Artificial islands face severe land subsidence (LS) challenges, yet accurate spatiotemporal prediction remains difficult. This study investigates LS patterns on Hengqin Island, China, by integrating Persistent Scatterer Interferometry (PS-InSAR) with machine learning (ML). We analyzed 96 Sentinel-1 images (2016-2023), validating measurements against historical levelling data (RMSE = 3.5 mm/yr). PS-InSAR results revealed a maximum subsidence rate of 334 mm/yr in 2019, which decelerated to 202 mm/yr by 2022. To forecast future deformation, four ML architectures were evaluated. The Back Propagation (BP) neural network demonstrated superior predictive accuracy (RMSE = 2.59 mm, R2 = 0.99). Using the trained BP model, we forecasted LS trends for 2024-2026, indicating persistent risks primarily in areas with high-saturation soft soils. This study pioneers a hybrid framework synergizing PS-InSAR time-series with explainable ML, providing critical insights into the geotechnical stability of artificial islands to support sustainable coastal planning and disaster mitigation.

Groundwater resources are essential to global freshwater supply, and accurate groundwater level prediction is critical for sustainable water resource management. To overcome the limitations of traditional deep learning models in long-sequence groundwater forecasting, including weak generalization, reduced long-term prediction accuracy, and limited interpretability, this study proposes a dual-path Informer-p model integrated with residual theory. The main path captures nonlinear temporal dependencies and long-term hydrological patterns, while the residual path provides a stable linear prediction baseline to enhance local fluctuation representation and robustness to extreme events. The model was validated using long-term groundwater observations from 34 monitoring stations across five major ecosystems in China. Results from representative stations, including Ailao Mountain, showed that Informer-p achieved excellent predictive performance with RMSE = 0.05 m, MAPE = 1.2%, R2 = 0.95, and KGE = 0.95, reducing RMSE and MAPE by 37.5% and 52%, respectively, compared with the original Informer. Across all stations, Informer-p outperformed the original Informer at 22 stations, with the greatest improvement observed in forest ecosystems. SHAP analysis identified window maximum, original groundwater level, and window minimum as the dominant predictive features. The proposed model provides an effective tool for national-scale groundwater level prediction and sustainable groundwater management.

The radial sand-ridge field off the Jiangsu coast is a distinctive landform in a strongly tide-dominated environment, where sediment supply and geomorphic patterns have been profoundly altered by Yellow River course changes, reduced Yangtze-derived sediment, and large-scale reclamation. Focusing on a typical nearshore sector off Dongtai, this study integrates multi-source data from 1979 to 2025, including historical nautical charts, high-precision engineering bathymetry, full-tide hydro-sediment observations, and surficial sediment samples, to quantify seabed erosion–deposition over 46 years and clarify linkages among tidal currents, suspended-sediment transport, and surface grain-size patterns. Surficial sediments from Maozhusha to Jiangjiasha channel systematically fine from north to south: sand-ridge crests are dominated by sandy silt, whereas tidal channels and transition zones are characterized by silty sand and clayey silt. From 1979 to 2025, Zhugensha and its outer flank underwent multi-meter accretion and a marked accretion belt formed between Gaoni and Tiaozini, while the Jiangjiasha channel and adjacent deep troughs experienced persistent scour (local mean rates up to ~0.25 m/a), forming a striped “ridge accretion–trough erosion” pattern. Residual and potential maximum currents in the main channels enhance scour and offshore export of fines, whereas relatively strong depth-averaged flow and near-bed shear on inner sand-ridge flanks favor frequent mobilization and short-range trapping of coarser particles. Suspended-sediment concentration and median grain size are generally positively correlated, with suspension coarsening in high-energy channels but dominated by fine grains on nearshore flats and in deep troughs. These findings refine understanding of muddy-coast geomorphology under strong tides and may inform offshore wind-farm foundation design, navigation-channel maintenance, and coastal-zone management.

The estimated spatiotemporal characteristics of particulate matter in the ocean vary with the measurement method used. This variation introduces considerable uncertainty in our understanding of how particle scattering cross-section, particle size, and carbon content relate to one another at local, regional, and global scales. A more accurate and detailed characterization of the spatiotemporal variations of particles in the water column and of the contribution of different types of particles to the optical parameters of water are crucial for improving our understanding of the marine biogeochemical cycle. In this study, we investigated how composition, size, and particulate organic carbon (POC) content of particulate matter, along with their corresponding optical proxies, change in the upper 200 m of an oligotrophic region in the tropical Western Pacific Ocean. We estimated the contributions of various water components to the particle backscattering coefficient and to POC. Using newly collected, vertically resolved data, we derived depth-resolved net primary productivity (NPP) with the absorption-based production model (AbPM) and the carbon-based production model (CbPM); both models account for vertical variations in water column properties. Our results indicated that particles larger than 8 & micro;m (especially minerals and aggregates) accounted for an increasing amount of POC at depths greater than 100 m, with a maximum at 500 m. In contrast, chlorophyll content decreased steadily with depth. Our comparison of the backscatter and absorption coefficients (optical proxies of POC) had the same trend, although the specific components that contributed to POC were different. Changes in parameters such as particle composition, size, POC content, and their optical proxies all corresponded to changes in the deep chlorophyll maximum (DCM) along the latitudinal gradient. When we compared the NPP estimates from the two approaches, the CbPM yielded higher values than the AbPM in surface waters, likely because of the way particles are distributed vertically. In areas where the DCM was deeper, the AbPM provided a better accounting of how individual components contributed to the NPP. Together, these findings clarify how particle composition and its vertical variability influence POC and inherent optical properties (IOPs) in this oligotrophic region. They also offer a basis for interpreting water column characteristics and assessing how changes in NPP may affect biogeochemical processes.

Knowledge of raindrop size distribution (RSD) is essential for understanding microphysical processes occurring within cloud and precipitation systems, as well as for enhancing the capabilities of numerical models and radar-based quantitative precipitation estimation (QPE). However, observation and study of RSD, especially its temporal and spatial variability, remain quite limited in specific regions. One such region is Southeast China. In this paper, four years of disdrometer data from a south coastal plain site (CPS) and a north hilly inland site (HIS) in the Fujian Province of Southeast China are analyzed and compared to elucidate the characteristics and discrepancies of RSD between these two distinct climatological sites. On this basis, empirical relations between the parameters of Gamma distribution and between radar reflectivity factor (Z) and rain rate (R) are proposed. The results are summarized as follows. (1) In the cases of light to moderate rains, HIS exhibits a higher (lower) concentration of small-size (midsize and large) raindrops with diameters of D < 1 mm (1 ⩽ D < 3 and D ⩾ 3 mm), compared to CPS. Conversely, as the rain intensity increases, the raindrop concentrations across all size categories at CPS gradually exceed those at HIS. (2) RSDs at both sites broaden and exhibit elevated concentrations across most diameter categories as the rain rate increases. (3) For rainfalls with rain rates below 5 mm h−1, collision and coalescence dominate, resulting in unimodal rain spectra at both sites; whereas for stronger rainfalls, breakup intensifies, leading to the development of bimodal rain spectra. (4) HIS experiences more stratiform rains but fewer, weaker convective rains than CPS. Stratiform RSD at HIS possesses more small and large raindrops but fewer midsize raindrops compared to CPS, whereas convective RSD at CPS possesses higher concentrations across all diameter categories. (5) Accordingly, specific Z–R relations at these two sites are proposed and validated for two real cases, demonstrating that the accuracy of radar QPE is effectively improved based on the proposed Z–R relations.

The Water and Sediment Regulation Scheme (WSRS), implemented since 2002, has been essential for controlling water flow and mitigating sediment siltation in the lower Yellow River. However, WSRS was suspended for the first time in 2016 and 2017 due to extremely low water flow. The rapid floodwater discharge over roughly 20 days conducted by WSRS strongly impacts total suspended solids (TSS) distribution in the Yellow River Estuary (YRE). This study employs high-frequency Sentinel-3 OLCI satellite imagery to investigate intraday TSS variations in the YRE under new water-sediment regulation conditions from 2016 to 2023. TSS concentrations were generally low during the 2016 and 2017 flood seasons, but increased markedly after WSRS resumed in 2018. Peak TSS values occurred in July or August, sometimes extending into September and October during autumn floods. A moderately strong positive correlation was observed between TSS concentrations at the river mouth and sediment load at Lijin Station during the flood seasons. The 2018 WSRS event generated an extensive river plume, with average TSS concentrations at the river mouth exceeding 400 g·m−3. From 2018 to 2023, TSS concentrations exhibited a declining trend during flood seasons, attributed to reduced sediment discharge and ongoing sediment accretion in the Yellow River Delta. Our findings highlight Sentinel-3 OLCI as a powerful tool to resolve WSRS-driven sediment dynamics, offering critical guidance for estuarine management.

In the past decade, the synthetic aperture radar interferometry (InSAR) technique has been extensively employed in deltas, making it possible to obtain more subsidence signals. However, the spatiotemporal nonlinearity of land subsidence often results in inaccurate estimations. Based on 72 Sentinel-1A images captured from 2016 to 2021 and the time-series persistent scatterer-interferometric SAR (PS-InSAR) method, we comprehensively analyze the temporal and spatial dynamics of recent land subsidence in the Yellow River Delta (YRD). The findings suggest a notable spatial shift in the subsidence funnel area within this delta region over the past 6 years (2016-2021), with gradual westward movement from the salt fields in the northeast to those in the central north. Additionally, with 2020 as the demarcation point, there was a notable change in magnitude, initially exhibiting acceleration at -333 mm/yr, followed by deceleration at -231 mm/yr and culminating in renewed acceleration at -413 mm/yr. The subsidence characteristics may be attributed to changes in the underground brine reserves, leading to consolidation of the confined aquifer. Furthermore, the ground subsidence trend suddenly slowed at the end of 2019, which we speculate is related to the significant reduction in human activities caused by COVID-19 prevention and control measures.

It is important to determine the relationship between the concentration of chlorophyll a (Chla) and the inherent optical properties (IOPs) of ocean water to develop optical models and algorithms that characterize the biogeochemical properties and estimate biological pumping and carbon flux in this environment. However, previous studies reported relatively large variations in the particulate backscattering coefficient (bbp(λ)) and Chla from more eutrophic high-latitude waters to clear oligotrophic waters, especially in oligotrophic oceanic areas where these two variables have little covariation. In this study, we examined the variability of bbp(λ) and Chla in the euphotic layer in oligotrophic areas of the tropical Western Pacific Ocean and determined the sources of these variations by reassessment of in-situ measurements and the biogeochemical-argo (BGC-Argo) database. Our findings identified covariation of bbp(λ) and Chla in the water column below the deep Chla maximum (DCM) layer, and indicated that there was no significant correlation relationship between bbp(λ) and Chla in the upper layer of the DCM. Particles smaller than 3.2 µm that were in the water column above the DCM layer had a large effect on the bbp(λ) in the vertical profile, but particles larger than 3.2 µm and smaller than 10 µm had the largest effect on the bbp(λ) in the water column below the DCM layer. The contribution of non-algal particles (NAPs) to backscattering is up to 50%, which occurs in the water depth of 50 m and not consistent with the distribution of Chla. Phytoplankton and NAPs were modeled as coated spheres and homogeneous spherical particles to simulate the bbp(λ) of the vertical profile by Aden-Kerker method and Mie theory, and the results also indicated that the backscattering caused by particles less than 20 µm were closer to the measured data when they were below and above the DCM layer, respectively. This relationship also reflects the bbp(λ) of particles in the upper water was significantly affected particle size, but bbp(λ) in the lower water was significantly affected by Chla concentration. This effect may have relationship with phytoplankton photoacclimation and the relationship of a phytoplankton biomass maximum with particle size distribution in the water column according to the previous relevant studies. These characteristics also had spatial and seasonal variations due to changes of Chla concentration at the surface and at different depths. There was mostly a linear relationship between Chla and bbp(700) during winter. During other seasons, the relationship between these two variables was better characterized by a power function (or a logarithmic function) in the lower layer of the DCM. The spatial and vertical relationships between the bbp(λ) and Chla and the corresponding variations in the types of particles described in this study provide parameters that can be used for accurate estimation of regional geochemical processes.

In recent years, noticeable subsidence depressions have occurred along the coastal zone of the Yellow River Delta. In some coastal areas, the average annual subsidence varies from tens of millimeters to hundreds of millimeters. Although some studies have discovered a significant land subsidence funnel in the coastal zone of the Yellow River Delta, it has rarely been reported in recent years. Using Sentinel-1A/1B images from the last five years and permanent scatterers interferometric synthetic aperture radar technology, we found a typical subsidence bowl in the northeastern part of the delta, with a cumulative settlement of nearly 1 m over five years. In addition, we used the approach of soil mechanics to simulate the settlement of confined brine layers with different thicknesses under drainage conditions. We found that the 15 m thick confined aquifer can produce 1 m of settlement for every 15% decrease in water content. The simulation results explain the large settlement of the brine industrial area. This study can provide guidance for brine mining in the future. If we continue to overexploit underground brine, there will be more severe land subsidence in the delta in the future.

Total suspended solids (TSS) can be a useful indicator of environmental change in nearshore coastal environments. Understanding the mechanisms of TSS variations in response to environmental drivers is of broad interest for ecology and geomorphology. The Yellow River Delta (YRD) in China is a fragile coastal region that has been affected by human activities and climate change. Here, we investigated TSS along the YRD shoreline over two decades with time‐series satellite data (2002–2020). We observed that TSS concentration decreased significantly in nearshore waters (5‐m isobath) surrounding the YRD, especially in the LaiZhou Bay. During the same time period, wave height (WH) along the deltaic shoreline and sediment load from the Yellow River have decreased, while sea surface height (SSH) has displayed a positive trend. Our results indicate that WH and SSH play a major role in sediment resuspension and dispersion, while the YSD mildly affected TSS variability along the coast. Monthly bed shear stress triggered by waves was then computed using WH, wave period (WP), and SSH. Bed shear stress and TSS displayed a positive correlation. We concluded that seasonal oscillations in SSH in conjunction with wind waves are responsible for TSS variability in the shallow waters in front of the YRD.

浒苔的暴发会对水体生态环境产生巨大的影响,对此进行遥感监测具有十分重要的意义.本文基于现场同步实测的有色溶解有机物(colored dissolved organic matter,CDOM)吸收系数、叶绿素浓度以及光谱数据建立遥感反演模型,再结合 MODIS 卫星影像提取山东半岛南侧近岸海域在各年份浒苔暴发前后 CDOM 与叶绿素浓度的时空分布特征.结果表明,浒苔的消亡分解会在水体中产生大量的CDOM,但浒苔的生长繁殖同样会消耗CDOM,此外CDOM还受到浒苔暴发时期强烈的光降解作用.在各种因素的综合作用下,研究区海域CDOM浓度在浒苔暴发时期微弱升高,浒苔消亡后CDOM浓度则开始回落.浒苔在暴发期会抑制其他浮游微藻的生长,使研究区海域叶绿素浓度有所降低,而浒苔消亡后叶绿素浓度有所上升.水体中的叶绿素受多种生物地球化学因素的影响,因此叶绿素浓度的降低与浒苔的暴发强度之间没有明确的相关性.遥感反演可以大范围快速地提取水体中各种要素的分布情况,但就浒苔的暴发对海水中各要素的影响机制而言,还需要结合各种生态环境因子进行综合分析.

With the rapid expansion of the scale of deep sea net-cage use in the nearshore area of Hainan Island, tropical cyclone-induced wave hazard assessment is urgently needed. In this study, the wind-wave-current coupled ADCIRC + SWAN model, which considers the effects of tidal and storm surges, was used to simulate tropical cyclone events over the last 33 years. This model adopts an unstructured high-resolution grid with a nearshore resolution of up to 100 m. The compared simulated results and observations during typhoons JEBI (2013), HAIYAN (2013) and KALMAEGI (2014) were in agreement. This study statistically analyzed maximum significant wave heights on the basis of a large set of simulated storm wave level maps to derive the wave heights of different return periods. Then, the results of nearshore wave hazard classification were obtained by applying the affinity propagation (AP) clustering method to dozens of nearshore profiles. The results demonstrate that the risk at any point in the nearshore area of Hainan Island is dominated by the wave hazard type and water depth condition. The wave hazard assessment method developed for Hainan Island will be significant in assisting government decision-making in the rational planning of deep sea net-cage aquaculture.

A cyclone is an intensive synoptic activity that occurs frequently over Baffin Bay. By modifying the large‐scale distribution pattern of sea level pressure, a passing cyclone can serve as an important regulator of sea ice outflow via the Davis Strait. We obtain a nearly 40‐year‐long record (1979/1980–2017/2018) of the sea ice area flux (SIAF) through the Davis Strait and Arctic cyclone activities in winter. A case study and statistical results indicate that the sea ice concentration and motion fields can be greatly altered by the occurrence of cyclones, thereby contributing to changes in sea ice export. Moreover, the effects of cyclones on sea ice export in Baffin Bay are dependent on the spatial distribution pattern of the storms. In terms of the cyclone center count and intensity, the key regions with significant impacts on sea ice export out of Baffin Bay are identified, one around Baffin Island (80°W–60°W, 60°N–70°N) and the other over the southern Labrador Peninsula (70°W–50°W, 40°N–60°N). A robust correlation exists between the winter‐accumulated SIAF via the Davis Strait and the average winter cyclone intensity (center count) in the critical regions with R = −0.57 (+0.49), affirming the vital role of cyclone activity in modulating the interannual variability of sea ice export in Baffin Bay.

Recently, many of the world's major river deltas have been sinking, making them increasingly vulnerable to floods and storm surges, salinization and permanent inundation. For the Yellow River delta, annual subsidence rates of several to dozens of centimeters have been reported in the past few years. The extraction of a considerable amount of groundwater due to continuous pumping is suggested as the main driver of the groundwater depression cone. Despite its scale and severity, methods to quantify subsidence are scarce. We introduce a soil mechanics approach to quantify subsidence due to the compaction of soft soil. The largest reduction in soft soil thickness, which is more than 2.6 m, occurred in the salt field area to the north of the Yellow River. Furthermore, by estimating the primary consolidation of soft soil, the subsidence caused by groundwater exploitation is quantified. In the coastal area of the delta, due to excessive exploitation of shallow underground brine resources, the maximum accumulated subsidence is as high as 2 m. Since the natural consolidation of these deltaic sediments has ended, if the current groundwater exploitation intensity is maintained, major subsidence disasters, such as subsidence depressions and ground fissures, will occur.

Islands are one of the most sensitive interfaces between global changes and land and sea dynamic effects, with high sensitivity and low stability. Therefore, under the dynamic coupling effect of human activities and frequent natural disasters, the vulnerability of the ecological environment of islands shows the characteristics of complexity and diversity. For the protection of island ecosystems, a system for the assessment of island ecosystems and studies on the mechanism of island ecological vulnerability are highly crucial. In this study, the North and South Changshan Islands of China were selected as the study area. Considering various impact factors of island ecological vulnerability, the geographical information systems (GIS) spatial analysis, field surveys, data sampling were used to evaluate island ecological vulnerability. The Bayesian network model was used to explore the impact mechanism of ecological vulnerability. The results showed that the ecological vulnerability of the North Changshan Island is higher than that of the South Changshan Island. Among all the indicators, the proportion of net primary productivity (NPP) and the steep slope has the strongest correlation with ecological vulnerability. This study can be used as references in the relevant departments to formulate management policies and promote the sustainable development of islands and their surrounding waters.

The power law particle size distribution (PSD) slope parameter is commonly used to characterize sediment fluxes, resuspension, aggregates, and settling rates in coastal and estuarine waters. However, particle size distribution metrics are also very useful for understanding sediment source and dynamic processes. In this study, a method was proposed to employ the particle size parameters commonly used in sedimentary geology (average particle size (ø), sorting, skewness, and kurtosis) as indicators of changes in sediment dynamic processes, and MODIS images were used to estimate these parameters. The particle size parameters were estimated using a Mie scattering model, Quasi-Analytical Algorithm (QAA) analysis algorithm, and least squares QR decomposition (LSQR) solution method based on the relationship between the power law distribution of the suspended particles and their optical scattering properties. The estimates were verified by field measurements in the Yellow Sea and Bohai Sea regions of China. This method provided good estimates of the average particle size (ø), sorting, and kurtosis. A greater number of wavebands (39) was associated with more accurate particle size distribution curves. Furthermore, the method was used to monitor changes in suspended particulate matter in the vicinity of the Heini Bay of China before and after the passage of a strong storm in August 2011. The particle size parameters represented the influence of a strong typhoon on the distribution of the near-shore sediment and, together with the PSD slope, comprehensively reflected the changes in the near-shore suspended particulate matter. This method not only established the relationship between remote sensing monitoring and the historical sediment record, it also extends the power law model to the application of sediment source and dynamic processes in coastal waters.

The current storm wave hazard assessment tends to rely on a statistical method using wave models and fewer historical data which do not consider the effects of tidal and storm surge. In this paper, the wave-current coupled model ADCIRC+SWAN was used to hindcast storm events in the last 30 years. We simulated storm wave on the basis of a large set of historical storms in the North-West Pacific Basin between 1985 and 2015 in Houshui Bay using the wave-current coupled model ADCIRC+SWAN to obtain the storm wave level maps. The results were used for the statistical analysis of the maximum significant wave heights in Houshui Bay and the behavior of wave associated with storm track. Comparisons made between observations and simulated results during typhoon Rammasun (2014) indicate agreement. In addition, results demonstrate that significant wave height in Houshui Bay is dominated by the storm wind velocity and the storm track. Two groups of synthetic storm tracks were designed to further investigate the worst case of typhoon scenarios. The storm wave analysis method developed for the Houshui Bay is significant in assisting government’s decision-making in rational planning of deep sea net-cage culture. The method can be applied to other bays in the Hainan Island as well.

Kelp aquaculture is one of the most important exploitation and utilization activities in coastal areas. The impacts of high-density kelp aquaculture on coastal area environments are attracting increasing attention. Based on in situ data from the suspended kelp aquaculture area of Heini Bay, numerical simulations were applied to distinguish hydrodynamic and sediment transport features under natural and aquaculture conditions. By comparing model simulations with observations, the calibrated models reflected the hydrodynamic conditions and sedimentary environments in Heini Bay well. Although the kelp scenario model was calibrated by data measured in an early stage of aquaculture and produced a relatively conservative result, the model was able to simulate the trend of sedimentary environment changes in the aquaculture area. The results of the simulations indicated that, after the occurrence of aquaculture activities, the average velocity was reduced by approximately 21% in the waters around Chu Island and Moye Island, and by 50% within the kelp aquaculture area. Along the western edges of the aquaculture area (i.e., the nearshore area), the average velocity barely changed, but the instantaneous velocity during the flood/ebb tide may increase by up to 3 times. The annual maximum erosion rate around Chu Island, Moye Island and Heishi Reef decreased by approximately 30%, and the total range of the erosion area where the erosion intensity was not less than 0.01 m/yr decreased by almost 36%. The deposition area in Heini Bay shifted to deeper waters, and almost the entire kelp aquaculture area was in a deposition state. However, the deposition rates in the aquaculture area were reduced accordingly.

Episodic floods and storm events have significantly impacted the marine sedimentary environment and hydrodynamic processes of inner shelf regions. The influence of a storm event on the coastal sedimentary environment depends on its trajectory and intensity, making it difficult to forecast the environmental impact. We analyzed the grain size distributions and time-series of settling particulate matter during Tropical Storm Muifa by collection of settling particulate samples and surface sediment samples before and after the storm from the inner-shelf of Heini Bay, China. We determined end-member components from shallow sediment core data and sediment trap data using end-member modeling with coupled cluster analysis. The results show that this storm event increased the mean grain size of seafloor sediment due to the addition of coarser particles, but did not increase the particle size range of settling particles. These findings are confirmed by the extremely leptokurtic distribution of particle size and the single-peak at 50-53 mu m, indicative of improved sorting and very positive skewing during the storm period. Furthermore, the storm carried these coarser particles into the bay, so there was a coarser sediment texture in the middle of the bay. In addition, we identified a common end-member component responding to this extreme weather event from the settling sediment particles during Tropical Storm Muifa and the nearby shallow sediment core samples. Our reconstruction of this historical extreme weather event indicated there were two sedimentary fragments that corresponded to two high-frequency periods of historical storm events. This indicates that storm events redistribute sediment in the seafloor and cause structural changes of grain size composition.

Unlike the rapid decline of Arctic sea ice in the warming climate, Antarctic sea‐ice extent exhibits a modest positive trend in the period of near four decades. In recent years, the fluctuation in Antarctic sea ice has been strengthened, including a decrease toward the lowest sea‐ice extent in February 2011 for the period of 1978–2016 and a strong rebound in the summer of 2012. The sea‐ice recovery mainly occurs in the Weddell Sea, Bellingshausen Sea, Amundsen Sea, southern Ross Sea, and the eastern Somov Sea. This study offers a new mechanism for this summertime sea‐ice rebound. We demonstrate that cloud‐fraction anomalies in winter 2011 contributed to the positive Antarctic sea‐ice anomaly in summer 2012. The results show that the negative cloud‐fraction anomalies in winter 2011 related to the large‐scale atmospheric circulation resulted in a substantial negative surface‐radiation budget, which cooled the surface and promoted more sea‐ice growth. The sea‐ice growth anomalies due to the negative cloud forcing propagated by sea‐ice motion vectors from September 2011 to January 2012. The distribution of the sea‐ice anomalies corresponded well with the sea‐ice concentration anomalies in February 2012 in the Weddell Sea and eastern Somov Sea. Thus, negative cloud‐fraction anomalies in winter can play a vital role in the following summer sea‐ice distribution.