Search Results (7,092)

To autonomously dock LNG unloading arms under adverse sea states, this study formulates a dynamic docking process as a trajectory forecasting task. By integrating visual-perception-based spatial localization with trajectory acquisition and forecasting, a comprehensive operational pipeline is established. To predict the dynamic trajectory of the vessel flange, an improved KSE-GRU model is proposed. By extracting implicit kinematic features, the model effectively enhances trajectory characterization under extreme sea states, thereby significantly improving forecasting accuracy and worst-case error constraints. To ensure the operational feasibility of autonomous docking, a robust control strategy is introduced to complement the trajectory predictions. The experimental results demonstrate that the proposed model outperforms traditional time-series forecasting models across all evaluation metrics. Compared with the baseline neural network models, the Mean-3D error is reduced by 19.14%, and the Max-3D error is capped at 348.77 mm, representing an 8.8% improvement over the baseline. Furthermore, the model demonstrates clear advantages in maintaining trajectory consistency and forecasting reliability. In summary, in this study, a robust trajectory forecasting model is developed for vessel target flanges integrated with a comprehensive control framework, thereby offering a practical approach to autonomous docking under dynamic oceanic conditions. Full article

The growing penetration of renewable energy has intensified building load fluctuations, substantially increasing balancing costs. Electric vehicles (EVs) in building clusters often have considerable idle parking time beyond essential charging needs, enabling them to provide significant flexibility while meeting scheduled demands. This EV flexibility can balance intra-day load deviations and enable arbitrage in day-ahead electricity markets. However, conventional model-based approaches are fundamentally limited by their dependence on forecasting accuracy under high uncertainty from renewable generation and EV behavior. To address this, we propose a novel bi-level online optimization framework. The upper level employs a Lyapunov optimization-based algorithm that operates without predictions, making real-time decisions on total EV charging power to balance supply-demand mismatches. The lower level introduces novel flexibility metrics for individual EVs—encompassing temporal, volumetric, and cross-day dimensions—and optimizes power allocation by minimizing flexibility loss. Furthermore, we model EV flexibility as virtual queues and rigorously derive mathematical bounds on their limits, providing theoretical support for managing flexibility reserves. Rigorous analysis validates the framework’s feasibility, and comprehensive simulations demonstrate its superiority over benchmark algorithms, achieving significant cost reductions under various uncertainty scenarios. Full article

Sustainable land-use regulation in historical and cultural cities requires balancing heritage conservation, development demand, cropland retention, and urban–rural spatial restructuring. However, the stage-wise reorganization of urban–rural construction land under these coupled pressures remains insufficiently understood. Taking Jingzhou District, China, as a case study, this study uses land-use data from 2000, 2005, 2010, 2015, and 2020 and integrates stage-wise random-forest analysis, consistency-based interaction-network mining, and multi-scenario simulation within the intPLUS framework. Population, GDP, and areal-water distance layers were matched to the corresponding stage-terminal snapshots where applicable, whereas 2020 POI data were used as contemporary spatial-context proxies. From 2000 to 2020, urban industrial land (UIL) expanded from 16.63 to 46.42 km², increasing by approximately 179.1%, whereas rural settlements (RS) increased more moderately from 56.59 to 60.27 km², increasing by approximately 6.5%. The stage-wise RF and interaction-network results show that UIL and RS followed different spatial association structures, with stronger UIL self-reinforcement and stronger RS self-continuity in the later stage. Historical validation showed overall accuracy values of approximately 91% and Kappa values around 0.80, but FoM values remained relatively low, ranging from 0.098 to 0.176. Class-specific mapping accuracy was higher for RS (81.90–82.37%) than for UIL (55.20–66.93%), indicating a weaker performance in locating UIL change. Therefore, the 2035 simulations should be interpreted as parameter-conditioned regulatory comparisons rather than deterministic pixel-level forecasts. The scenario results indicate that the conservation-oriented limited growth was associated with the restricted UIL expansion and better cropland retention under the prescribed demand and constraint settings, while the RS reduction occurred only under explicit village-consolidation and construction-land quota reallocation assumptions. By distinguishing UIL and RS, this study provides differentiated regulation-oriented evidence for sustainable land-use governance in historical and cultural cities. Full article

Accurate multi-horizon Significant Wave Height (SWH) forecasting is vital for offshore safety and efficiency. Beyond scheduling maintenance windows, reliable lead-time predictions provide critical early warnings to protect personnel and high-value assets from hazardous high-wave conditions. However, the non-stationary and multi-scale nature of sea states poses challenges for consistent long-term accuracy. To address this challenge, we propose a robust three-stage framework for decomposition, feature selection, and multi-horizon forecasting. Specifically, Optimal Variational Mode Decomposition (OVMD) is adopted to construct multiscale and multi-view representations of nonlinear SWH sequences, while a Triangulated Maximally Filtered Graph (TMFG) constructs a sparse dependency network to select informative and non-redundant predictors from decomposed components and environmental variables. A hybrid prediction model then combines a Temporal Convolutional Network (TCN) for local multi-scale patterns with a Bidirectional Gated Recurrent Unit (BiGRU) for long-range dependencies. Experiments on real-world buoy observations show that the proposed approach improves accuracy and robustness over commonly used statistical and deep-learning baselines across short-, medium-, and long-term horizons. Ablation studies confirm that integrating modal decomposition with sparse feature selection enhances model robustness, offering reliable decision support for offshore window planning and high-wave condition monitoring. Full article

High-resolution spatiotemporal sea ice concentration (SIC) estimates are essential for Arctic navigation and ice analysis, but existing observational products are often too coarse, and physics-based models are computationally expensive. This study proposes a data-driven framework that couples Light Gradient Boosting Machine (LightGBM) temporal prediction with Kriging-based spatial interpolation to reconstruct SIC fields over the Northern Sea Route sector. LightGBM is trained on a grid-based SIC time series with engineered features representing persistence, seasonality, and short-term variability, enabling multi-horizon forecasting across large spatial grids. The predicted SIC fields are then refined using Ordinary Kriging (OK) and Co-Kriging (CK) with Gaussian and spherical semi-variogram models. Prediction performance is evaluated using root mean square error, and interpolation accuracy is assessed through cross-validation. Results show that, for high-latitude regions and resolutions finer than 0.25° × 0.25°, OK with a spherical semi-variogram achieves lower interpolation errors than CK and Gaussian-based alternatives. By sequentially coupling temporal learning and spatial refinement, the proposed framework improves temporal continuity, spatial structure, and error quantification, providing high-resolution SIC information suitable for large-scale Arctic ice analysis and navigation support. Full article

This study proposes a hybrid forecasting framework that integrates Kalman Filtering (KF), Markov Switching (MS), and nonlinear recurrent learning for stock-index prediction. The KF component smooths short-term price noise, the MS model identifies latent return–volatility regimes, and the LSTM/GRU components learn nonlinear temporal patterns from regime-conditioned information. The framework is evaluated using the CSI 300, S&P 500, and Nikkei 225 indices through forecasting-accuracy measures, Bootstrap Diebold–Mariano tests with Modified Bayes Factor evidence, out-of-sample trading simulations, and robustness checks. The empirical results show that regime conditioning is the primary source of forecasting and economic improvement. KF–MS–LSTM performs best for the CSI 300 and Standard MS performs strongest for the S&P 500, while KF–MS–LSTM and KF–MS–GRU are more competitive for the Nikkei 225. In contrast, models without regime information, including pure LSTM/GRU and the standalone Transformer, generally exhibit weaker forecasting and trading performance. The findings suggest that latent market-state information is more important than neural-network complexity alone for robust financial forecasting, while the incremental value of Kalman filtering and recurrent learning remains market dependent. Overall, the results support regime-aware forecasting as an interpretable and economically meaningful approach for stock-index prediction under heterogeneous market environments. Full article

Accurate forecasting of urban water demand is essential for scientific regulation and sustainable management of water resources, particularly in complex DMA (District Metered Area) environments. This study proposes an integrated regional water demand prediction framework that combines CEEMDAN decomposition with deep learning techniques. CEEMDAN is first applied to decompose the original water demand time series into multiple Intrinsic Mode Functions (IMFs), effectively extracting multi-scale features and mitigating non-stationarity and complexity. A hybrid Transformer-BiLSTM model is then constructed to capture global dependencies, nonlinear dynamics, and bidirectional temporal features. Experimental results demonstrate that the proposed CEEMDAN-Transformer-BiLSTM model significantly outperforms various benchmark models in terms of prediction accuracy, robustness, and generalization across different DMAs. This research provides a new perspective for modeling complex water resource time series and offers theoretical and practical support for optimizing urban water allocation and achieving sustainable management, while laying a foundation for future work involving external driving factors, enhanced model interpretability, and dynamic regulation mechanisms. Full article

Polar motion (PM), a key component of Earth orientation parameters (EOPs), is essential for high-precision satellite orbit determination and deep-space navigation. However, delays in data acquisition and processing limit its availability for real-time applications, necessitating the development of prediction models based on historical observations. Common approaches include least squares extrapolation (LS), autoregressive (AR) models, and their combination (LS + AR), often enhanced by effective angular momentum (EAM) from Earth’s fluid components. This study examines an EAM + LS + AR method for PM prediction, systematically evaluating how different EAM forecast horizons (1–10 days) affect 90-day prediction accuracy for both PM X and Y components. A segmented optimization strategy is proposed and validated against International Earth Rotation and Reference Systems Service(IERS) official predictions using the IERS EOP 14 C04 product. Key findings include: (a) Adjusting the EAM horizon substantially reduces prediction errors. Segmented prediction improves PM X accuracy by 20–30% (1–60 days) and 10–20% (61–90 days) relative to IERS rapid products, while PM Y short-term accuracy improves by 20–40% (1–15 days). (b) The influence of EAM horizon on long-term PM Y prediction gradually weakens, with errors converging to approximately 8 mas by day 90. (c) For 1–10-day forecasts, optimal horizons follow a systematic pattern: day m predictions achieve the highest accuracy using an (m—1)-day EAM horizon, while a 10-day horizon is optimal for long-term forecasts. (d) The proposed method shows clear advantages over IERS forecasts, with 83.5% of PM X predictions (1–90 days) and 50.78% of PM Y predictions (1–15 days), outperforming IERS daily products during the 2024 test period. Full article

Qinghai Lake, the largest endorheic saline lake in China, has undergone a pronounced hydrological regime shift from a multi-decadal decline to a rapid post-2004 recovery, reflecting strong hydroclimatic non-stationarity in the northeastern Tibetan Plateau (TP). This paper supplements the current water level and lake area status of Qinghai Lake to provide basic background for future prediction. Reliable forecasting of such climate sensitive lake systems remains difficult because conventional statistical models often fail to capture non-linear fluctuations, whereas standalone deep learning models may overlook long-term deterministic evolution. To address this challenge, we developed a serial decomposition GeoAI framework that integrates autoregressive integrated moving average (ARIMA), one-dimensional convolutional neural networks (1D-CNNs), and long short-term memory (LSTM) networks for non-stationary water level forecasting. Using annual water level observations from 1960 to 2025, the ARIMA component was first used to extract the low-frequency deterministic trend, after which the CNN-LSTM module reconstructed the nonlinear residual variability. The model was trained on the 1960–2012 period and validated over 2013–2025, which represents the most dynamic expansion stage of Qinghai Lake. The hybrid framework outperformed the benchmark models, achieving a Root Mean Square Error (RMSE) of 0.2033 m, Mean Absolute Error (MAE) of 0.1727 m, and Mean Squared Error (MSE) of 0.0413 m² during validation. The decomposition strategy effectively reduced phase lag and amplitude attenuation, improving both predictive accuracy and process interpretability. Multi-step forecasting for 2026–2056 suggests that Qinghai Lake will continue to rise, reaching approximately 3204.08 m by 2056, although the growth rate is projected to slow as negative hydrological feedback strengthen. By explicitly separating deterministic climate scale signals from nonlinear short-term variability, the proposed framework provides a robust and transferable geoinformation based tool for forecasting water level dynamics and supporting adaptive management in climate sensitive, data scarce lake basins. Full article

This paper analyzes volatility forecasting in the Spanish electricity spot market over the period 2021–2025, characterized by uncertainty, frequent price jumps, and the increasing occurrence of zero and negative prices. To accommodate these features, electricity prices are shifted to ensure well-defined log-returns, and predictable intraday and seasonal patterns are removed using the Ullrich demeaning procedure. Daily realized volatility measures are constructed from high-frequency data, including jump-robust and noise-robust estimators such as Median Realized Volatility and Realized Kernel. A broad set of volatility models, comprising GARCH-type specifications and multiple extensions of the Heterogeneous Autoregressive (HAR) framework, is evaluated using a coherent out-of-sample forecasting procedure. Model comparison is conducted through the Model Confidence Set methodology based on the QLIKE loss function, which identifies a Superior Set of Models with equal predictive ability. Conditional diagnostics, including Out-of-Sample $R_{\mathrm{OOS}}^2$ measures and Mincer–Zarnowitz regressions, are subsequently used to characterize forecast accuracy, unbiasedness, and efficiency. The empirical results show that all GARCH models are systematically excluded from the superior set, while HAR-type specifications based on realized volatility dominate. Within this set, a HAR model incorporating Median Realized Volatility, jump components, and day-of-the-week effects delivers the strongest economic performance, achieving an Out-of-Sample $R_{\mathrm{OOS}}^2$ close to 0.5 with unbiased forecasts. Overall, the findings highlight the importance of long-memory dynamics, discontinuous price movements, and residual weekly seasonality for volatility forecasting in modern electricity markets. Full article

Government Purchasing Price (Harga Pembelian Pemerintah, HPP) is a policy established to maintain stable Harvested Dry Paddy (Gabah Kering Panen, GKP) prices at the farm-gate level and to protect farmers from declining incomes due to price drops during harvest periods. The effectiveness of the policy has yet to be evaluated; however, reports indicate that paddy prices in several regions are still below the HPP rate. This study explores variations in the trends and volatility of farm-gate-level GKP prices before and after the adoption of the new HPP policy and constructs a provincial-level forecasting model based on the Extreme Gradient Boosting (XGBoost) methodology using a daily provincial panel dataset covering the period from 1 January 2023 to 31 December 2025. An analysis of six sample provinces was performed: the Special Region of Yogyakarta (DIY), East Java, South Kalimantan, Bali, West Sumatra, and Jambi. The model was trained using pre-policy observations and recursively forecasted post-policy prices under a hypothetical no-HPP-policy scenario, which were then descriptively compared with observed prices after the policy was implemented. The results show that the model delivers very high prediction accuracy, with tested Mean Absolute Percentage Error (MAPE) values ranging from 0.61% to 1.60% and Root Mean Squared Error (RMSE) values ranging from IDR 50.31 to IDR 158.04. The comparison shows that observed post-policy GKP prices tend to remain higher and more stable over time than those forecasted under the no-HPP-policy scenario, although the magnitude of this difference varies among regions. These findings provide descriptive forecasting evidence regarding post-policy GKP price dynamics rather than definitive causal estimates of policy impact. Full article

Solar filaments (and their limb counterparts, prominences) are critical tracers of the Sun’s magnetic topology and key precursors to coronal mass ejections (CMEs). Precise identification and continuous tracking of these features are essential for understanding solar eruptive mechanisms and improving space weather forecasting. This systematic review evaluates the evolution of automated detection methodologies, addressing the challenge of processing the exponentially growing volume of high-resolution solar observations. We identify deep learning architectures, particularly U-Net variants and Mask R-CNN, as the most promising current paradigms. Compared to traditional image processing, these data-driven models demonstrate superior robustness against noise and variable observing conditions, achieving high-precision segmentation (>90% accuracy) with sub-second inference speeds. This leap in computational efficiency and accuracy directly facilitates real-time operational monitoring and enables large-scale statistical analysis of filament evolution across solar cycles. We conclude that future breakthroughs lie in developing physics-informed AI and standardized benchmarks to bridge the gap between pixel-level segmentation and physical interpretation, ultimately creating detection systems that are both operationally reliable and scientifically meaningful. Full article

Rooftop farms are urban green infrastructure integrating food production, ecological regulation, and public services, and their management increasingly relies on data-driven approaches. However, open built environments, microclimatic heterogeneity, and limited sensor deployment challenge continuous monitoring and short-term prediction of rooftop plant growth. This study proposes and validates a virtual sensor-driven digital twin system using a rooftop tomato case in Xiamen, China. The system adopts a five-layer architecture comprising data acquisition, transmission, modeling, processing, and application service layers. By coupling a Long Short-Term Memory (LSTM) weather prediction model with the Decision Support System for Agrotechnology Transfer (DSSAT) crop growth model, a predictive virtual sensor module was developed to forecast leaf area index (LAI), aboveground biomass, phenology, and yield for seven days. Results show that the system links environmental data acquisition, LSTM–DSSAT prediction, database storage, and three-dimensional visualization, transforming rooftop plant growth into an updatable, predictable, and visualized digital twin object. The coupled model showed high predictive accuracy, with R² values of 0.9814 for LAI and 0.9966 for aboveground biomass, while supporting phenology and yield prediction. The system supports irrigation optimization, landscape management, and activity planning in sensor-constrained rooftop farms. Full article

As the demand for sustainable construction materials grows, wood ash and nanosilica have emerged as promising components for eco-friendly mortars, whose optimization requires advanced analytical techniques capable of capturing their complex linear and nonlinear interactions, making frameworks such as response surface methodology and artificial neural networks essential for effective mix design. This study examines the mechanical performance of eco-friendly mortar incorporating wood ash (WA) as a partial cement replacement and nanosilica solution (NSS) as a strength-enhancing additive, with the aim of optimizing compressive and flexural behaviour. Wood ash was substituted at levels of 5–25%, while NS (0.265 moL⁻¹) was substituted at levels of 0–1.7%. Twenty-one mortar samples were produced and tested at multiple curing ages. Two modelling techniques, response surface methodology (RSM) and artificial neural networks (ANNs), were employed to evaluate the individual and interactive effects of WA and NSS on strength development at curing ages of 28 and 180 days. While RSM provided insight into factor significance and linear interactions, ANN more effectively captured nonlinear behaviour, achieving superior predictive accuracy (R² = 1.000 for 28-day strength). Experimental results revealed that nanosilica substantially enhanced strength up to an optimal dosage of approximately 2.5 g, beyond which performance declined due to particle agglomeration or matrix over-refinement. In contrast, higher WA contents produced strength reductions attributable to dilution effects. Optimization showed that mixtures containing low WA (≤30 g) combined with moderate NSS (2.0–2.5 g) exhibited the highest mechanical performance. Collectively, the findings confirm that ANN-based models outperform RSM and multilinear regression, underscoring their effectiveness for mix design optimization and performance forecasting in sustainable cementitious systems. Full article

Short-term wind power forecasting is a key enabling technology for wind farm operation optimization, power grid dispatch, and electricity market decision-making. However, existing studies often lack unified standards in data partitioning, input feature construction, and hyperparameter tuning, making fair and reproducible comparisons across models difficult to achieve. To address this issue, this study focuses on day-ahead wind power forecasting for a single wind farm and establishes a benchmarking framework with strict chronological splitting, a shared feature information set, and a consistent hyperparameter tuning budget. Within this framework, six representative models, namely Ridge, XGBoost, LightGBM, DLinear, Transformer, and PatchTST, are systematically evaluated. A two-level evaluation protocol combining a fixed hold-out split and expanding-window rolling validation is adopted to compare model performance from multiple perspectives, including overall accuracy, sensitivity to hyperparameter tuning, robustness across rolling windows, and performance under typical operating scenarios. The results show that model rankings are not fully consistent between the hold-out evaluation and the rolling-validation setting. Under the fixed hold-out split, LightGBM achieved the lowest NRMSE of 10.2326%, while Transformer obtained the lowest NMAE of 6.9944%. In contrast, under the 8-fold expanding-window rolling validation, Transformer achieved the lowest average NRMSE of 8.1684%, followed by LightGBM with 8.7344%. These results indicate that the best performance on a single test split does not necessarily imply the strongest robustness across multiple time windows. In addition, strong tree-based models remain highly competitive in this single-wind-farm forecasting task, whereas more complex deep temporal models do not always deliver stable advantages. Meanwhile, the performance gains brought by hyperparameter optimization vary substantially across models, suggesting that conclusions drawn from default-parameter comparisons are of limited reliability. These findings demonstrate that systematic benchmarking under strict temporal constraints and fair tuning conditions is essential for clarifying the comparative performance, robustness, and engineering applicability of different model families. The study can therefore provide practical guidance for model selection and deployment in short-term wind power forecasting for single wind farms. Full article