Ice Images Research Articles

Investigating Subsurface Properties of the Shallow Lunar Crust Using Seismic Interferometry on Synthetic and Recorded Data

AbstractIn the past few years, the remarkable progress of commercially operated spacecrafts, the success with reusable rocket engines, as well as the international competition to explore space, has led to a substantial acceleration of activities in the design and preparation of ambitious future lunar missions. In the search for ice and/or cavities imaging the shallow subsurface structure is of vital importance. Hereby, previous studies have shown that seismic interferometry is a promising method to investigate the subsurface properties from passive lunar data. In this study, we want to evaluate the potential of this method further by examining the required duration of seismic measurements and the influence of scattering on the Green's function retrieval. Therefore, we applied seismic interferometry to both measured Apollo 17 data and synthetic data. Our findings indicate that, under optimal conditions, a few hours of data are sufficient when using the method of time‐scaled phase‐weighted stack (ts‐PWS). However, this strongly depends on the inter‐station distance, the orientation toward the principal noise sources, and the timing of the measurement during the lunar cycle. Additionally, we were able to reproduce the measured data using numerical simulations in 2D. The synthetic results show that scattering effects clearly influence the Green's function extraction, especially for larger station distances.

Using the Neural Network Technique for Lead Detection in Radar Images of Arctic Sea Ice

Using the Neural Network Technique for Lead Detection in Radar Images of Arctic Sea Ice

Observational Evidence of Cold Filamentary Intensification in an Energetic Meander of the Antarctic Circumpolar Current

Abstract Eddy stirring at mesoscale oceanic fronts generates finescale filaments, visible in submesoscale-resolving model simulations and high-resolution satellite images of sea surface temperature, ocean color, and sea ice. Submesoscale filaments have widths of O(1–10) km and evolve on time scales of hours to days, making them extremely challenging to observe. Despite their relatively small scale, submesoscale processes play a key role in the climate system by providing a route to dissipation; altering the stratification of the ocean interior; and generating strong vertical velocities that exchange heat, carbon, nutrients, and oxygen between the mixed layer and the ocean interior. We present a unique set of in situ and satellite observations in a standing meander region of the Antarctic Circumpolar Current (ACC) that supports the theory of cold filamentary intensification—revealing enhanced vertical velocities and evidence of subduction and ventilation associated with finescale cold filaments. We show that these processes are not confined to the mixed layer; EM-APEX floats reveal enhanced downward velocities (>100 m day−1) and evidence of ageostrophic motion extending as deep as 1600 dbar, associated with a ∼20-km-wide cold filament. A finer-scale (∼5 km wide) cold filament crossed by a towed Triaxus is associated with anomalous chlorophyll and oxygen values extending at least 100–200 dbar below the base of the mixed layer, implying recent subduction and ventilation. Energetic standing meanders within the weakly stratified ACC provide an environment conductive to the generation of finescale filaments that can transport water mass properties across mesoscale fronts and deep into the ocean interior.

Structure Discovery in Atomic Force Microscopy Imaging of Ice.

The interaction of water with surfaces is crucially important in a wide range of natural and technological settings. In particular, at low temperatures, unveiling the atomistic structure of adsorbed water clusters would provide valuable data for understanding the ice nucleation process. Using high-resolution atomic force microscopy (AFM) and scanning tunneling microscopy, several studies have demonstrated the presence of water pentamers, hexamers, and heptamers (and of their combinations) on a variety of metallic surfaces, as well as the initial stages of 2D ice growth on an insulating surface. However, in all of these cases, the observed structures were completely flat, providing a relatively straightforward path to interpretation. Here, we present high-resolution AFM measurements of several water clusters on Au(111) and Cu(111), whose understanding presents significant challenges due to both their highly 3D configuration and their large size. For each of them, we use a combination of machine learning, atomistic modeling with neural network potentials, and statistical sampling to propose an underlying atomic structure, finally comparing its AFM simulated images to the experimental ones. These results provide insights into the early phases of ice formation, which is a ubiquitous phenomenon ranging from biology to astrophysics.

UltraSOUND-based characterization of ventricular tachycardia SCAR and arrhythmogenic substrate: The SOUNDSCAR study

BackgroundIntracardiac echocardiography (ICE) represents a valuable image integration technique, with the unique advantage of dynamic real-time scar characterization. ObjectivesThe goals of this study were to assess the correlation between ICE-defined and electroanatomic mapping (EAM)–defined scar in patients with ischemic cardiomyopathy and to define the outcomes of ICE-guided ventricular tachycardia (VT) ablation. MethodsThirty-eight patients with ischemic cardiomyopathy (SOUNDSCAR cohort) underwent full left ventricular (LV) ICE imaging and EAM. ICE-defined scar parameters (end-diastolic and end-systolic wall diameter [EDWD and ESWD], end-systolic wall thickening [percentage difference between EDWD and ESWD with respect to EDWD], slope [end-diastole to end-systole wall thickening], and American Heart Association wall motion scoring) were correlated with EAM-defined scar (voltage <1.5 mV). In a separate cohort (n = 21), outcomes of an ICE-guided VT ablation approach (EAM focused to ICE-defined scar regions) were compared with those of conventional ablation (full left ventricular mapping with EAM only; n = 21). ResultsIn the 38 SOUNDSCAR patients (mean age 67 ± 11 years; 35 male [92%]; left ventricular ejection fraction 31% ± 10%; 2474 ICE segments; 524 ICE sectors), all ICE-defined parameters strongly predicted EAM-defined scar (area under the curve: American Heart Association score 0.873; ESWD 0.880; EDWD 0.827; slope 0.855; percentage difference between EDWD and ESWD with respect to EDWD, 0.851). All ICE-defined parameters had large effect sizes for predicting EAM-defined scar (logistic regression, P < .001). A detailed topographical comparison of ICE-defined (slope) and EAM-defined scar was possible in 25 patients and demonstrated 88% ± 10% overlap. Compared with conventional VT ablation, ICE-guided ablation was associated with shorter procedure times and comparable VT-free survival (ICE-guided vs conventional: procedure time 240 ± 20 minutes vs 298 ± 39 minutes; P < .001; VT recurrence 3 [14%] vs 7 [31%]; P = .19). ConclusionICE-defined scar demonstrates a strong correlation with EAM-defined scar. ICE-guided VT ablation is associated with enhanced procedural efficiency.

Efficient Retrieval of Images with Irregular Patterns Using Morphological Image Analysis: Applications to Industrial and Healthcare Datasets.

Image retrieval is the process of searching and retrieving images from a datastore based on their visual content and features. Recently, much attention has been directed towards the retrieval of irregular patterns within industrial or healthcare images by extracting features from the images, such as deep features, colour-based features, shape-based features, and local features. This has applications across a spectrum of industries, including fault inspection, disease diagnosis, and maintenance prediction. This paper proposes an image retrieval framework to search for images containing similar irregular patterns by extracting a set of morphological features (DefChars) from images. The datasets employed in this paper contain wind turbine blade images with defects, chest computerised tomography scans with COVID-19 infections, heatsink images with defects, and lake ice images. The proposed framework was evaluated with different feature extraction methods (DefChars, resized raw image, local binary pattern, and scale-invariant feature transforms) and distance metrics to determine the most efficient parameters in terms of retrieval performance across datasets. The retrieval results show that the proposed framework using the DefChars and the Manhattan distance metric achieves a mean average precision of 80% and a low standard deviation of ±0.09 across classes of irregular patterns, outperforming alternative feature-metric combinations across all datasets. Our proposed ImR framework performed better (by 8.71%) than Super Global, a state-of-the-art deep-learning-based image retrieval approach across all datasets.

A fused super-resolution network and a vision transformer for airfoil ice accretion image prediction

Designing large neural network models targeting high accuracy and low sample number requirement is an important task in accelerating airfoil ice accretion calculation. Both convolutional neural network and Transformer are potential large-scale architectures for icing image generation. In this study, FSRN (fused super-resolution network) and ViT (Vision Transformer) are designed and applied to predict icing images with complex shapes. The novelty of FSRN lies in dividing the training process into main feature generation and detail information processing, and three branches of SR (super-resolution) networks are applied for multi-inputs and fused to generate icing images. The core part of ViT is the large-scale attention structure which is proven to be powerful in learning features. Both 7-dimensional icing condition vectors and the airfoil image are set as inputs to predict 136×136 icing images, and FocalLoss is chosen as the loss function. FSRN achieves determination coefficients of 0.974 and 0.958 respectively while ViT achieves 0.967 and 0.953 in two validation data sets. FSRN demonstrated greater potential in reducing sample number compared to ViT and MLP (multilayer perceptron).

Applications of Deep Learning-Based Super-Resolution Networks for AMSR2 Arctic Sea Ice Images

Studies have indicated that the decrease in the extent of Arctic sea ice in recent years has had a significant impact on the Arctic ecosystem and global climate. In order to understand the evolution of sea ice, it is becoming increasingly imperative to have continuous observations of Arctic-wide sea ice with high spatial resolution. Passive microwave sensors have the benefit of being less susceptible to weather, wider coverage, and higher temporal resolution. However, it is challenging to retrieve accurate parameters of sea ice due to the low spatial resolution of passive microwave images. Therefore, improving the spatial resolution of passive microwave images is beneficial for reducing the uncertainty of sea ice parameters. In this paper, four competitive multi-image super-resolution (MISR) networks are selected to explore the applicability of the networks on multi-frequency Advanced Microwave Scanning Radiometer 2 (AMSR2) images of Arctic sea ice. The upsampling factor is set to 4 in the experiment. Firstly, the optimal input lengths of the image sequence for the four MISR networks are found, and then the best network on different frequency band images is further identified. Furthermore, some factors, including seasons, sea ice motion, and polarization mode of images, that may affect the super-resolution (SR) results are analyzed. The experimental results indicate that utilizing images from winter yields superior SR results. Conversely, SR results are the worst during summer across all four MISR networks, exhibiting the largest difference in PSNR of 4.48 dB. Additionally, the SR performance is observed to be better for images with smaller magnitudes of sea ice motion compared to those with larger motions, with the maximum PSNR difference of 2.04 dB. Finally, the SR results for vertically polarized images surpass those for horizontally polarized images, showcasing an average advantage of 4.02 dB in PSNR and 0.0061 in SSIM. In summary, valuable suggestions for selecting MISR models for passive microwave images of Arctic sea ice at different frequency bands are offered in this paper. Additionally, the quantification of the various impact factors on SR performance is also discussed in this paper, which provides insights into optimizing MISR algorithms for passive microwave sea ice imagery.

Black Ice Classification with Hyperspectral Imaging and Deep Learning

With the development of new technologies inside car mechanisms with various sensors connected to the IoT, a new generation of automation is attracting attention. However, there are still some factors that are difficult to detect. Among them, one of the highest risk factors is black ice. A road covered with black ice, which is hard to see from a distance, is not only the cause of damage to vehicles passing over the spot, but it also puts lives at risk. Hence, the detection of black ice is essential. A lot of research has been done on this topic with various sensors and methods. However, hyperspectral imaging has not been used for this particular purpose. Therefore, in this paper, black ice classification has been performed with the help of hyperspectral imaging in collaboration with a deep learning model for the first time. With abundant spectral and spatial information, hyperspectral imaging is a good way to analyze any material. In this paper, a 2D–3D Convolutional Neural Network (CNN) has been used to classify hyperspectral images of black ice. The spectral data were preprocessed, and the dimension of the image cube was reduced with the help of Principal Component Analysis (PCA). The proposed method was then compared with the existing method for better evaluation.

Feasibility and safety of reprocessing of intracardiac echocardiography catheters for electrophysiology procedures – a large single center experience

PurposeIntra-cardiac echocardiography (ICE) has become an important tool for catheter ablation. Adoption of ICE imaging is still limited because of its prohibitively high cost. Our aim was to study the safety and feasibility of ICE catheters reprocessing and its environmental and financial impact.MethodsThis was a single center retrospective analysis of all consecutive electrophysiology procedures in which ICE catheters were used from 2015 to 2022. In total, 1128 patients were studied (70.6% male, mean age was 57.9 ± 13.2 years). The majority of procedures were related to atrial fibrillation ablation (84.6%).ResultsFor the whole cohort, 57 new ICE catheters were used. Consequently one catheter could be used for 19.8 procedures. New catheters were only used when the image obtained by reused probes was not satisfactory. There were no cases of ICE probe steering mechanism malfunction, no procedure related infections and no allergic reactions that could be attributed to the resterilization process. In total, there was 8.6% of complications not related to ICE imaging. Financially, ICE probe reprocessing resulted with 90% cost reduction (> 2 millions of Euros savings for the studied period) and 95% waste reduction (639.5 kg less, mostly non degradable waste was produced).ConclusionOur data suggests that ICE catheter reprocessing is feasible and safe. It seems that risk of infection is not increased. Significant economic and environmental savings could be achieved by ICE catheters reprocessing. Furthermore, ICE reprocessing could allow more extensive ICE usage resulting in safer procedures with a potential reduction of serious complications.Graphical

Improved Sea Ice Image Segmentation Using U2-Net and Dataset Augmentation

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Traditional image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning-based semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and severe weather conditions affect image quality, which affects the accuracy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multiscale inflation convolution and a multilayer convolutional block attention module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insufficient number of training samples to a certain extent and improved the accuracy of image segmentation; (2) this study designed a multilevel Gaussian noise data augmentation scheme to improve the network’s ability to resist noise interference and achieve a more accurate segmentation of images with different degrees of noise pollution; (3) the inclusion of a multiscale inflation perceptron and multilayer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

Improved Detection of Ice Accretion Status on Transmission Lines Using YOLOv5s

Ice accretion on transmission lines is one of the major hidden dangers to the safe operation of power systems. The current ice image monitoring system of power companies urgently needs to quickly and accurately detect the ice accretion status from massive real-time image data to assist in the smooth implementation of de-icing work. Based on the original dataset constructed with the help of Shanxi Power Company, this paper establishes a transmission line ice accretion image dataset through image screening, image enhancement, image sliding window segmentation, and image annotation. On the basis of the original YOLOv5s model, this paper proposes three improvements: 1. Designing a feature enhancement module based on atrous convolution to increase the receptive field and obtain more contextual information while preserving the texture details of the feature map. 2. This paper simplifies cross-scale connections and contextual information weighting operations in the feature pyramid to enhance the network's feature extraction capabilities. 3. Introducing Swin-Transformer network structure in the process of feature fusion, further enhancing the semantic information and global perception of small targets. It can be seen from the ablation experiment analysis that the mAP0.5:0.5 of the proposed algorithm has increased by 7.6% compared with the original YOLOv5s. At the same time, the performance comparison experiment validated that the detection accuracy of the proposed algorithm achieved better performance with little sacrifice in detection speed.

FastICENet: A real-time and accurate semantic segmentation model for aerial remote sensing river ice image

River ice semantic segmentation is a crucial task, which can provide us with information for river monitoring, disaster forecasting, and transportation management. Previous works mainly focus on higher accuracy acquirement, while efficiency is also important for reality usage. In this paper, a real-time and accurate river ice semantic segmentation network is proposed, named FastICENet. The general architecture consists of two branches, i.e., a shallow high-resolution spatial branch and a deep context semantic branch, which are carefully designed for the scale diversity and irregular shape of river ice in remote sensing images. Then, a novel Downsampling module and a dense connection block based on a lightweight Ghost module are adopted in the context branch to reduce the computation cost. Furthermore, a learnable upsampling strategy DUpsampling is utilized to replace the commonly used bilinear interpolation to improve the segmentation accuracy. We deploy detailed experiments on three publicly available datasets, named NWPU_YRCC_EX, NWPU_YRCC2, and Alberta River Ice Segmentation Dataset. The experimental results demonstrate that our method achieves state-of-the-art performance with competing methods, on the NWPU_YRCC_EX dataset, we can achieve the segmentation speed as 90.84FPS and the segmentation accuracy as 90.770% mIoU, which also illustrates the good leverage between accuracy and speed. Our code is available at https://github.com/nwpulab113/FastICENet

PO-04-094 RELEVANCE OF MICROBUBBLE FORMATION WITH PULSED FIELD ABLATION SHOWING IRREVERSIBLE ELECTROPORATION IN A CANINE MODEL

With ablation using a saline flow catheter tips, occasionally microbubbles will be seen, either from excessive heating or steam pops. The occurrence and implications of microbubble formation with PFA/IRE ablation has not been determined. This study aim was to clarify the means of microbubble during PFA/IRE ablation. Therefore, a total of 4 dogs underwent evaluation with the delivery of 34 ablated lesions in the right and left atrium. During PFA/IRE ablation, we monitored by the ICE imaging whether microbubble formation occurred. With these, microbubbles were seen in 82% of deliveries. The microbubbles were class I in 25 %, class II in 25 %, and class III in 50 %. There appeared to be no untoward effect of class I microbubbles. However, with the others, a suggested biophysical property was seen. In those with catheter positioning directly perpendicular to the endocardial surface, microbubbles were less common. On the other hand, with more parallel tip positioning, or with lowere contact force, microbubbles could reach the class II or III level. These were different than past studies showing simple heat related microbubbles. With PFA the heat is not present. Nevertheless, the process of electrophoresis appeared to create the microbubbles to a greater extent than the irrigation catheter’s flow. The concern with this is a decrease in the effectiveness of delivery as judged by high-density mapping. With this study, no actual perforations were seen, but there was an energy loss with the electrophoretic effects. Actually, in gross pathology, the lesion length and width ranged from 16.5 to 24.1 mm and from 11.9 to 21.8 mm in the RA. Class II or III microbubbles are readily seen in PFA/IRE ablation. These appear to be different from that seen with irrigation-tip catheters. The marked occurrence of microbubbles suggests an electrophoretic process, which like incomplete contact could result in a substantial loss of energy rendering ablation lesions less effective. Even with enough contact PFA/IRE, the effect could be substantial. While few complications are seen with PFA/IRE ablation, the marked electrophoretic effect producing microbubbles, also seen with high output pacing could result in a diminution of the actual lesion formation as judged by histology.

Imaging Low-Temperature Phases of Ice with Polarization-Resolved Hyperspectral Stimulated Raman Scattering Microscopy.

Water freezes into various phases of ice under different cryogenic temperatures and pressure conditions, such as ice Ih and ice XI at normal pressure. Vibrational imaging with high spectral, spatial, and polarization resolutions could provide detailed information on ice, including the phases and crystal orientations at the microscopic level. Here, we report in situ stimulated Raman scattering (SRS) imaging of ice to analyze the vibrational spectral changes of the OH stretching modes associated with the phase transition between ice Ih and ice XI. In addition, polarization-resolved measurements were performed to reveal the microcrystal orientations of the two phases of ice, with the spatial-dependent anisotropy pattern indicating the inhomogeneous distribution of their orientations. Furthermore, the angular patterns were theoretically explained by third-order nonlinear optics with the known crystal symmetries of the ice phases. Our work may provide new opportunities to investigate many intriguing physical chemistry properties of ice under low-temperature conditions.

Inhomogeneous regularization with limited and indirect data

For an ill-posed inverse problem, particularly with incomplete and limited measurement data, regularization is an essential tool for stabilizing the inverse problem. Among various forms of regularization, the ℓp penalty term provides a suite of regularization of various characteristics depending on the value of p. When there are no explicit features to determine p, a spatially varying inhomogeneous p can be incorporated to apply different regularization characteristics that change over the domain. This study proposes a strategy to design the exponent p when the first and second derivatives of the true signal are not available, such as in the case of indirect and limited measurement data. The proposed method extracts statistical and patch-wise information using multiple reconstructions from a single measurement, which assists in classifying each patch to predefined features with corresponding p values. We validate the robustness and effectiveness of the proposed approach through a suite of numerical tests in 1D and 2D, including a sea ice image recovery from partial Fourier measurement data. Numerical tests show that the exponent distribution is insensitive to the choice of multiple reconstructions.

Left atrial reservoir strain measurements derived from intracardiac echocardiography in patients with atrial fibrillation: comparison with transthoracic echocardiography

BackgroundIntracardiac echocardiography (ICE) provides accurate left atrial (LA) anatomical information in the procedure of atrial fibrillation (AF) ablation but lacks LA functional assessment. LA reservoir strain (LASr) is an excellent marker of LA reservoir function. This study aimed to assess the agreement between LASr derived from ICE and transthoracic echocardiography (TTE) in AF patients and analyze the reproducibility of LASr assessed by ICE combined with speckle tracking imaging.MethodsThis study prospectively enrolled 110 patients with a clinical diagnosis of AF who were ready for AF ablation, including 71 patients with paroxysmal AF and 39 with persistent AF. TTE and ICE examinations were performed on each individual before AF ablation. LASr measurements derived from ICE and TTE images were using dedicated LA-tracking software. Pearson correlation coefficients (r) and Bland–Altman plots were used to evaluate the agreement of LASr between the two modalities. Intraclass correlation coefficients (ICCs) were used to assess intra- and inter-observer reproducibility.ResultsThe agreement between LASr obtained from ICE and TTE, especially between LASrLPV (LASr derived from LA left pulmonary vein view of ICE) and LASrTTE (LASr derived from TTE) were good in both paroxysmal and persistent AF patients [r = 0.890 (P < 0.001) for overall population; r = 0.815 (P < 0.001) and Bias ± LOA: -0.3 ± 9.9% for paroxysmal AF; r = 0.775 (P < 0.001) and Bias ± LOA: -2.6 ± 3.9% for persistent AF, respectively]. But the values of LASr derived from ICE were slightly lower than those of TTE, especially in patients with persistent AF. The ICCs for LASr derived from ICE were excellent (all ICCs > 0.90).ConclusionsIn patients with AF, LASr derived from ICE demonstrated excellent reproducibility and showed good agreement with LASr obtained from TTE. Obtaining LASr from ICE images may be a supplementary method to evaluate LA reservoir function in AF patients and expands the potential of ICE in the field of cardiac function assessment.Graphical

Sea Ice Classification Using Mutually Guided Contexts

In this paper, sea ice classification on a remote sensing image given just a small number of labeled pixels is investigated. Effective sea ice classification is rendered from two aspects. First, a feature extraction method is developed. It extracts the context feature from a classification map. Second, an iterative learning paradigm is established. The labeled pixels are divided into two training subsets. At each iteration, the context feature for one subset is extracted from the classification map which is obtained subject to the other subset. Therefore, the two subsets mutually guide each other for updating the context feature in an iterative manner, which finally renders effective sea ice classification. The above paradigm is referred to as mutually guided contexts. The advantages of the new paradigm are two-fold. First, the context feature enriches the sea ice image representation in a general manner regardless of the types of raw image data. Second, the two training subsets keep providing different refined classification maps for each other such that the comprehensiveness of the context feature is recursively enhanced. Therefore, the paradigm of mutually guided contexts comprehensively characterizes the sea ice image representation for training and classification even when only small training data are available. Experiments validate the effectiveness of the mutually guided contexts for sea ice classification.

Domain-invariant icing detection on wind turbine rotor blades with generative artificial intelligence for deep transfer learning

Abstract Wind energy’s ability to liberate the world from conventional sources of energy relies on lowering the significant costs associated with the maintenance of wind turbines. Since icing events on turbine rotor blades are a leading cause of operational failures, identifying icing in advance is critical. Some recent studies have utilized deep learning (DL) techniques to predict icing events with high accuracy by leveraging rotor blade images, but these studies only focus on specific wind parks and fail to generalize to unseen scenarios (e.g., new rotor blade designs). In this paper, we aim to facilitate ice prediction on the face of lack of ice images in new wind parks. We propose the utilization of synthetic data augmentation via a generative artificial intelligence technique—the neural style transfer algorithm to improve the generalization of existing ice prediction models. We also compare the proposed technique with the CycleGAN as a baseline. We show that training standalone DL models with augmented data that captures domain-invariant icing characteristics can help improve predictive performance across multiple wind parks. Through efficient identification of icing, this study can support preventive maintenance of wind energy sources by making them more reliable toward tackling climate change.

Sea ice image classification based on ResFPG network and heterogeneous data fusion

ABSTRACT Sea ice detection has played an important role in climate protection and strategic deployment. Due to the autonomous learning characteristics of deep learning, it has been gradually applied to the classification of remote sensing sea ice images. At present, deep learning models are mostly used in sea ice classification of single source remote sensing data. Due to the limitations of single source data and the information loss of deep learning model in the process of feature extraction layer by layer, it is inevitable to encounter a bottleneck in sea ice detection requiring fine classification. To solve the above problems, this paper proposes a sea ice image classification method based on ResNet16-feature pyramid networks-spatial pyramid pooling-gated fusion network (ResFPG) and heterogeneous data fusion. In the feature extraction part, the method uses the improved ResNet16 to extract the multi-level feature information of sea ice in synthetic aperture radar data and optical data, reducing information loss in the feature extraction process, then mines and fuses the low-level spatial information and high-level semantic information through the improved feature pyramid networks (FPN), and then collects and fuses the output features of different scales through the spatial pyramid pooling (SPP) network. In the feature fusion part, a gated feature-level fusion strategy is designed to further improve the overall classification accuracy by adaptively adjusting the feature contribution of two heterogeneous sources of data through the gated fusion network (GFN). In order to verify the effectiveness of this method, we use two sets of heterogeneous sea ice remote sensing data located in Hudson Bay area for experiments. The experimental results show that compared with other image classification methods, the proposed method fully excavates and integrates the multi-scale and multi-level features in heterogeneous data, effectively distinguishes the feature contribution, and achieves better classification results (97.14% and 95.85%).