Automatic cloud detection in remote sensing images is of great significance. Deep-learning-based methods can achieve cloud detection with high accuracy; however, network training heavily relies on a large number of labels. Manually labelling pixel-wise level cloud and non-cloud annotations for many remote sensing images is laborious and requires expert-level knowledge. Different types of satellite images cannot share a set of training data, due to the difference in spectral range and spatial resolution between them. Hence, labelled samples in each upcoming satellite image are required to train a new deep-learning-based model. In order to overcome such a limitation, a novel cloud detection algorithm based on a spectral library and convolutional neural network (CD-SLCNN) was proposed in this paper. In this method, the residual learning and one-dimensional CNN (Res-1D-CNN) was used to accurately capture the spectral information of the pixels based on the prior spectral library, effectively preventing errors due to the uncertainties in thin clouds, broken clouds, and clear-sky pixels during remote sensing interpretation. Benefiting from data simulation, the method is suitable for the cloud detection of different types of multispectral data. A total of 62 Landsat-8 Operational Land Imagers (OLI), 25 Moderate Resolution Imaging Spectroradiometers (MODIS), and 20 Sentinel-2 satellite images acquired at different times and over different types of underlying surfaces, such as a high vegetation coverage, urban area, bare soil, water, and mountains, were used for cloud detection validation and quantitative analysis, and the cloud detection results were compared with the results from the function of the mask, MODIS cloud mask, support vector machine, and random forest. The comparison revealed that the CD-SLCNN method achieved the best performance, with a higher overall accuracy (95.6%, 95.36%, 94.27%) and mean intersection over union (77.82%, 77.94%, 77.23%) on the Landsat-8 OLI, MODIS, and Sentinel-2 data, respectively. The CD-SLCNN algorithm produced consistent results with a more accurate cloud contour on thick, thin, and broken clouds over a diverse underlying surface, and had a stable performance regarding bright surfaces, such as buildings, ice, and snow.

From the time that it first develops, a sea surface temperature anomaly (SSTA) will develop in space and time until it dissipates. Although many SST products are available, great challenges are still faced when attempting to directly explore the evolution of SSTAs. To address some of these problems, in this study, we developed a global SSTA dataset that included details of the spatial structure of SSTAs and their temporal evolution. This dataset is called GDPoSSTA. GDPoSSTA is comprised of three datasets and two relationship files and covers the period from January 1982 to December 2009. The three datasets are in SHP format and consist of a dataset of processed object-oriented SSTAs named DSPOSSTA, a dataset of sequenced object-oriented SSTA series named DSSOSSTA, and a dataset of variation object-oriented SSTA named DSVOSSTA. The two relationship files, which are in CSV format, store the evolving behavior of the SSTA sequence object and SSTA variation objects. Finally, geographic spatiotemporal statistics are derived for the DSPOSSTA and a comparison of applying TITAN to DSVOSSTA and DSPOSSTA is carried out which demonstrates the feasibility and applicability of GDPoSSTA. The GDPoSSTA dataset is available on ScienceDB platform (http://www.doi.org/10.11922/sciencedb.j00076.00090).

The ablation of Arctic sea ice makes seasonal navigation possible in the Arctic region, which accounted for the apparent influence of sea ice concentration in the navigation of the Arctic route. This paper uses Arctic sea ice concentration daily data from January 1, 2000, to December 31, 2019. We used a sea ice concentration threshold value of 40% to define the time window for navigating through the Arctic Northeast Passage (NEP). In addition, for the year when the navigation time of the NEP is relatively abnormal, we combined with wind field, temperature, temperature anomaly, sea ice age and sea ice movement data to analyze the sea ice conditions of the NEP and obtain the main factors affecting the navigation of the NEP. The results reveal the following: (1) The sea ice concentration of the NEP varies greatly seasonally. The best month for navigation is September. The opening time of the NEP varies from late July to early September, the end of navigation is concentrated in mid-October, and the navigation time is basically maintained at more than 30 days. (2) The NEP was not navigable in 2000, 2001, 2003 and 2004. The main factors are the high amount of multi-year ice, low temperature and the wind field blowing towards the Vilkitsky Strait and sea ice movement. The navigation time in 2012, 2015 and 2019 was longer, and the driving factors were the high temperature, weak wind and low amount of one-year ice. The navigation time in 2003, 2007 and 2013 was shorter, and the influencing factors were the strong wind field blowing towards the Vilkitsky Strait. (3) The key navigable areas of the NEP are the central part of the East Siberian Sea and the Vilkitsky Strait, and the Vilkitsky Strait has a greater impact on the NEP than the central part of the East Siberian Sea. The main reason for the high concentration of sea ice in the central part of the East Siberian Sea (2000 and 2001) was the large amount of multi-year ice. The main reason for the high concentration of sea ice in the Vilkitsky Strait (2000 to 2004 and 2007, 2013) was the strong offshore wind in summer, all of which were above 4 m s⁻¹, pushing the sea ice near the Vilkitsky Strait to accumulate in the strait, thus affecting the opening of the NEP.

The 44 years (1979–2022) of satellite-derived sea ice extent in the Arctic and Antarctic reveals the details and new trends in the process of polar sea ice coverage changes. The speed of Arctic sea ice extent reduction and the interannual difference significantly increased after 2004. Trend analysis suggests that the Arctic Ocean may experience an ice-free period around 2060. The maximum anomaly of Arctic sea ice extent has gradually transitioned from September to October, indicating a trend of prolonged melting period. The center of gravity of sea ice in the Arctic Ocean is biased towards the Pacific side, and the spatial distribution pattern of sea ice is greatly influenced by the Atlantic warm current. The dynamism of the sea ice extent on the Atlantic side is significantly greater than in other regions. Since 2014, the Antarctic sea ice extent has shifted from slow growth to a rapid decreasing trend; the sea ice extent reached a historical minimum in 2022, decreasing by 2.02 × 106 km² compared to 2014. The Antarctic experiences seven months of ice growth each year and five months of ice melting period, the annual change patterns of sea ice extent in the Arctic and Antarctic are slightly different.

Spatiotemporal clustering patterns of marine anomaly variations are the focus of much current global climate change research. Marine anomaly variations have multidimensional attributes and are spatiotemporally continuous; existing methods for clustering face challenges in mining effectively their spatiotemporal clustering patterns. Using long-term marine remote sensing products, we present the dual-constraint spatiotemporal clustering approach (DcSTCA) for exploring marine clustering patterns. The DcSTCA includes three steps. The first step constructs a spatiotemporal grid cube based on the spatial connectivity and time evolution process of marine anomaly variations, which is used to search the spatiotemporal neighborhood. The second step calculates the proximities in space, time, and thematic attribute to obtain the spatiotemporal clustering cores and spatiotemporal density of each grid cell. The final step derives spatiotemporal clustering patterns by connecting the clustering cores and their spatiotemporal neighbors according to their density connectivity. Experiments on simulated datasets are used to demonstrate the effectiveness and the advantages of the DcSTCA compared with spatial–temporal density-based spatial clustering of applications with noise (ST-DBSCAN). The applications on sea surface temperature in the Pacific Ocean show that the DcSTCA can effectively explore marine clustering patterns from remote sensing products, and these mined clustering patterns may provide new references for global change research.

The value of ecosystem regulation services (ERSV) is a crucial aspect of gross ecosystem product (GEP). Understanding and mastering the spatiotemporal evolution characteristics and driving factors of ERSV is essential for the efficient management of regional ecosystems. This study proposes an ERSV accounting model at the plot scale and uses the barycentric analysis method, the optimal parameters-based geographical detector model (OPGD), and the constraint line extraction method to analyze the spatiotemporal evolution characteristics, main driving factors, and constraint rules of ERSV in Yunyang District, Hubei Province in 2016, 2018, 2020, and 2021. The results show that (1) In the temporal dimension, the overall ERSV of the district increased by CNY 1.664 billion from 2016 to 2021, with an increase rate of 3.68%. The contribution values of climate regulation function and water retention function to ERSV was significant. (2) In the spatial dimension, the ERSV was high in the north and south and low in the middle, with high-value areas mainly located in woodland and wetland areas. The center of gravity of the ERSV increase shifted to the southwest by 12,455.42 m, while the center of gravity of the reduction shifted to the southwest by 3582.79 m from 2016 to 2021. (3) The interaction of any two driving factors had greater explanatory power for the spatial differentiation of ERSV than that of a single driving factor, and all of them showed nonlinear or double factor enhancement characteristics. The human active index (HAI) and construction land proportion (CLP) were the leading anthropogenic factors, while the land surface temperature (LST) and NDVI were the leading natural factors. (4) The ERSV could maintain a high and stable value output when the HAI was less than 0.3, CLP was less than 15%, LST was between 18 and 22 °C, and NDVI was greater than 0.5. These results can guide the practices of ecology, production, and life in Yunyang District and contribute to the high quality and sustainable development of the regional ecology and economy.