Sea ice poses a significant risk to offshore structures, as ice-structure interaction depends strongly on the type, geometry, and frequency of ice features. This study analyses Ice Profiling Sonar (IPS) observations from three subsurface moorings (NENS1-NENS3) deployed along a transect on the Northeast Newfoundland Shelf between April 2015 and June 2016 to characterize level ice, ridge keels, and sea ice floes. Ice draft time series were combined with co-located current measurements to derive spatial draft profiles, and feature identification algorithms were applied to classify individual ice features. Draft probability density functions show that thin first-year ice dominates at all sites, with modal drafts of 0.2-0.3 m and rapidly decreasing occurrence of thicker ice. Level ice consists of long, continuous undeformed segments with similar mean draft ranges across locations but substantial variability in width. Keel statistics show strong sensitivity to draft threshold, with deep keels (>8 m) occurring predominantly at the northernmost site. Classical Rayleigh-based keel identification was found to be insufficient in this region, where thinner ice and irregular keel geometries complicate keel boundary detection. Extreme keel drafts were analyzed using a peak-over-threshold approach and a Weibull exceedance model, yielding an estimated 100-year return keel draft of approximately 20 m with associated uncertainty. Floe analysis indicates more numerous and larger floes toward the central and northern sites. Scaling relationships show that level ice forms thin but laterally extensive sheets, ridge keels thicken primarily through convergence and pile-up, and floe thickness is largely independent of floe size. The results provide a feature-based description of the sea ice environment on the Northeast Newfoundland Shelf and support offshore design and risk assessment.
Icebergs impose a significant threat to shipping, offshore oil operations, and underwater pipelines. Detecting and monitoring icebergs in the North Atlantic Ocean is particularly challenging due to frequent cloud cover. Synthetic Aperture Radar (SAR) has emerged as an effective solution for addressing these challenges. This study presents a novel method for detecting icebergs under varying sea conditions using C-band dual-polarimetric imagery from the RADARSAT Constellation Mission (RCM) using the data collected along Canada's east coast during iceberg-prone seasons in 2022 and 2023. Our approach processes large SAR images by dividing them into 100 x 100-pixel patches, each covering an area of 5 km x 5 km, and identifies icebergs within each patch. The method combines statistical features, which highlight subtle patterns in RCM imagery, with high-dimensional features extracted from three pre-trained convolutional neural network (CNN) models. These features are further enhanced with climate parameters and classified using the LightGBM algorithm. To further reduce false alarms (FAs), a Constant False Alarm Rate (CFAR) postprocessing step was applied, enhancing the reliability of the detection process. The proposed approach demonstrates exceptional performance, achieving a 99.08% accuracy rate, a false alarm (FAs) rate of only 1%, and an AUC value nearing 1.
Icebergs pose significant risks to shipping, offshore oil exploration, and underwater pipelines. Detecting and monitoring icebergs in the North Atlantic Ocean, where darkness and cloud cover are frequent, is particularly challenging. Synthetic aperture radar (SAR) serves as a powerful tool to overcome these difficulties. In this paper, we propose a method for automatically detecting and classifying icebergs in various sea conditions using C-band dual-polarimetric images from the RADARSAT Constellation Mission (RCM) collected throughout 2022 and 2023 across different seasons from the east coast of Canada. This method classifies SAR imagery into four distinct classes: open water (OW), which represents areas of water free of icebergs; open water with target (OWT), where icebergs are present within open water; sea ice (SI), consisting of ice-covered regions without any icebergs; and sea ice with target (SIT), where icebergs are embedded within sea ice. Our approach integrates statistical features capturing subtle patterns in RCM imagery with high-dimensional features extracted using a pre-trained Vision Transformer (ViT), further augmented by climate parameters. These features are classified using XGBoost to achieve precise differentiation between these classes. The proposed method achieves a low false positive rate of 1% for each class and a missed detection rate ranging from 0.02% for OWT to 0.04% for SI and SIT, along with an overall accuracy of 96.5% and an area under curve (AUC) value close to 1. Additionally, when the classes were merged for target detection (combining SI with OW and SIT with OWT), the model demonstrated an even higher accuracy of 98.9%. These results highlight the robustness and reliability of our method for large-scale iceberg detection along the east coast of Canada.
Wind is one of the important environmental factors influencing marine target detection as it is the source of sea clutter and also affects target motion and drift. The accurate estimation of wind speed is crucial for developing an efficient machine learning (ML) model for target detection. For example, high wind speeds make it more likely to mistakenly detect clutter as a marine target. This paper presents a novel approach for the estimation of sea surface wind speed (SSWS) and direction utilizing satellite imagery through innovative ML algorithms. Unlike existing methods, our proposed technique does not require wind direction information and normalized radar cross-section (NRCS) values and therefore can be used for a wide range of satellite images when the initial calibrated data are not available. In the proposed method, we extract features from co-polarized (HH) and cross-polarized (HV) satellite images and then fuse advanced regression techniques with SSWS estimation. The comparison between the proposed model and three well-known C-band models (CMODs)—CMOD-IFR2, CMOD5N, and CMOD7—further indicates the superior performance of the proposed model. The proposed model achieved the lowest Root Mean Squared Error (RMSE) and Mean Absolute Error (MAE), with values of 0.97 m/s and 0.62 m/s for calibrated images, and 1.37 and 0.97 for uncalibrated images, respectively, on the RCM dataset.
Satellite synthetic aperture radar (SAR) data are becoming increasingly valuable for marine operations in ice-affected environments. There are growing varieties of satellites, beam modes and other sensor parameters that are available, so there is a need to develop a universal method to compare the performance of satellite imagery for a given application. This paper introduces the concept of a confidence map for iceberg detection for the safety and efficiency of marine activities. By comparing the characteristics of a set of validated iceberg targets in SAR data with a new image, it is possible to assess what proportion of icebergs in a region may be detected. While the results are intuitive, they quantify the performance of satellite data for iceberg monitoring
Soil moisture is one of the main factors affecting microwave radar backscatter from the ground. While there are other factors that affect backscatter levels (for instance, surface roughness, vegetation, and incident angle), relative variations in soil moisture can be estimated using space-based, medium resolution, multi-temporal synthetic aperture radar (SAR). Understanding the distribution and identification of water-saturated areas using SAR soil moisture can be important for wetland mapping. The SAR soil moisture retrieval algorithm provides a relative assessment and requires calibration over wet and dry periods. In this work, relative soil moisture indicators are derived from a time series of the RADARSAT Constellation Mission (RCM) SAR compact polarimetric (CP) data over reclaimed areas of an oil sands mine in Alberta, Canada. An evaluation of the soil moisture product is performed using in situ measurements showing agreement from June to September. The surface scattering component of m-chi CP decomposition and the RL SAR products demonstrated a good agreement with the field data (low RMSE values and a perfect alignment with field-identified wetlands).
The satellite-based techniques for the monitoring of extreme ice features (EIFs) in the Canadian Arctic were investigated and demonstrated using synthetic aperture radar (SAR) and electro-optical data sources. The main EIF types include large ice islands and ice-island fragments, multiyear hummock fields (MYHF) and other EIFs, such as fragments of MYHF and large, newly formed hummock fields. The main objectives for the paper included demonstration of various satellite capabilities over specific regions in the Canadian Arctic to assess their utility to detect and characterize EIFs. Stereo pairs of very-high-resolution (VHR) imagery provided detailed measurements of sea ice topography and were used as validation information for evaluation of the applied techniques. Single-pass interferometric SAR (InSAR) data were used to extract ice topography including hummocks and ice islands. Shape from shading and height from shadow techniques enable us to extract ice topography relying on a single image. A new method for identification of EIFs in sea ice based on the thermal infrared band of Landsat 8 was introduced. The performance of the methods for ice feature height estimation was evaluated by comparing with a stereo or InSAR digital elevation models (DEMs). Full polarimetric RADARSAT-2 data were demonstrated to be useful for identification of ice islands.
Drifting icebergs present significant navigational and operational risks in remote offshore regions, particularly along the East Coast of Canada. In such areas with harsh weather conditions, traditional methods of monitoring and assessing iceberg-related hazards, such as aerial reconnaissance and shore-based support, are often unfeasible. As a result, satellite-based monitoring using Synthetic Aperture Radar (SAR) imagery emerges as a practical solution for timely and remote iceberg classifications. We utilize the C-CORE/Statoil dataset, a labeled dataset containing both ship and iceberg instances. This dataset is derived from dual-polarized Sentinel-1. Our methodology combines state-of-the-art deep learning techniques with comprehensive feature selection. These features are coupled with machine learning algorithms (neural network, LightGBM, and CatBoost) to achieve accurate and efficient classification results. By utilizing quantitative features, we capture subtle patterns that enhance the model’s discriminative capabilities. Through extensive experiments on the provided dataset, our approach achieves a remarkable accuracy of 95.4% and a log loss of 0.11 in distinguishing icebergs from ships in SAR images. The introduction of additional ship images from another dataset can further enhance both accuracy and log loss results to 96.1% and 0.09, respectively.
The need to monitor ice conditions has motivated the launch of several earth observation (EO) satellites and ice mapping applications are among the highest consumers of satellite data. However, oil and gas operations (O&G) in ice-prone (both sea ice and iceberg) environments have largely been using EO data for upstream, strategic reports on ice conditions. There are many recent and upcoming advances in EO technology that are already enabling satellites to be used for other critical operations and there is value in using satellites extensively for ice management. The remainder of this paper briefly describes these advances and their impact on detecting ice conditions to support oil and gas operations.
The availability of high-resolution atmospheric/ocean forecast models, satellite data and access to high-performance computing clusters have provided capability to build high-resolution models for regional ice condition simulation. The paper describes the implementation of the Los Alamos sea ice model (CICE) on a regional scale at high resolution. The advantage of the model is its ability to include oceanographic parameters (e.g., currents) to provide accurate results. The sea ice simulation was performed over Baffin Bay and the Labrador Sea to retrieve important parameters such as ice concentration, thickness, ridging, and drift. Two different forcing models, one with low resolution and another with a high resolution, were used for the estimation of sensitivity of model results. Sea ice behavior over 7 years was simulated to analyze ice formation, melting, and conditions in the region. Validation was based on comparing model results with remote sensing data. The simulated ice concentration correlated well with Advanced Microwave Scanning Radiometer for EOS (AMSR-E) and Ocean and Sea Ice Satellite Application Facility (OSI-SAF) data. Visual comparison of ice thickness trends estimated from the Soil Moisture and Ocean Salinity satellite (SMOS) agreed with the simulation for year 2010–2011.
Information on the locations and characteristics of extreme sea ice features (such as, hummocks, ridges, stamukhas and icebergs) is important for various marine applications. Imagery acquired by high resolution optical satellites was previously used for qualitative image interpretation to identify various sea ice features and it is especially valuable when detailed ground validation is not available. Current optical satellites, such as GeoEye-1, are able to acquire images with very high resolution of 0.5m. This work addresses the problem of quantitative retrieval of ice feature parameters from very high resolution optical imagery. The developed algorithms facilitate extraction of ice feature height from shadow and derivation of statistical information on ice deformation parameters. Automated processing of GeoEye-1 image demonstrated capabilities of retrieval of ridge frequency and segmentation of rubble fields.
Research on automatic detecting, tracking and characterizing extreme ice features in the Arctic is based on analyzing and processing satellite synthetic aperture radar (SAR) and optical images. Algorithms to identify ridges from very high-resolution optical data have an accuracy of 86.4% when compared to manual extraction and ridge height has been estimated from shadow. SAR signatures of various ice features have been analyzed and the results indicate that it is possible to identify rubble fields from other ice types.
Well sites, including both well pads and exploratory core holes, are small polygonal landscape disturbance features approximately one half to one hectare (0.5–1 ha) in area, resulting from oil and gas exploration activities. Automatic extraction and monitoring of such small features using remote-sensing technology at regional scales has always been desirable for wildlife habitat monitoring and environmental planning and modelling. Due to the vast disturbances of well sites in a province like Alberta, Canada, high-resolution imagery is not practical for well site extraction. For operational purposes, mid-resolution and cost-effective satellite imagery such as Landsat is the choice. However, automatic well site extraction using mid-resolution satellite imagery is a challenging task. Wells are typically less than three pixels in width and length in a Landsat multispectral image. Furthermore, the spectral contrast between the well site pixels and the surrounding areas is low due to vegetation regrowth and the spectral complexity of the surrounding environment. This article presents a novel methodology for automatic extraction of well sites from Landsat-5 TM imagery. The method combines both pixel- and object-based image analyses and contains three major steps: geometric enhancement, segmentation, and well site extraction. The method was applied to Landsat-5 TM images acquired over Fort McMurray, Alberta, Canada. For accuracy assessment, four regions of interest were selected and the results of the proposed automatic method were evaluated against visual inspection of the Landsat-8 pan-sharpened image. The method results in a total average correctness, completeness, and quality measures of about 80, 96, and 77%, respectively over the four sites. In addition, the method is very fast as an entire Landsat scene is processed in less than 10 minutes. The method is an operational approach for automatic detection of well sites over the entire province and can dramatically reduce the labour cost of manual digitization for monitoring and updating well site maps.
Abstract P>Sea ice monitoring is an important field of scientific research and relevant to operational applications. One of the major engineering challenges in undertaking production developments in Arctic offshore regions is the frequent presence of extreme ice features that pose a hazard to facilities and surrounding subsea infrastructure. The information on extreme ice features (i.e., ridges, icebergs etc.) is important from the standpoint of potential ice load levels on fixed structures and ice scouring of seafloor facilities. Satellite observation has been shown to be useful for extracting and characterizing ice regimes. Sea ice can be monitored using satellite imagery acquired by different types of sensors: microwave radiometer, optical instrument and synthetic aperture radar (SAR). The outputs of sea ice monitoring may include various ice parameters such as edge, thickness, concentration, classification, iceberg detection, and ice statistics. This paper describes application of high and low resolution SAR imagery for sea ice monitoring and to resolve local features and extend the statistical baseline to larger regions because extreme ice features may be invisible or ambiguous with other ice features in these data. The use of higher resolution imagery allows for easier detection of ice features and provides sufficient spatial detail necessary for detecting ice features from sea ice, identification and estimation of size and geometry of ice floes and icebergs. It was demonstrated that SAR sensors with multiple resolution lead to a better understanding of ice conditions including ice edge, concentration, floe statistics, and other ice features such as icebergs. A technique based on SAR interferometry was used for identification of iceberg in sea ice as well as for extracting iceberg topography.
Information on extreme ice features (ridges, icebergs etc.) is important for various marine operations. Satellite synthetic aperture radar (SAR) imagery is capable of monitoring sea ice, identifying and tracking ice features over broad spatial scales. This work investigates possibilities of extreme sea ice features retrieval from various RADARSAT-2 data. Several different beam modes and analysis techniques, such as polarimetric decompositions, were investigated. It was demonstrated that the spatial frequency of sea ice ridges has a very good correlation with the SAR backscatter coefficient. The problem of discriminating glacier ice from sea ice can be resolved by applying Pauli decomposition to full polarimetric data.
A tool developed for simulating RADARSAT-2 (RS2) Maritime Satellite Surveillance Radar (MSSR) mode data from higher resolution data is described. RS2 Fine and Fine Quad images containing validated ship and iceberg targets were resampled to low resolution ScanSAR Narrow (SCN) and MSSR mode data. This tool can be adopted to use other image modes as inputs and simulate other outputs as well and the simulated products are used to develop a ship and iceberg discriminator for those modes. A series of tests were applied to verify the accuracy of the backscatter characteristics of the simulated products and the performance of the target discriminator are presented for SCN and MSSR mode Ocean Surveillance, Very wide swath, Near incidence (OSVN)[1]. Since there was a very limited ship data suitable for simulating MSSR mode available, only a demonstration of MSSR OSVN classifier was included.
Multi-resolution SAR datasets (ENVISAT, TerraSARX, TanDEM-X) were used for ice parameters retrieval using automated algorithms within a prototype of system of multisource data fusion. It has been demonstrated that two SAR sensors with multiple frequencies and resolution lead to a better understanding of ice conditions including ice edge, concentration, floe statistics, and other ice features such as icebergs. Time series of ENVISAT Wide Swath data with low resolution were used to monitor the dynamic changes in ice, to detect ice edge, and to estimate ice concentration. High resolution TerraSAR-X/TanDEM-X constellation data were used to generate an interferogram for improved detection and estimation of size and geometry of ice floes and icebergs. Each individual floe has its own fringes interferometric pattern which can be used for calculating floe statistics. The iceberg interferogram was used for detecting iceberg in sea ice as well as for extracting iceberg topography.
A remote sensing technique, based on processing satellite altimeter data, for iceberg detection was validated and implemented for operational iceberg monitoring. Algorithms for altimeter data preprocessing and analysis were developed to efficiently detect icebergs and eliminate false detections caused by signal noise and the presence of small islands. Results of iceberg detection for application in ship navigation are demonstrated.