Since rain alters the histogram pattern of radar images, rain-contaminated radar data can be identified. In this article, a support vector machine (SVM)-based method for rain detection using X-band marine radar images is presented. First, the normalized histogram bin values for each image are extracted and combined into feature vector. Then, SVMs are employed to classify between rain-free and rain-contaminated images. Radar images and simultaneous rain rate data collected from a sea trial in North Atlantic Ocean are utilized for model training and testing. Comparison with the zero pixel percentage (ZPP) threshold method shows that the SVM-based method obtains higher detection accuracy, with 98.4% for the Decca radar data and 99.7% for the Furuno radar. It is also found that as the total number of bins does not significantly affect detection accuracy, the proposed method can be applied to different radar systems directly with a suitable number of bins. In addition, compared to the ZPP threshold method, the SVM-based method proves to be more robust even with limited training samples.

In this article, an unsupervised clustering-based method for identifying rain-contaminated and low-backscatter regions in X-band marine radar images is presented. Rain blurs the wave signatures of radar images, and low-backscatter images caused by calibration errors or too-low wind speed contain little or no wave signatures. In both cases, ocean surface parameter measurement using X-band marine radar will be negatively affected. Four types of features can be extracted based on the distinct difference in texture and pixel intensity distribution between rain-free, rain-contaminated, and low-backscatter regions. Features extracted from each pixel are combined into a feature vector and mapped onto a 10×10-neuron self-organizing map (SOM). Then, the hierarchical agglomerative clustering algorithm is introduced, which clustered those neurons into three types (i.e., rain-free, rain-contaminated, and low-backscatter). The method is validated using the shipborne marine radar data collected on the East Coast of Canada. The good agreement between the pixel-based clustering results and manually segmented reference images indicates that both rain-contaminated and low-backscatter regions can be identified effectively using the proposed method.

Bayesian neural networks (BNNs) have been demonstrated to be effective in accurate retrieval of sea ice concentration (SIC) from multi-source data, while providing estimates of uncertainty, which are essential for downstream services. However, uncertainty obtained by BNNs are intrinsically uncalibrated, which indicates that it may not correlate well with model error. To address this issue, we investigate a new approach that combines an auxiliary prediction interval (PI) estimator with the BNN-based SIC mean estimator to develop a well-calibrated SIC retrieval model that is both accurate and reliable. We adopt a training strategy called “uncertainty matching" to train the model, which ensures that the estimated uncertainties match the estimated PIs. We use a subset of AMSR2 brightness temperature data and ERA5 atmospheric data collected from 2014 to 2015 in the Baffin Bay area as input features of the model. Comparison between model inference and SIC labels obtained from the enhanced NASA Team (NT2) algorithm shows that the proposed approach is able to produce well-calibrated uncertainty with more accurate predictions in marginal ice zones.

The AutoICE challenge, organized by multiple national and international agencies, seeks to advance the development of near-real-time sea ice products with improved spatial resolution, broader spatial and temporal coverage, and enhanced consistency. In this paper, we present a detailed description of our solutions and experimental results for the challenge. We have implemented an automated sea ice mapping pipeline based on a multi-task U-Net architecture, capable of predicting sea ice concentration (SIC), stage of development (SOD), and floe size (FLOE). The AI4Arctic dataset, which includes synthetic aperture radar (SAR) imagery, ancillary data, and ice-chart-derived label maps, is utilized for model training and evaluation. Among the submissions from over 30 teams worldwide, our team achieved the highest combined score of 86.3 %, as well as the highest scores on SIC (92.0 %) and SOD (88.6 %). Notably, the result analysis and ablation studies demonstrate that instead of model architecture design, a collection of strategies/techniques we employed led to substantial enhancement in accuracy, efficiency, and robustness within the realm of deep-learning-based sea ice mapping. Those techniques include input SAR variable downscaling, input feature selection, spatial–temporal encoding, and the choice of loss functions. By highlighting the various techniques employed and their impacts, we aim to underscore the scientific advancements achieved in our methodology.

Mapping sea ice in the Arctic is essential for maritime navigation, and growing vessel traffic highlights the necessity of the timeliness and accuracy of sea ice charts. In addition, with the increased availability of satellite imagery, automation is becoming more important. The AutoICE Challenge investigates the possibility of creating deep learning models capable of mapping multiple sea ice parameters automatically from spaceborne synthetic aperture radar (SAR) imagery and assesses the current state of the automatic-sea-ice-mapping scientific field. This was achieved by providing the tools and encouraging participants to adopt the paradigm of retrieving multiple sea ice parameters rather than the current focus on single sea ice parameters, such as concentration. The paper documents the efforts and analyses, compares, and discusses the performance of the top-five participants’ submissions. Participants were tasked with the development of machine learning algorithms mapping the total sea ice concentration, stage of development, and floe size using a state-of-the-art sea ice dataset with dual-polarised Sentinel-1 SAR images and 22 other relevant variables while using professionally labelled sea ice charts from multiple national ice services as reference data. The challenge had 129 teams representing a total of 179 participants, with 34 teams delivering 494 submissions, resulting in a participation rate of 26.4 %, and it was won by a team from the University of Waterloo. Participants were successful in training models capable of retrieving multiple sea ice parameters with convolutional neural networks and vision transformer models. The top participants scored best on the total sea ice concentration and stage of development, while the floe size was more difficult. Furthermore, participants offered intriguing approaches and ideas that could help propel future research within automatic sea ice mapping, such as applying high downsampling of SAR data to improve model efficiency and produce better results.

In recent years, the adoption of deep learning (DL) techniques for predicting sea ice concentration (SIC) given both passive microwave (PM) data and reanalysis data has seen a growing interest. For use in downstream services, these sea ice concentration estimates should be accompanied by uncertainty estimates. To provide these estimates, we utilize a heteroscedastic Bayesian neural network (HBNN), which can estimate both model (epistemic) and data (aleatoric) uncertainty. We use both PM and atmospheric data as our input features, and demonstrate that both are needed for accurate SIC estimates. Results show that over an annual cycle, the months of melt onset, such as April, May, and June produce the highest uncertainties relative to other months, with total (epistemic + aleatoric) uncertainties of approximately 20%, while areas in the marginal ice zone, contributed highest total uncertainty of 25% spatially. When considering an average over the test year, the level of uncertainty due to the data (aleatoric) is consistent with other studies, at 10%-15%. The advantage of our approach is that the uncertainties are specific to the data instance, and both model and data uncertainty are estimated.