponding auto ball correlation function for measuring lag-specific nonlinear dependence in strictly stationary time series taking values in a separable Banach space. The proposed diagnostic uses metric-ball probabilities to measure fixed-lag distributional dependence without moment requirements, making it suitable for vector-, function-, and norm-induced object-valued time series. Under suitable conditions, we show that the proposed measure is zero if and only if the lagged components are independent. We further develop sample versions of the proposed statistics and establish their large-sample properties, including strong consistency under absolute regularity and a fixed-lag null asymptotic law under a finite-range dependence condition on the lagged-pair process. Simulation studies demonstrate that the proposed method performs well in a variety of settings, especially for nonlinear, heavy-tailed time series. A real-data analysis of annual sunspot numbers further illustrates how the proposed diagnostic can reveal nonlinear residual dependence that is not visible from ordinary autocorrelation diagnostics. Full article

Recent studies have investigated whether the rate of global warming has changed since the 1970s, with particular attention to the role of natural variability and its removal from temperature time series. In particular, Foster and Rahmstorf analyzed global mean surface temperature series, adjusted for natural variability. However, their procedure might produce spurious changepoints, since it does not appropriately handle the autocorrelation present in the residuals of the models considered. In this study, we revisit the same adjusted temperature series using a different methodology (the Quandt likelihood ratio test) while properly accounting for the presence of autocorrelation. We find evidence that global temperature has departed from its previous path since around 2013–2014. Our results provide robust proof of a clear recent increase in the temperature trend for adjusted time series, at a rate of warming that has doubled since that date. Full article

This study presents a phenomenological estimation framework for a membraneless alkaline water electrolyzer (MAWE), developed primarily from experimentally measured current signals and end-of-test mass-loss data. Thirteen KOH concentrations (5–35 g in 1 L deionized water) were investigated under a constant 12 V DC supply for 7200 s. The time-varying current was continuously recorded throughout each experiment, while the total gas production was determined from the net mass loss measured at the end of the electrolysis process. A time-resolved hydrogen-production representation was subsequently reconstructed from the measured current signal using Faraday’s law and constrained to be stoichiometrically consistent with the experimentally observed total mass loss. The term “charge-consistent” used throughout this study does not imply a new electrochemical principle, but rather refers to maintaining physical consistency between the experimentally measured current signal, Faraday-based charge transfer, and the experimentally observed end-of-test mass loss within the proposed phenomenological framework. Experimental results indicate that both the current response and the cumulative gas production exhibit a strong and distinctly nonlinear dependence on the KOH concentration. Two phenomenological modeling approaches were examined. The first is a static polynomial formulation describing the nonlinear relationship between the measured current signal and the reconstructed production rate. The second is a semi-empirical grey-box formulation in which the Faraday-based theoretical production term is corrected using an experimentally identified efficiency coefficient. Model performance was assessed using train/test data partitioning, residual analysis, autocorrelation functions, and Ljung–Box tests, demonstrating a high degree of internal charge consistency and macroscopic agreement with the reconstructed experimental representation. The proposed framework provides a reduced-order and experimentally accessible approach for representing reconstructed production behavior in MAWE systems without resorting to detailed multi-physics modeling or EIS-based characterization and offers a physically consistent baseline for comparison with more complex data-driven or control-oriented modeling strategies. Full article

In this study, we developed a leakage-free time-series machine learning framework to improve the accuracy of short-term (10 min ahead) wind speed forecasting. The measurements were obtained from real operational data collected at the Bandırma/Balıkesir wind power plant in Türkiye. The framework incorporates chronological train validation test splitting, causal missing data imputation, leakage-free feature engineering, and supervised lag-based modeling. Such a leak-proof design is crucial to avoid future information influencing the training and testing process of models, thus making the forecasting process more realistic and reliable in practice. We tested several models, including persistence, Support Vector Regression (SVR), Least-Squares Gradient Boosting (LSBoost), Random Forest (RF), Elastic Net (ELASTIC), and a stacking ensemble, and evaluated their performance using Root Mean Squared Error (RMSE), Mean Absolute Error (MAE), R-Squared (R²), bias measures, and skill scores, complemented by diagnostic analyses including residual distribution, autocorrelation, regime-based evaluation, Bland–Altman plots, and Quantile Quantile (Q-Q) plots. Our analyses showed that the Elastic Net model achieved balanced and statistically consistent performance, with a test RMSE of 0.6325 m/s, R² = 0.977, and negligible bias. Residual analysis indicated that errors were centered around zero, exhibited weak temporal dependence, and followed an approximately normal distribution in the central quantiles. Regime-based evaluation revealed that the model performed strongly in medium- and high-wind-speed conditions, while accuracy decreased under low wind speeds due to measurement uncertainty and low signal-to-noise ratios. Feature importance analysis indicated that previous wind speed was the dominant predictor, with solar irradiation and air temperature also contributing significantly. Forecast error decomposition showed that most prediction errors arose from natural atmospheric variability, with minimal systematic bias. The Diebold–Mariano test confirmed that ELASTIC statistically outperformed conventional machine learning models such as SVR and Random Forest. The proposed framework demonstrates statistically consistent short-term forecasting behavior that may support operational wind energy management and grid balancing applications. Full article

Coffee export price volatility is a relevant problem for producing countries because it affects commercial planning, contract negotiation, producers’ income stability, and the financial sustainability of the agro-export value chain. In economies that are highly dependent on primary commodities, abrupt fluctuations in international prices increase uncertainty and reduce the ability of economic agents to anticipate market behavior. In this context, the objective of this study was to forecast the behavior of the Peruvian coffee export price during 2025 by comparing econometric and time-series models. The research adopted a quantitative approach with a non-experimental, retrospective, and longitudinal design, using a monthly series for the 2010–2024 period. Seven specifications were estimated: linear model, quadratic model, Holt–Winters exponential smoothing, causal model, lagged model, ARIMA, and GARCH. The results showed that the GARCH (1,1) model achieved the best statistical performance, with the lowest Akaike Information Criterion, a Durbin–Watson statistic close to 2, an R² higher than that of the alternative models, and no residual autocorrelation. Likewise, the significance of the ARCH and GARCH components confirmed the existence of volatility clustering in the series. The projections for 2025 show a fluctuating trajectory, although with a tendency to stabilize around values close to 10 from March onward. It is concluded that the GARCH (1,1) model is the most appropriate specification for forecasting the Peruvian coffee export price, as it provides a useful tool for export planning, risk management, and decision-making in a context of high uncertainty in the coffee market. Full article

Accurate short-term forecasting of Limnospira platensis biomass is essential for optimizing experimental scheduling and cultivation strategies, yet small datasets and strong temporal autocorrelation pose significant challenges for model reliability. In this study, we developed a leakage-safe, data-driven framework for direct multi-step forecasting of biomass concentration based on experimental time-series data from nine independent cultivation trials conducted under heterogeneous nutritional and environmental conditions. Gradient Boosting consistently outperformed a persistence baseline across all forecasting horizons (R² ≈ 0.915 at h = 1, 0.935 at h = 2, 0.814 at h = 3), demonstrating strong predictive capability under Leave-One-Experiment-Out cross-validation, which ensures generalization to unseen experiments. Residual analysis and prediction intervals confirmed robust uncertainty quantification and revealed condition-dependent variability in predictive performance. Overall, the results show that rigorously validated machine learning models can reliably forecast biomass trajectories beyond naïve baselines, even under limited and heterogeneous datasets. This approach provides a scalable and reproducible methodological framework for predictive modeling in algal biotechnology; however, because the training data were collected at flask scale, direct transfer to larger photobioreactor or outdoor systems should be considered a future validation step rather than an immediate deployment outcome. Full article

This study presents a reproducible high-resolution framework for assessing urban chikungunya environmental suitability and outbreak-related spatial heterogeneity during the 2025 outbreak in the western Guangdong–Hong Kong–Macao Greater Bay Area. Using Sentinel-2–derived environmental indicators together with a random forest–based residual correction of Landsat surface temperature, we developed a 10 m weighted additive Mosquito Habitat Suitability Index (MHSI). Index weights were empirically derived by comparing reported case locations at the street and town level with randomly sampled background points. The optimized weighting scheme indicated that humidity- and water-related conditions contributed more strongly to habitat suitability than vegetation and temperature. Reported case locations generally corresponded to higher MHSI values than background locations, suggesting that the index captures broad spatial patterns of environmental suitability. Comparison with a coarser, model-derived global chikungunya risk map was used as an external comparative consistency assessment rather than predictive validation, showing moderate agreement at the macro-spatial scale (Pearson r = 0.3421) after correction for spatial autocorrelation. Residual-difference analysis, combined with multiple points-of-interest (POI) categories, ordinary least squares (OLS), and geographically weighted regression (GWR), further suggested that human activity, transport connectivity, and healthcare accessibility may account for part of the remaining spatial mismatch not explained by environmental suitability alone. Sensitivity analyses indicated that the broad LST downscaling pattern and the exploratory GWR interpretation were reasonably stable under alternative sampling, smoothing, grid-size, and bandwidth settings. Taken together, this framework provides preliminary spatial evidence for high-resolution environmental suitability assessment and exploratory interpretation of outbreak-related spatial heterogeneity, while underscoring the need for finer-scale epidemiological data and more explicit representation of human-driven processes. Full article

The Yellow River Delta, a young alluvial plain in China, is experiencing severe land subsidence that threatens its ecological security and sustainable development. However, the driving mechanisms of this subsidence exhibit strong spatial heterogeneity, which traditional global models fail to capture. This study integrates high-precision subsidence measurements from Sentinel-1A imagery and SBAS-InSAR technology (2017–2023) with multi-source environmental factors (topography, geology, land use, precipitation) to propose a Spatially Adaptive Ensemble Learning Model with feature selection (SA-GSE). The model concatenates predictions from base learners (CatBoost, XGBoost, Random Forest) with spatial features (e.g., distance to salt pans, local topographic variance) to form meta-features, which are then input into a multilayer perceptron meta-learner. Through 5-fold spatial cross-validation, SA-GSE learns spatially dynamic base-model weights, implicitly adapting to regional variations in subsidence drivers. The model achieves an R² of 0.7810 and RMSE of 40.55 mm/yr on the test set, outperforming individual base models and ordinary stacking. Residual spatial autocorrelation is substantially reduced, with SA-GSE yielding the lowest Moran’s I (0.0334, p = 0.206) among all evaluated models, confirming effective capture of spatial heterogeneity. Driving force analysis reveals that distance to salt pans is the most important predictor (permutation importance: 0.4456), underscoring the dominant role of brine extraction-induced aquifer compaction. Lagged precipitation importance (0.3191) exceeds that of current precipitation (0.2453), indicating a recharge lag effect. SHAP interaction analysis uncovers a nonlinear “precipitation decoupling” mechanism in salt pan areas, where high precipitation paradoxically exacerbates subsidence. The resultant map of predicted subsidence rates highlights elevated rate zones in the northern salt pans and along the Guangli River. While the map does not represent a full risk assessment—as it does not include exposure or vulnerability—it provides a spatially explicit estimate of hazard likelihood. This ensemble framework yields novel perspectives on subsidence drivers in heterogeneous regions and can support land subsidence prevention and groundwater management planning. Full article

Aridity is a key climatic factor influencing ecosystem dynamics and land degradation in arid and semi-arid regions. This study analyzes the spatial relationship between aridity and land cover degradation in northwestern Mexico during 2005–2020 using a Geographically Weighted Regression (GWR) model, complemented by spatial autocorrelation techniques including Moran’s I and Local Indicators of Spatial Association (LISA). Aridity was derived from climatic data, and land cover transitions were used as proxies for degradation. The results indicate that the study area is predominantly characterized by arid and semi-arid conditions, where degradation-related transitions are strongly concentrated. In particular, transitions from shrubland to grassland (59.53%) and from shrubland to bare soil (93.60%) occur primarily under arid conditions, highlighting the high vulnerability of these ecosystems to water deficit. The GWR model explains approximately 49.5% of the spatial variability in degradation. However, residual analysis shows strong spatial autocorrelation (Moran’s I = 0.72, p < 0.001), indicating spatially structured patterns not fully captured by the model. These findings demonstrate that, although aridity is a key driver, additional factors influence degradation patterns. Full article

During the COVID-19 pandemic, Health Canada temporarily exempted pharmacists from specific restrictions under the Controlled Drugs and Substances Act (CDSA), allowing them to prescribe opioids. However, it is not yet established whether opioid dispensing patterns differ between urban and rural pharmacists. This study aims to assess the impact of the CDSA subsection 56(1) temporary exemption on opioid prescribing practices among urban and rural pharmacists between 1 February 2018 and 30 April 2022. Descriptive statistics and visualizations assessed differences in opioid prescribing between urban and rural pharmacists under the CDSA exemption. Initial analyses employed linear regression to examine changes, followed by evaluation of temporal dependence using autocorrelation and residual analysis. When appropriate, a suitable time series model was subsequently applied. Following the CDSA exemption, the mean weekly proportion of opioid claims prescribed by urban pharmacists increased from 0.0% to 1.03%. In contrast, rural pharmacists’ prescriptions rose from 0.0% to 0.35%. The estimated mean level change was 0.667% for urban pharmacists (95% CI: 0.520–0.838%, p < 0.0001) and 0.201% for rural pharmacists (95% CI: 0.140–0.291%, p < 0.0001). The study identified distinct differences in opioid prescribing practices between urban and rural pharmacists in Nova Scotia. Furthermore, opioid prescriptions increased steadily across all patient groups, indicating evolving patterns of opioid use within the province. Full article

A probabilistic data-driven framework for voltage quality forecasting in distribution transformers based on Gaussian process regression and high-resolution field measurements is presented. Voltage time series acquired under real operating conditions were modeled using composite covariance functions designed to capture long-term trends and stochastic multi-scale fluctuations. The proposed approach enables simultaneous prediction and uncertainty quantification, allowing direct compliance assessment with voltage quality standards. The additive Gaussian process models achieved coefficients of determination above 0.75 and produced statistically uncorrelated residuals, indicating an adequate representation of the intrinsic temporal structure. However, the predictive intervals exhibit a certain level of undercoverage, indicating that, while uncertainty is effectively quantified, there is still room for improvement in calibration. The selected kernel structures revealed distinct physical regimes in the voltage dynamics, including smooth steady operation, moderately irregular behavior associated with localized disturbances, and multi-scale stochastic variability. For benchmarking purposes, results were compared with those obtained from a stochastic damped harmonic oscillator with restoring force, a naive model, a seasonal naive model and an Autoregressive Integrated Moving Average model. The oscillator model, the naive model, the seasonal naive model, and the Autoregressive Integrated Moving Average model generated strongly autocorrelated residuals, whereas the Gaussian process models yielded consistent white-noise residuals that outperformed all the other models. These findings demonstrate that probabilistic Gaussian process modeling provides an interpretable, scalable, and uncertainty-aware alternative for predictive voltage quality assessment in modern distribution systems. Full article

Quantitative trading systems require predictive models that simultaneously deliver accurate forecasts, calibrated uncertainty quantification, and actionable risk measures. This paper proposes an information-theoretic semiparametric regression framework combining a convolutional neural network–Transformer (CNN–Transformer) network for nonlinear temporal dependencies with a Gaussian process (GP) prior for residual autocorrelation and calibrated predictive distributions. Three theoretical results are established: an identifiability theorem guarantees joint recoverability of the nonparametric and GP components; a consistency theorem showing that the penalised maximum likelihood estimator converges at a rate $n^{-1/(2+d_{\mathrm{eff}})}$; and a coverage theorem proving asymptotic nominal coverage of the GP’s credible intervals. The framework enables an entropy-regulated trading module where predictive differential entropy informs position sizing via an uncertainty-penalised Kelly criterion, Kullback–Leibler divergence quantifies model uncertainty, and CVaR-constrained optimisation controls the tail risk. Simulations show the method outperforms the CNN, long short-term memory (LSTM), Transformer, XGBoost, random forest, least absolute shrinkage and selection operator (LASSO), and standard GP regression approaches. Backtesting on four Chinese A-share stocks yielded annualised returns of 15.9–22.4% with Sharpe ratios of 0.49–0.62, maximum drawdowns below 15%, and daily 95% CVaR reductions of 28–31% relative to a full-Kelly baseline, confirming both predictive accuracy and risk management effectiveness. Full article

This study applied time-series modeling using autoregressive integrated moving average (ARIMA) to compare the growth performance of tilapia broodfish in pond and recirculating aquaculture systems (RAS) from June 2023 to May 2024. Descriptive statistics showed a higher mean percentage weight gain under RAS (26.69%) than pond culture (23.75%), although monthly variability in the RAS dataset was influenced by an outlier, which may be attributed to influential exogenous factors rather than water-quality parameters. Normality, stationarity, and autocorrelation diagnostics confirmed that both datasets were appropriate for ARIMA modeling without differencing. Multiple ARIMA models were evaluated based on RMSE, MAPE, MAE, AIC, BIC, and residual behavior; ARIMA (1,0,1) emerged as the best fit for both systems. Forecasting up to May 2028 revealed stable long-term growth patterns, with RAS consistently showing slightly higher forecasted growth compared to pond culture, although the difference remained small in absolute terms. Predictions remained within model-generated 95% confidence intervals; however, these results indicate internal model consistency rather than independent validation of predictive accuracy. The findings highlight that RAS offers more consistent and slightly superior growth performance, supporting its potential for optimized broodfish production. Recommendations emphasize adopting RAS for enhanced growth predictability and improved management in tilapia aquaculture. Full article

Short-term load forecasting plays a pivotal role in modern power system operations yet it remains challenging due to the complex spatiotemporal dependencies in load data. This paper proposes a dual-head attention residual network (DARNet) that significantly advances STLF through three key innovations: (1) a hybrid encoder combining 1D-CNN and GRU architectures to simultaneously capture the local load patterns and long-term temporal dependencies, achieving a 28% better locality awareness than that of conventional approaches; (2) a novel dual-head attention mechanism that dynamically models both the inter-temporal relationships and cross-variable dependencies, reducing the feature engineering requirements; and (3) an autocorrelation-adjusted recursive forecasting framework that cuts the multi-step prediction error accumulation by 33% compared to that with standard seq2seq models. Extensive experiments on real-world datasets from three Chinese cities demonstrate DARNet’s superior performance, outperforming six state-of-the-art benchmarks by 21–35% across all of the evaluation metrics (MAPE, SMAPE, MAE, and RRSE) while maintaining robust generalization across different geographical regions and prediction horizons. Full article

The large-scale rapid deployment of renewable generation and energy storage is transforming traditional power system dynamics through intermittency, reduced inertia, and pronounced long-range temporal dependence. Existing power system modeling frameworks are primarily based on short-memory assumptions and integer-order dynamics, which are unable to capture the persistence and oscillatory behavior of emerging renewable-dominant power systems. This structural mismatch leads to inaccurate system representation and degraded long-horizon prediction performance. Although fractional calculus has been applied to specific control and forecasting tasks in power systems, the joint system-level modeling of renewable generation and load demand using real-world data remains largely unexplored. In this paper, we develop a data-driven fractional-order dynamic modeling framework that explicitly incorporates long-memory effects into the governing equations through fractional differential equations based on the Caputo formulation. Using publicly available high-resolution datasets of load and renewable generation, empirical analysis reveals power-law decaying autocorrelations and dominant low-frequency spectral characteristics that motivate the use of fractional-order dynamics. Fractional orders and model parameters are jointly identified through prediction-error minimization to ensure consistency between modeled trajectories and observed persistence. The numerical results demonstrate that the proposed approach achieves a root–mean–square error of $3.12$, compared to $5.64$ and $4.98$ for integer-order and finite-memory models, respectively, and reduces the normalized root–mean–square error from $0.156$ and $0.132$ to $0.087$. Residual and spectral analyses further confirm that long-memory behavior is effectively captured by the proposed dynamics. The framework provides a scalable and physically interpretable foundation for the data-driven modeling of renewable-dominant power systems. Full article