ABSTRACT Long-term changes and year-to-year variability in sea ice conditions on the northern Labrador (Nunatsiavut) coast and shelf have important influences on regional climate, marine ecosystems, and coastal communities. The drivers of sea ice variability in this region are poorly understood despite being critical for planning for future changes. Here, we evaluate the spatial and temporal trends and variability of sea ice area, concentration, thickness, and volume over the Labrador Shelf between 1979 and 2021 based on Canadian Ice Service sea ice charts. We characterise the seasonal cycle into two phases: a growth phase (December to January) and a peak phase (February to April). We then use Empirical Orthogonal Function analysis on mean ice thickness to identify the dominant modes of variability, and use correlations and simple physical models to investigate the relationships between these modes and thermodynamic forcing variables. Around 68% of the total variability can be explained by the first two modes (Mode 1: 52.6%; Mode 2: 15.2%). The first mode represents sea ice volume changes across the entire shelf, mainly driven by remote air temperature variations, with a smaller but non-negligible influence from local anomalies. The second mode represents a cross-shelf dipole structure that may be linked to the dynamic effects of winds and ocean currents.

Monitoring sea ice in the Arctic region is crucial for polar maritime activities. The Canadian Ice Service (CIS) wants to augment its manual interpretation with machine learning-based approaches due to the increasing data volume received from newly launched synthetic aperture radar (SAR) satellites. However, fully supervised machine learning models require large training datasets, which are usually limited in the sea ice classification field. To address this issue, we propose a semi-supervised interactive system to classify sea ice in dual-pol RADARSAT-2 imagery using limited training samples. First, the SAR image is oversegmented into homogeneous regions. Then, a graph is constructed based on the segmentation results, and the feature set of each node is characterized by a convolutional neural network. Finally, a graph convolutional network (GCN) is employed to classify the whole graph using limited labeled nodes automatically. The proposed method is evaluated on a published dataset. Compared with referenced algorithms, this new method outperforms in both qualitative and quantitative aspects.

Abstract. The Canadian Arctic Archipelago (CAA) serves as both a source and a sink for sea ice from the Arctic Ocean, while also exporting sea ice into Baffin Bay. We use observations from Sentinel-1, RADARSAT-2, the RADARSAT Constellation Mission (RCM), and CryoSat-2, together with the Canadian Ice Service ice charts, to quantify sea ice transport and replenishment across and within the CAA from 2016 to 2022. We also provide the first estimates of the ice area and volume flux within the CAA from the Queen Elizabeth Islands to Parry Channel, which spans the central region of the Northwest Passage shipping route. Results indicate that the CAA primarily exports ice to the Arctic Ocean and Baffin Bay, with an average annual (October to September) ice area flux of 137 ± 72 × 103 km2 and a volume flux of 58 ± 68 km3. The CAA contributes a larger area but smaller volume of ice downstream to the North Atlantic than what is delivered via Nares Strait. The average annual ice area flux from the Queen Elizabeth Islands to Parry Channel was 27 ± 10 × 103 km2 and the volume flux was 34 ± 12 km3, with a majority occurring through Byam Martin Channel, which is directly above the central region of Northwest Passage. Over our study period, annual multi-year ice (MYI) replenishment within the CAA was resilient, with an average of 14 ± 38 × 103 km2 imported from the Arctic Ocean and an average of 56 ± 36 × 103 km2 of first-year ice (FYI) retained following the melt season. The considerable ice flux to Parry Channel, together with sustained MYI replenishment, emphasizes the continued risk that sea ice poses to practical utilization of key shipping routes in the CAA, including the Northwest Passage.

The ice phenology of freshwater lakes throughout the Northern Hemisphere has undergone important climate-induced shifts over the past century. In Canada's North, where freshwater lakes and wetlands cover 15 to 40% of the landscape, monitoring ice phenology is vital to understand its impacts on climate, socio-economic, ecological, and hydrological systems. The rapid and dynamic nature of ice phenology events has restricted monitoring efforts to the use of satellite sensors with frequent revisit times (e.g., MODIS, AVHRR), but their low resolution (e.g., > 500 m) limits observations to larger water bodies. However, the increased abundance of high-resolution open-access satellite imagery combined with the rise of cloud-computing technologies has provided opportunities to reduce the trade-off between temporal (i.e., revisit time) and spatial (i.e., pixel size) resolution allowing for lake ice monitoring over broad scales. In this study, we present the Open Pixel-based Earth eNgine Ice (OPEN-ICE) algorithm implemented in Google Earth Engine (GEE), which classifies imagery from multiple open-access optical sensors, then combines them to construct dense annual time series of ice-water observations and estimate pixel spring breakup dates at a 30-m resolution. Using Landsat 7 ETM+, Landsat 8 OLI, and Sentinel-2 MSI scenes over lakes spanning northern latitudes, we build reference datasets to train decision trees that discriminate between ice, water, and clouds. We combine ice-water classifications from each sensor into annual time series and remove misclassifications with a temporal filter applied using a pixel-wise logistic regression. We then detect the sequence of transition from ice to water in each pixel's time series to estimate the occurrence of breakup each year. We deploy the OPEN-ICE algorithm over all freshwater pixels of Canada for the period of 2013 to 2021. Spring ice phenology events estimated by OPEN-ICE show high accuracy when compared to whole-lake breakup dates measured by the Canadian Ice Service in 105 lakes across 9 years, with mean bias errors of −1.10 and − 0.69 days for breakup start and end, respectively. We apply the OPEN-ICE algorithm to 4000 lakes across Canada and evaluate differences in breakup dates across ecozones and lake sizes. Our new OPEN-ICE tool provides accurate estimates of annual spring breakup events applicable across all boreal and arctic regions to monitor the rapid changes taking place in these vulnerable ecosystems.

Though polar ecologists consider sea ice primarily as a habitat for marine mammals, caribou use sea ice to complete their reproductive cycles, to access areas with preferred climatic and vegetation conditions, and to avoid predators seasonally and sporadically. Building on previous caribou research in Uqsuqtuuq (Gjoa Haven, Nunavut), we explored the connections between caribou and sea ice phenology in 5 community-identified caribou crossing areas around Qikiqtaq (King William Island). We defined freeze-up and breakup based on Uqsuqtuurmiut (people of Uqsuqtuuq) knowledge of caribou habitat requirements, to orient our analysis to the complex and multifaceted hazards that caribou can encounter while moving through their dynamic and unpredictable sea ice habitat. We investigated the reliability of caribou sea ice habitat surrounding Qikiqtaq, prioritizing key transitional periods with intensified caribou movement. We use regional ice charts produced by the Canadian Ice Service (CIS) and held workshops with Uqsuqtuurmiut to understand how sea ice phenology and caribou mobility have changed over time. The high spatial and temporal variability of sea ice phenology around Qikiqtaq facilitates caribou moving across sea ice should they need to respond to seasonal or unpredictable changes in ecological conditions or anthropogenic disturbance. Therefore, these localized sea ice conditions may increase caribou resiliency to changes or extreme events by providing alternative options for movement across the sea ice. We encourage others to consider the needs of wildlife sea ice users when assessing or providing ice information.

Arctic amplification has many impacts on sea-ice extent, thickness, and flux. It becomes critical to monitor sea-ice conditions at finer spatio-temporal resolution. We used a simple convolutional neural network (CNN) on the RADARSAT-2 dual-polarized ScanSAR wide archive available over Coronation Gulf, Canada, to assess which SAR parameter improves model performances to classify sea ice from water on a large volume of data covering 11 years of ice and surface water conditions. An overall accuracy of 90.1% was achieved on 989 scenes of 100% ice cover or ice-free conditions. An accuracy of 86.3% was achieved on the last year of data (134 scenes) which was kept out of the training process to test the model on an independent dataset. A better accuracy is obtained at lower incidence angles and the HH polarization provides the most information to classify ice from water. To achieve the best accuracy, the incidence angle and the noise equivalent sigma-nought had to be included as input to the model. A comparison done with the ASI passive microwave product shows similar errors in total sea ice concentration when using the Canadian Ice Service regional charts as reference. Nonetheless, errors from both datasets differ and the CNN outputs show greater potential to reduce masked areas, given the better spatial resolution, enabling data classification closer to land and identify features not captured by the ASI dataset.

In this study, sea ice edge derived from three passive microwave (PM) algorithms, ARTIST sea ice (ASI), enhanced NASA Team 2 (NT2), and Bootstrap (BT), are compared to those derived from the daily Canadian Ice Service charts over a primarily seasonal ice zone in the eastern Canadian Arctic for 2013–2021. To determine the ice edge error, we introduced an edge-length-based displacement measure called the edge displacement error (EDE), a dimensionless measurement obtained by dividing the weighted average Hausdorff distance by the ice edge length. We found that the ASI algorithm has the highest EDE on average, while the BT algorithm has the lowest one. In October (the beginning of the freeze-up period), the ice edge exhibits significant meandering, and the EDE is less sensitive to changes in the charted area. In the freeze-up period, the PM algorithms have the highest mean EDE value relative to other months due to the appearance of thin ice. A greater range of EDE values was observed in April than in other months. Throughout this region, the wind speed varies the most in April and May, whereas in April, the air temperature fluctuates more than in the other months.

Through analysis of Canadian Ice Service ice charts, we have characterized the temporal and spatial variability of landfast sea ice (or fast ice) surrounding Hudson Bay and James Bay from 2000 to 2019. Over this 19-year period, we observed contrasting changes in fast-ice persistence between the western and eastern sides of Hudson Bay and James Bay. Fast ice in western Hudson Bay and James Bay trended towards later freeze-up and earlier break-up that resulted in a shortening of the fast-ice season at a rate of 6 days/decade. Contrastingly, eastern Hudson Bay and James Bay showcased relatively earlier freeze-up and delayed break-up, and an overall trend towards a longer fast-ice season at a rate of 8 days/decade. The general trend in air temperature followed a similar spatial pattern to the changing fast-ice persistence; however, the timing of fast-ice break-up did not have a strong relationship with the thawing-degree days during spring. Variations in fast-ice area showed latitudinal and meridional gradients, with greater fast-ice area in eastern Hudson Bay and James Bay compared to the west. Given the overall warming trend in the Arctic, observing areas of decreasing fast-ice persistence is unexpected; however, this study highlights the role of regional factors, such as coastal orientation and bathymetry, in controlling the stability, growth and decay of fast ice.

ABSTRACT Intra-annual and decadal observations of snow depth on sea ice and on terrestrial land are examined within the Canadian Arctic. In situ snow depth measurements at 11 study sites spanning 1955–2019 form the basis of the analysis. Ice chart data acquired via the Canadian Ice Service are used to establish sea ice break-up and freeze-up dates and assess their impact on snow depth evolution. We find that on-ice and on-land snow accumulation in autumn differ due to the lag between the freeze-up and the first snow of the season. Once sea ice consolidates, on-ice and on-land snow depth become positively correlated in winter (p < 0.05). The mean seasonal rate of snow accumulation on sea ice from September to April is 3.2 ± 0.6 cm month−1 across the Canadian Arctic. Snow depth on terrestrial land is generally higher than on sea ice in the southern Canadian Arctic by up to 20–30 cm; but snow depth on sea ice tends to exceed that on land in the northern Canadian Arctic from winter to spring. Four sites (Eureka, Resolute, Cambridge Bay and Hall Beach) with continuous long-term records are selected for interannual analysis. Decadal trends in on-ice snow depth are mostly negative from autumn to spring. Autumn and spring snowfall have increased at three of the four sites. The Canadian Arctic experiences warming on a decadal scale, especially in autumn, by 0.5 to 0.8°C decade−1. Sea ice freeze-up is delayed by up to 2.5 days decade−1 in the southern Canadian Arctic, whereas break-up occurs earlier by about 3 days decade−1 in the northern Canadian Arctic.

The distribution of sea ice is one of the major safety hazards for sea navigation. As human activities in polar regions become more frequent, monitoring and forecasting of sea ice are of great significance. In this paper, we use SAR data from the C-band synthetic aperture radar (SAR) Gaofen-3 satellite in the dual-polarization (VV, VH) fine strip II (FSII) mode of operation to study the Arctic sea ice classification in winter. SAR data we use were taken in the western Arctic Ocean from January to February 2020. We classify the sea ice into four categories, namely new ice (NI), thin first-year ice (tI), thick first-year ice (TI), and old ice (OI), by referring to the ice maps provided by the Canadian Ice Service (CIS). Then, we use the deep learning model MobileNetV3 as the backbone network, input samples of different sizes, and combine the backbone network with multiscale feature fusion methods to build a deep learning model called Multiscale MobileNet (MSMN). Dual-polarization SAR data are used to synthesize pseudocolor images and produce samples of sizes 16 × 16 × 3, 32 × 32 × 3, and 64 × 64 × 3 as input. Ultimately, MSMN can reach over 95% classification accuracy on testing SAR sea ice images. The classification results using only VV polarization or VH polarization data are tested, and it is found that using dual-polarization data could improve the classification accuracy by 10.05% and 9.35%, respectively. When other classification models are trained using the training data from this paper for comparison, the accuracy of MSMN is 4.86% and 1.84% higher on average than that of the model built using convolutional neural networks (CNNs) and ResNet18 model, respectively.

Fully polarimetric (FP) SAR systems offer parameters that describe and quantify the scattering mechanisms from the surface cover. These are usually derived from decomposition of matrices derived from the original scattering matrix from observations at each pixel. Power from scattering mechanisms have potential for retrieval of sea ice information, which cannot be derived using traditional backscatter (magnitude or phase) measured by single- or dual-polarization SAR systems. This study investigates the potential of selected FP parameters that represent the power of three scattering mechanisms, in addition to the total power, in identifying ice types and surface features for operational use. Parameters were obtained from a set of 62 RADARSAT-2 Quad-pol data over Resolute Passage, central Arctic, during the period September-December 2017. A scattering-based color-composite scheme was developed. Analysis of the examined color images was supported by information from regional ice charts and SAR image interpretations from the Canadian Ice Service. Case studies are presented to demonstrate the potential of the proposed color-composite tool. Open water, new ice, multi-year ice and a few surface features including rafted, ridged and smooth/rough surfaces can be identified better in the color images. Physical interpretation of the relative power from the given scattering mechanisms is explained for the relevant ice types and surfaces.

Abstract First‐year ice (FYI) and multi‐year ice (MYI) are the two most common ice types in the Arctic. In this article, the classification of FYI and MYI over the Arctic region in the winter of 2019/2020 and 2020/2021 is investigated by combining the data of the scatterometer on Chinese‐French Oceanography Satellite (CFOSCAT) and the Advanced Microwave Scanning Radiometer‐2 (AMSR‐2) based on the Tree Augmented Naive Bayes (TAN) classifier. The CFOSCAT/AMSR ice type classification results are validated by using Ocean and Sea Ice Satellite Application Facility (OSI SAF) sea ice type products, Canadian Ice Service ice charts, and synthetic‐aperture radar data. The results showed that the overall MYI extent change trend retrieved from CFOSCAT/AMSR was consistent with the OSI SAF product with a correlation coefficient of 0.89 for winter of 2019/2020 and 0.88 for 2020/2021. In addition, CFOSCAT/AMSR identified a slightly larger MYI extent than OSI SAF and the average deviation between them is 10.1% for 2019/2020 while 8.3% for 2020/2021. Besides, CFOSCAT/AMSR can identify more MYI pixels when the MYI concentration is relatively low in the Western Arctic region. We also used CFOSCAT data only to retrieve ice type and found that the active and passive microwave data fusion could capture more MYI pixels located near the boundary of MYI and FYI main body, and the introduction of AMSR‐2 data in ice type classification could reduce the error caused by the abnormal values of CFOSCAT parameters.

With the increasing availability of SAR imagery in recent years, more research is being conducted using deep learning (DL) for the classification of ice and open water; however, ice and open water classification using conventional DL methods such as convolutional neural networks (CNNs) is not yet accurate enough to replace manual analysis for operational ice chart mapping. Understanding the uncertainties associated with CNN model predictions can help to quantify errors and, therefore, guide efforts on potential enhancements using more–advanced DL models and/or synergistic approaches. This paper evaluates an approach for estimating the aleatoric uncertainty [a measure used to identify the noise inherent in data] of CNN probabilities to map ice and open water with a custom loss function applied to RADARSAT–2 HH and HV observations. The images were acquired during the 2014 ice season of Lake Erie and Lake Ontario, two of the five Laurentian Great Lakes of North America. Operational image analysis charts from the Canadian Ice Service (CIS), which are based on visual interpretation of SAR imagery, are used to provide training and testing labels for the CNN model and to evaluate the accuracy of the model predictions. Bathymetry, as a variable that has an impact on the ice regime of lakes, was also incorporated during model training in supplementary experiments. Adding aleatoric loss and bathymetry information improved the accuracy of mapping water and ice. Results are evaluated quantitatively (accuracy metrics) and qualitatively (visual comparisons). Ice and open water scores were improved in some sections of the lakes by using aleatoric loss and including bathymetry. In Lake Erie, the ice score was improved by ∼2 on average in the shallow near–shore zone as a result of better mapping of dark ice (low backscatter) in the western basin. As for Lake Ontario, the open water score was improved by ∼6 on average in the deepest profundal off–shore zone.

The Canadian RADARSAT Constellation Mission (RCM) has passed its early operation phase with the performance evaluation being currently active. This evaluation aims to confirm that the innovative design of the mission’s synthetic aperture radar (SAR) meets the expectations of intended users. In this study, we provide an overview of initial results obtained for three high-priority applications; flood mapping, sea ice analysis, and wetland classification. In our study, the focus is on results obtained using not only linear polarization, but also the adopted Compact Polarimetric (CP) architecture in RCM. Our study shows a promising level of agreement between RCM and RADARSAT-2 performance in flood mapping using dual-polarized HH-HV SAR data over Red River, Manitoba, suggesting smooth continuity between the two satellite missions for operational flood mapping. Visual analysis of coincident RCM CP and RADARSAT-2 dual-polarized HH-HV SAR imagery over the Resolute Passage, Canadian Central Arctic, highlighted an improved contrast between sea ice classes in dry ice winter conditions. A statistical analysis using selected sea ice samples confirmed the increased contrast between thin and both rough and deformed ice in CP SAR. This finding is expected to enhance Canadian Ice Service’s (CIS) operational visual analysis of sea ice in RCM SAR imagery for ice chart production. Object-oriented classification of a wetland area in Newfoundland and Labrador by fusion of RCM dual-polarized VV-VH data and Sentinel-2 optical imagery revealed promising classification results, with an overall accuracy of 91.1% and a kappa coefficient of 0.87. Marsh presented the highest user’s and producer’s accuracies (87.77% and 82.08%, respectively) compared to fog, fen, and swamp.

Mapping different types of sea ice that form, grow, and melt in polar oceans is essential for shipping navigation, climate change modeling, and local community safety. Currently, ice charts are manually generated by analysts at the Canadian Ice Service (CIS) based on dual-polarized RADARSAT-2/RADARSAT Constellation Mission (RCM) imagery on a daily basis. Inspired by the demand for a computer-based mapping system, we have developed an automatic sea ice classification method that integrates spatial contexture (unsupervised segmentation) with textural features (supervised pixel-level labeling). First, the full-scene image is oversegmented, and the segments are merged into homogeneous regions across the entire scene. Second, pixel-based classifiers (support vector machine, random forest) are compared for their ability to label the generated homogeneous regions. Finally, the segmentation and labeling are combined using a proposed energy function. The proposed method was tested on 18 dual-polarization RADARSAT-2 scenes acquired over the Beaufort Sea. This dataset contains water, young ice, first-year ice, and multi-year ice covering melt, summer, and freeze-up seasons. The proposed method obtains an average classification accuracy of 86.33% based on the leave-one-out validation. The experimental results show that the proposed method achieves promising classification results in both quantity and quality measurements compared to benchmark methods. The robustness against incidence angle variance indicates that the proposed method is well-qualified for operational sea ice mapping.

As a result of global warming, multiyear ice (MYI) is being replaced by first-year ice (FYI) in the Arctic. Microwave scatterometers in the Ku-band and C-band can provide daily observations of sea ice type. However, their comparative capabilities in mapping ice type have not been thoroughly evaluated. We present a systematic intercomparison of the backscatter signature in VV polarization ( <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\sigma }_{\mathrm {vv}}^{\mathrm {o}}$ </tex-math></inline-formula> ) and the sea ice classification from three scatterometer systems using the same ice classification approach. The systems are the Ku-band quick scatterometer (QSCAT) and the newly launched Chinese rotating fan-beam scatterometer (RFSCAT) and the C-band advanced scatterometer (ASCAT). Three freezing seasons are used, i.e., 2007/08 and 2008/09 for the QSCAT/ASCAT comparison and 2019/20 for the RFSCAT/ASCAT comparison. With reference to ASCAT, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\sigma }_{\mathrm {vv}}^{\mathrm {o}}$ </tex-math></inline-formula> bias between QSCAT and RFSCAT results from their different incidence angles. A continuous declining trend of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\sigma }_{\mathrm {vv}}^{\mathrm {o}}$ </tex-math></inline-formula> from MYI and FYI is observed during winter, with a greater difference between MYI and FYI in the Ku-band. The MYI and FYI extent derived from QSCAT/RFSCAT is highly consistent with that derived from ASCAT, with a difference less than 7% and 3% for MYI and FYI, respectively. The overall accuracy (OA) is around 77% and 80% for the RFSCAT results and ASCAT results, respectively, compared with Sentinel-1 SAR images. The classification results show high consistency (81%–89%) with ice charts from the Canadian Ice Service. The incorporation of <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">${\mathrm {Tb}}_{36\mathrm {h}}$ </tex-math></inline-formula> from AMSR-E/AMSR2 improves the OA of the classification when using ASCAT or RFSCAT by 7%–11%.

Remote sensing satellites have been broadly applied to sea ice monitoring. The substantial increase in satellite imagery provides a large amount of data support for deep learning methods in the sea ice classification field. However, there is a lack of public remote sensing datasets to facilitate sea ice classification with spatial and temporal information and to benchmark the deep learning methods. In this paper, we provide a labeled large sea ice dataset derived from time-series sentinel-1 SAR images, dubbed SI-STSAR-7, and a validated dataset construction method for sea ice classification research. The SI-STSAR-7 dataset includes seven different sea ice types corresponding to different sea ice development stages in Hudson Bay during winter, and its samples are time sequences of SAR image patches in order to embody the differences of backscattering intensity and textures between different sea ice types, as well as the change of sea ice with time. We construct the dataset by first performing noise reduction and mitigation of incidence angle dependence on SAR images, and then producing data samples and labeling them based on our proposed sample-producing principles and the weekly regional ice charts provided by Canadian Ice Service. Three baseline classification methods are developed on SI-STSAR-7 to establish benchmarks, which are evaluated with accuracy and kappa coefficient. The sample-producing principles are verified through experiments. Based on the experimental results, sea ice classification can be implemented well on SI-STSAR-7.

The IPCC special report on the ocean and cryosphere in a changing climate (SROCC) highlights with high confidence that declining Arctic sea ice extents and increased ship-based transportation are impacting the livelihoods of Arctic Indigenous peoples. Current IPCC assessments cannot address the local scale impacts and adaptive needs of Arctic Indigenous communities based on the global, top-down model approaches used. Inuit maintain the longest unrecorded climate history of sea ice in Canada, and to support Inuit community needs, a decolonized, Inuit knowledge-based approach was co-developed in the community of Mittimatalik, Nunavut (Canada) to create the Mittimatalik siku asijjipallianinga (sea ice climate atlas) 1997–2019. This paper presents the novel approach used to develop the atlas based on Inuit knowledge, earth observations and Canadian Ice Service (CIS) sea ice charts, and demonstrates its application. The atlas provides an adaptation tool that Mittimatalik can use to share locations of known and changing sea ice conditions to plan for safe sea ice travel. These maps can also be used to support the safety and situational awareness of territorial and national search and rescue partners, often coming from outside the region and having limited knowledge of local sea ice conditions. The atlas demonstrates the scientific merit of Inuit knowledge in environmental assessments for negotiating a proposal to extend the shipping seasons for the nearby Mary River Mine. The timing and rates of sea ice freeze-up (October–December) in Mittimatalik are highly variable. There were no significant trends to indicate that sea ice is freezing up later to support increased shipping opportunities into the fall. The atlas shows that the first 2 weeks of November are critical for landfast ice formation, and icebreaking at this time would compromise the integrity of the sea ice for safe travel, wildlife migration and reproduction into the winter months. There was evidence that sea ice break-up (May–July) and the fracturing of the nearby floe edge have been occurring earlier in the last 10 years (2010–2019). Shipping earlier into the break-up season could accelerate the break-up of an already declining sea ice travel season, that Inuit are struggling to maintain.

Two decades (2000–2019) of the landfast ice properties in the Beaufort Sea region in the Canadian Arctic were analyzed at 250 m spatial resolution from two sources: (1) monthly maps derived at the Canada Centre for Remote Sensing from the Moderate Resolution Imaging Spectroradiometer clear-sky satellite image composites; and (2) Canadian Ice Service charts. Detailed comparisons have been conducted for the landfast ice spatial extent, the water depth at, and the distance to the outer seaward edge from the coast in four sub-regions: (1) Alaska coast; (2) Barter Island to Herschel Island; (3) Mackenzie Bay; and (4) Richards Island to Cape Bathurst. The results from both sources demonstrate good agreement. The average spatial extent for the entire region over the April–June period is 48.5 (±5.0) × 103 km2 from Canadian Ice Service data versus 45.1 (±6.1) × 103 km2 from satellite data used in this study (7.0% difference). The correlation coefficient for April–June is 0.73 (p = 2.91 × 10−4). The long-term linear trends of the April–June spatial extent since 2000 demonstrated statistically significant decline: −4.45 (±1.69) × 103 km2/decade and −4.73 (±2.17) × 103 km2/decade from Canadian Ice Service and satellite data, respectively. The landfast ice in the Beaufort Sea region showed the general tendency for an earlier break-up, later onset, and longer ice-free period. The break-up date has decreased by 7.6 days/decade in the Mackenzie Bay region. The western part of the study area did not demonstrate statistically significant changes since 2000.

Sea ice has a significant effect on climate change and ship navigation. Hence, it is crucial to draw sea-ice maps that reflect the geographical distribution of different types of sea ice. Many automatic sea-ice classification methods using synthetic aperture radar (SAR) images are based on the polarimetric characteristics or image texture features of sea ice. They either require professional knowledge to design the parameters and features or are sensitive to noise and condition changes. Moreover, ice changes over time are often ignored. In this article, we propose a new SAR sea-ice image classification method based on a combined learning of spatial and temporal features, derived from residual convolutional neural networks (ResNet) and long short-term memory (LSTM) networks. In this way, we achieve automatic and refined classification of sea-ice types. First, we construct a seven-type ice data set according to the Canadian Ice Service ice charts. We extract spatial feature vectors of a time series of sea-ice samples using a trained ResNet network. Then, using the feature vectors as inputs, the LSTM network further learns the variation of the set of sea-ice samples with time. Finally, the extracted high-level features are fed into a softmax classifier to output the most recent ice type. Taking both spatial features and time variation into consideration, our method can achieve a high classification accuracy of 95.7% for seven ice types. Our method can automatically produce more objective sea-ice interpretation maps, allowing detailed sea-ice distribution and improving the efficiency of sea-ice monitoring tasks.