Search Results (131)

Coastal cities are prone to flooding due to extreme rainfall, rising sea levels, and urbanization. This study develops a non-stationary flood risk prediction framework for a coastal city to assess the combined effects of rainfall, tide, and land surface change on future flood inundation and socioeconomic risk. Future rainfall was predicted by integrating the time-varying parameter distribution (TVPD) model with CMIP6 data through a genetic algorithm; future tides were estimated using the TVPD model; and land use in 2035 was simulated using the Markov–PLUS model. Flood inundation and the associated socioeconomic risks were then evaluated. The results showed that the integrated rainfall prediction approach reduced RMSE by 13.4% compared with the individual models. The land use simulation also showed acceptable performance, with a Kappa coefficient of 0.79 and an FOM value of 0.15. Under the combined effects of rainfall, tide, and land use change, the future peak inundation volume increased by 19.97% on average relative to the baseline period, while the affected population and economic losses increased by 72,603 people and US$12.61 billion, respectively. These results indicate that flood risk in coastal cities may be substantially exacerbated under a non-stationary environment, and the proposed framework can provide support for future flood risk assessment and adaptation planning. Full article

In this study, a hierarchical aluminum foam-filled thin-walled structure is proposed and its performance under axial impact is subsequently investigated. Two primary configurations are studied, namely, a hierarchical unit-cell structure (HUCS) and hierarchical multi-cell structure (HMS), respectively. Meanwhile, based on the experimental results, models are established to further investigate the effect of geometries, foam densities and impact velocities on the impact performance of the proposed structure. Finally, an improved simplified super folding element (SSFE) theoretical model which accounts for the constraint-induced strengthening effect of the foam filler is derived and a closed-form expression for the mean crushing force (MCF) is obtained. Compared with non-hierarchical counterparts (NHUCS and NHMS), the hierarchical designs exhibited superiority in reducing deformations and enhancing specific energy absorption (SEA). Compared to non-hierarchical structures, under an impact with identical energy, the HUCS shows a 12.7% reduction in maximum deformation and a 15.4% increase in SEA at the same deformation level. Meanwhile, the HMS reduces MCF by 17.2% and initial peak force (IPF) by 20.2% compared to the NHMS. Parametric studies reveal that wall thickness has a greater influence on final deformation than foam density. Numerical results are in good agreement with the proposed SSFE model within the baseline parameter range, with typical deviations below 10%, though larger discrepancies up to 23% are observed for certain extreme combinations of wall thickness and foam density. The hierarchical multi-cell collaborative design and the MCF prediction method presented here can provide practical guidance for designing high-efficiency impact-protective structures. Full article

Accurate prediction of fishing grounds plays a crucial role in supporting the efficient operation of ocean-going fishing vessels. Based on catch data of Chub Mackerel (Scomber japonicus) and multiple concomitant oceanographic variables from 2014 to 2022 in the Northwest Pacific Ocean, we employed four machine learning methods, including Random Forest (RF; scikit-learn v1.7.2), Extreme Gradient Boosting (XGBoost; xgboost v3.1.3), Light Gradient Boosting Machine (LightGBM; lightgbm v4.6.0) and Categorical Boosting (CatBoost; catboost v1.2.8), to construct a prediction model for high-abundance fishing grounds of Chub Mackerel. After selecting the optimal model through evaluation metrics, we applied the SHapley Additive exPlanations (SHAP; shap v0.44.1) method to visualize and interpret the optimal model, quantifying the importance of environmental factors on high-abundance fishing grounds, thus enhancing the interpretability and credibility of the machine learning model. The results indicated that the catch exhibited significant fluctuations at both interannual and intramonthly scales (p < 0.05). The annual catch showed a phased increasing trend, peaking in 2017 and 2018. Monthly catches were highest in September and October. Evaluated against established performance metrics, the RF model demonstrated the highest predictive performance with the highest values of accuracy and F1-score, 76.33% and 77.73%, Precision 72.81%, Recall 83.36%, ROC-AUC 0.8393, respectively, and was therefore selected as the most suitable for predicting Chub Mackerel fishing grounds. SHAP analysis identified the temporal variables year and month as the most influential predictors, followed by chlorophyll-a concentration (Chl-a), sea surface salinity (SSS), and sea surface temperature (SST). SHAP analysis can comprehensively reveal the degree and direction of influence of each variable at both global and local levels. These findings indicate that integrating machine learning with explainability techniques can enhance the scientific robustness and transparency of fishing ground forecasts, providing data-driven support for ecosystem-based fishery management. Full article

The present study aims to provide a comprehensive and integrated analysis of the potential of offshore renewable energy resources in the maritime sector located at the Danube mouth area in the Black Sea, one of the most complex and dynamic hydrological and climatic systems in Eastern Europe. In the current context of climate change, the Danube mouths are of strategic importance due to the specific morphology of the area and the high potential for harnessing multiple renewable sources such as wind, wave, and solar energy. Therefore, this research supports sustainable development and adaptation to climate change. At the same time, predicted climate change may increase the frequency of extreme events, such as storms, sudden changes in water levels, and increased wave heights, which can affect navigational safety, ecosystem integrity, and coastal infrastructure. Thus, this research seeks not only to identify the energy potential of renewable resources but also to assess their risks and vulnerabilities. Using a wide range of data types, three time periods were studied for the main Danube mouth: Sulina and St. George. Both Sulina and St. George present future wind and wave intensification trends, especially in high-emission scenarios, without significant changes in the dominant direction. St. George remains the area with the more intense regime, while Sulina has more moderate episodes, but with a slightly more evident increase in the frequency of 6–12 m/s winds. At the same time, solar radiation shows a slight increase in recent years, especially in the summer season. Harnessing these resources has the potential to, for example, power coastal communities and offshore installations, providing clean and reliable energy while reducing greenhouse gas emissions. Full article

In the Yingjiang area of western Yunnan, precipitation is high throughout the year, making it one of the regions with the highest annual precipitation in mainland China. Extreme rainfall in this region often triggers severe flooding, yet the key mechanism of water vapor transport underlying abnormally heavy precipitation remains unclear. This study used automatic weather station observations of precipitation, the fifth-generation atmospheric reanalysis produced by the European Centre for Medium-Range Weather Forecasts, and Global Data Assimilation System (GDAS) data to analyze, for the first time, large-scale water vapor transport, precipitation mechanisms, and the primary water vapor sources and their contributions in this region. The results show the following: In the Yingjiang area, the water vapor sources at all height levels in summer are dominated by the southwest monsoon water vapor transport pathways, such as the Bay of Bengal and the Arabian Sea, with their total contributions to specific humidity and water vapor flux exceeding 70%. This indicates that low-latitude sea areas such as the Bay of Bengal and the Arabian Sea serve as key moisture source regions for Yingjiang in the global water vapor cycle. Water vapor transport over the windward slope causes strong low-level convergence and high-level divergence phenomena, and the suction effect leads to strong upward motion near the 850 hPa level. The pseudo-equivalent potential temperature isolines tilt along the mountain slope, maintaining an unstable stratification characterized by warm, humid lower layers and cold, dry upper layers, providing favorable thermal conditions for precipitation. In addition, in the summer of 2020, abnormally high southwest seasonal wind and air transport, combined with strong low-level convergence and high-level divergence of the vertical circulation structure, were key factors causing the abnormally high precipitation. This study provides an important reference for the prediction of extreme precipitation and the early warning of rainstorm disasters in the southwest monsoon region in the context of global climate change. Full article

Swimming crab (Portunus trituberculatus) is a commercially valuable species in the Yellow Sea, where recent fluctuations in resource levels have raised concerns about sustainable management. This study aimed to improve the estimation of the carapace length at 50% maturity (L₅₀) using machine learning techniques, providing a more consistent and reproducible framework for visual maturity classification by standardizing image-based decision processes. Using geometric image augmentation (e.g., rotation, flipping, brightness adjustment), Hue–Saturation–Value (HSV) color segmentation, and algorithms, such as Extreme Gradient Boosting (XGB), Support Vector Machine (SVM), Random Forest (RF), and ensemble models, we classified the maturity of female crabs based on gonad color features. Model performance was evaluated using accuracy, AUC, and the TSS, with the ensemble model showing the highest predictive capability. The machine learning-based L₅₀ was estimated at 64.63 mm (±1.73 mm), yielding a narrower uncertainty range than the visually derived L₅₀ of 65.47 mm (±2.89 mm) under the same macroscopic labeling framework. These results suggest that machine learning-assisted maturity classification can enhance the precision and operational consistency of maturity estimation under a standardized framework, while biological accuracy cannot be confirmed in the absence of an independent reference, such as histological validation. Full article

Sea-level rise (SLR), a climate hazard driven by global warming, poses a severe threat to low-lying coastal regions when combined with strong typhoons and storm surges, endangering human lives and socio-economic development. The Guangdong–Hong Kong–Macao Greater Bay Area (GBA) is a core strategic zone for China’s economic development and is increasingly affected by such compound hazards, exacerbating its storm-related disasters amid climate change. Here, we analyze long-term observational data from the GBA using mathematical statistics and simulation methods to address these climate-related challenges. This study predicts future scenarios of extreme water levels in the Guangdong–Hong Kong–Macao Greater Bay Area (GBA), aiming to assess the hazard posed by storm surge disasters under varied sea-level rise (SLR) scenarios. The findings indicate that, under future climate projections, both the extreme water levels in the GBA and the hazard of storm surge disasters in its floodplain areas will exhibit a significant upward trend—with the degree of hazard amplification positively correlated with the magnitude of SLR. This study provides a scientific basis to improve the accuracy of extreme water-level prediction, supporting more reliable short-term early flood warnings. It also offers guidance for optimizing SLR-adapted coastal zone spatial planning, guiding the layout of storm surge control projects and land use in high-hazard areas. Additionally, our results fill a gap in the literature on the SLR’s impact in the GBA and support decision-makers in the GBA in building climate resilience and mitigating disaster hazards. Full article

Photovoltaic (PV) power forecasting has become a key tool for the intelligent management of electrical grids. Since the largest source of error in PV power forecasting originates from uncertainties in solar irradiance prediction, improving the accuracy of solar irradiance forecasts has emerged as an active research topic. This study evaluates multiple random tree-based model versions using a challenging dataset collected at globally distributed stations, spanning elevations from sea level to nearly 4000 m and covering a wide range of climate classes. The originality of the study lies in the synergistic contribution of two elements: the innovative inclusion of diffuse irradiance among the predictors and a comparative analysis of forecast quality across lowland and mountainous locations. In such environments, accurate solar resource forecasting is particularly important for the intelligent management of stand-alone PV systems deployed at high altitudes and in remote, off-grid areas. Overall, the results identify Extremely Randomized Trees (XTRc) as the best-performing model. XTRc achieves Skill Scores ranging from 0.087 to 0.298 across individual stations. The model accuracy remains high even at mountain stations, provided that sky-condition variability is low. Full article

This systematic review synthesizes current scientific knowledge on the drivers of climate variability and change across the South Pacific, with a particular focus on mechanisms influencing tropical cyclone behavior and regional hydroclimatic extremes. The review begins by contextualizing the unique vulnerabilities of Pacific Island nations, which arise from geographic isolation, socio-economic constraints, and extensive coastal exposures. It examines the foundational role of the South Pacific Convergence Zone in organizing regional convection and precipitation and explores the multi-scale climate oscillations that modulate environmental conditions across interannual, decadal, and intraseasonal timescales. The compounding effects of anthropogenic climate change—including rising temperatures, sea-level increase, shifting rainfall regimes, and changing storm characteristics—are critically assessed. Special attention is given to the complex interplay between natural variability and human-induced trends in altering tropical cyclone genesis, tracks, and intensity. The review identifies persistent knowledge gaps, such as data inhomogeneity, limited long-term records, and uncertainties in downscaled projections, and concludes with prioritized research directions aimed at enhancing predictive capacity and supporting climate-resilient adaptation across this highly vulnerable region. Full article

Recent studies have reported a rapid increase in short-duration, high-intensity rainfall over the Seoul Metropolitan Area (SMA), primarily associated with mesoscale convective systems (MCSs), highlighting the need for high-resolution and multi-platform observations for accurate forecasting. To address this challenge, the Korea Meteorological Administration (KMA) established the Korean Precipitation Observation Program (KPOP), an intensive observation network integrating radar, wind lidar, wind profiler, and storm tracker measurements. This study introduces the design and implementation of the KPOP network and evaluates its observational and forecasting value through a heavy rainfall event that occurred on 17 July 2024. Wind lidar data and weather charts reveal that a strong low-level southwesterly jet and enhanced moisture transport from the Yellow Sea played a key role in sustaining a quasi-stationary, line-shaped rainband over the metropolitan region, leading to extreme short-duration rainfall exceeding 100 mm h⁻¹. To investigate the impact of KPOP observations on numerical prediction, preliminary data assimilation experiments were conducted using the Korean Integrated Model-Regional Data Assimilation and Prediction System (KIM-RDAPS) with WRF-3DVAR. The results demonstrate that assimilating wind lidar observations most effectively improved the representation of low-level moisture convergence and spatial structure of the rainband, leading to more accurate simulation of rainfall intensity and timing compared to experiments assimilating storm tracker data alone. These findings confirm that intensive, high-resolution wind observations are critical for improving initial analyses and enhancing the predictability of extreme rainfall events in densely urbanized regions such as the SMA. Full article

Ensuring the safe operation of marine structures requires accurate phase-resolved wave prediction. However, current studies mostly focus on single-model verification and lack a systematic comparison of mainstream architectures under multiple environmental factors on a unified experimental benchmark, thus offering limited guidance for engineering practice. To fill this gap, we conducted a systematic wave-tank evaluation that quantifies how sea state levels, directional spectrum, prediction distance and lead time jointly affect model accuracy. Four architectures—RNN, LSTM, GRU, and TCN—were trained on 7 × 7 probe matrices acquired under sea states levels (4–7), two directional spreading coefficients (n = 2 and 6), five prediction distances (6.7–33.3 m), and lead times of 1–30Δt. Root-mean-square error (RMSE) served as the quantitative metric. Among recurrent architectures, RNN-WP achieved the lowest high-frequency error under mild sea states (SS4, RMSE = 0.28 m), LSTM-WP delivered the best overall accuracy (SS4–5, RMSE ≤ 0.37 m), and GRU-WP excelled in the medium to high frequency band (SS4–5, RMSE ≤ 0.31 m), whereas TCN-WP remained most robust at long horizons and severe sea states (SS7, RMSE = 0.42 m). Increasing sea-state severity raised RMSE by 40–90%, while a narrower directional distribution amplified errors under extreme conditions. Prediction distance and lead time altered model ranking, confirming that nonlinearity, directional spreading, distance and temporal horizon are the dominant controlling factors for deep learning phase resolved wave prediction. Full article

This paper investigates the influence of back-to-back major hurricanes “Helene” and “Milton” which devastated south-eastern regions of the USA in 2024, and the extent to which associated storm surges influenced Extreme Value Analysis (EVA) of the long ocean water level record at Key West, Florida dating back to 1913. The highest recorded storm surge of 890 mm was recorded during a major hurricane event in October 1944, approximately 56 mm higher than the peak of the surge recorded at Key West during hurricane “Wilma” in 2005. Reanalysis of 2023 published EVA results for Key West indicate that despite the devastation of “Helene” and “Milton”, the super-elevation of the ocean water surface above Mean Sea Level (MSL) recorded at the Key West tidal facility during these hurricanes were at or below that which would be expected around once per annum. The timing and location of the peak of the storm surge with high predicted tides is no more than coincidental but remain the governing factors behind realizing record-breaking water levels over the historical record. Full article

Climate change in Antarctica has profound global implications, influencing sea level rise, atmospheric circulation, and the Earth’s energy balance. This study presents a data-driven baseline analysis of meteorological observations from a British Antarctic Survey automatic weather station (2020–2024). Temporal and seasonal analyses reveal strong insolation-driven variability in temperature, snow depth, and solar radiation, reflecting the extreme polar day–night cycle. Correlation analysis highlights solar radiation, upwelling longwave flux, and snow depth as the most reliable predictors of near-surface temperature, while humidity, pressure, and wind speed contribute minimally. A linear regression baseline and a Random Forest model are evaluated for temperature prediction, with the ensemble approach demonstrating superior accuracy. Although the short data span limits long-term trend attribution, the findings underscore the potential of lightweight, reproducible pipelines for site-specific climate monitoring. All analysis codes are openly available in github, enabling transparency and future methodological extensions to advanced, non-linear models and multi-site datasets. Full article

In the context of global climate change and accelerated urbanization, coastal cities face severe threats from storm surges, and accurately predicting coastal water level changes during storm surges has become a core technological demand for disaster prevention and reduction. Storm surges are caused by atmospheric pressure and wind conditions, and their destructive power is closely related to the morphology of the coastline. Traditional tide level prediction models often face difficulties in boundary condition parameterization. Tide level changes result from the combined effect of various complex processes. In past prediction studies, harmonic analysis and numerical simulations have dominated, each with their own limitations. Although machine learning applications in tide prediction have garnered attention, issues such as data inconsistency or missing data still exist. The physical–data fusion approach aims to overcome the limitations of single methods but still faces some challenges. This paper proposes a Deep-Numerical-Reinforcement learning fusion prediction model (DNR), which adopts ensemble learning. First, deep learning models and the numerical model Finite-Volume Coastal Ocean Model (FVCOM) are used to predict tide levels at different tide stations, and then a fusion approach based on the improved reinforcement learning model DDPG_dual is applied for model assimilation. This reinforcement learning fusion model includes a module specifically designed to handle tide extreme points. In the case of the Typhoon Mangkhut storm surge, the DNR model achieved the best results for tide level predictions at six tide stations in the South China Sea. Full article

Extreme climate events—such as heatwaves, floods, and droughts—are increasingly affecting ecosystems, with the global average temperature projected to rise by up to 3 °C (IPCC, 2023) due to anthropogenic greenhouse gas emissions. These changes pose critical challenges to food security, as evidenced by 733 million people facing hunger in 2024. In response, crop modeling considering different climate change scenarios has become a valuable tool to guide the development of climate-resilient agricultural strategies. Despite its nutritional importance and capacity to thrive across diverse environments, Ipomoea batatas (sweet potato) remains understudied in terms of potential spatial distribution forecasting, particularly in regions of high agrobiodiversity such as northwestern South America. Therefore, in this study we modeled the projected distribution of wild and landrace sweet potato genepools in the northern Andes under four future timeframes using seven machine learning algorithms. Our results predicted a 50% reduction in the climatically suitable range for the wild genepool by 2081, coupled with an average altitudinal shift from 1537 to 2216 m above sea level (a.s.l.). For landraces, a 36% reduction was projected by 2080, with a shift from 62 to 1995 m a.s.l. By the end of the century, suitable zones for both wild and cultivated genepools are expected to converge in high-altitude regions such as the Colombian Massif, with additional remnants of wild populations near the mountain range of Farallones de Cali. This modeling approach provides essential insights into the spatial dynamics of I. batatas under climate change, highlighting the need for ex situ conservation planning in vulnerable regions as well as assisted migration to more suitable areas. Future research should integrate edaphic and biotic interaction data to better approach the realized niche of the species and understand potential responses under a niche conservatism assumption, as well as genomic data to account for the species’ intrinsic adaptative potential, overall informing conservation, germplasm mobilization, and pre-breeding strategies that may ultimately secure the role of sweet potato in resilient food systems. Full article