Arctic Sea Ice and Open Water Classification From Spaceborne Fully Polarimetric Synthetic Aperture Radar

Sea-ice mapping using Synthetic Aperture Radar (SAR) in the melt season poses challenges, primarily due to meltwater complicating the distinguishability of sea-ice types. In response to this issue, this study introduces a novel method for classifying sea ice during the Bohai Sea’s melting period. The method categorizes sea ice into five types: open water (OW), gray ice (Gi), melting gray ice (GiW), gray–white Ice (Gw), and melting gray–white Ice (GwW). To achieve this classification, 51 polarimetric features are extracted from L-, S-, and C-band PolSAR data using various polarization decomposition methods. This study assesses the separability of these features among different combinations of sea-ice type by calculating the Euclidean distance (ED). The Support Vector Machine (SVM) classifier, when employed with single-frequency polarimetric feature sets, achieves the highest accuracy for OW and Gi in the C-band, GiW in the S-band, and Gw and GwW in the L-band. Remarkably, the C-band features exhibit the overall highest accuracy when compared to the L-band and S-band. Furthermore, employing a multi-dimensional polarimetric feature set significantly improves classification accuracy to 94.55%, representing a substantial enhancement of 9% to 22% compared to single-frequency classification. Benefiting from the performance advantages of Random Forest (RF) classifiers in handling large datasets, RF classifiers achieve the highest classification accuracy of 95.84%. The optimal multi-dimensional feature composition includes the following: L-band: SE, SEI, α¯, Span; S-band: SEI, SE, Span, PV-Freeman, λ1, λ2; C-band: SE, SEI, Span, λ3, PV-Freeman. The results of this study provide a reliable new method for future sea-ice monitoring during the melting season.

Section: Multi-frequency Classifier Selectionmentioning

confidence: 97%

“…However, the RF classifier's classification accuracy continues to improve and achieves the highest overall accuracy in this experiment. This advantage may be attributed to its suitability for handling large datasets compared to other classifiers [47].…”

Section: Multi-frequency Classifier Selectionmentioning

confidence: 99%

Assessment of Sea-Ice Classification Capabilities during Melting Period Using Airborne Multi-Frequency PolSAR Data

Wang,

Zhang,

Shi

et al. 2024

“…As an active region of the Arctic sea ice, the Fram Strait is chosen as the observation area [54,55], as shown in Figure 2. The Arctic sea ice remote sensing images were captured during the summer and in a thawing period.…”

Section: Datasetmentioning

confidence: 99%

Ice Identification with Error-Accumulation Enhanced Neural Dynamics in Optical Remote Sensing Images

Xiong,

Wang,

et al. 2023

Arctic sea ice plays an important role in Arctic-related research. Therefore, how to identify Arctic sea ice from remote sensing images with high quality in an unavoidable noise environment is an urgent challenge to be solved. In this paper, a constrained energy minimization (CEM) method is applied for Arctic sea ice identification, which only requires the target spectrum. Moreover, an error-accumulation enhanced neural dynamics (EAEND) model with strong noise immunity and high computing accuracy is proposed to aid with the CEM method for Arctic sea ice identification. With the theoretical analysis, the proposed EAEND model possesses a small steady-state error in noisy environments. Finally, compared with other existing models, the proposed EAEND model can not only complete sea ice identification in excellent fashion, but also has the advantages of high efficiency and noise immunity.

“…Gray-level co-occurrence matrices (GLCMs) are the most popular methods for texture feature extraction [24,[26][27][28][29]. After feature extraction, a ML model is then employed to classify sea ice, such as random forest (RF) [29,30], k-means [22,24], supporting vector machine (SVM) [26][27][28][31][32][33][34], decision tree [23] and Bayesian methods [35]. The main drawback of these methodologies is that the complicated feature engineering methodologies require a high level of professional knowledge and a large amount of time to pick up the optimal features.…”

Section: Introductionmentioning

confidence: 99%

Sea Ice Detection from RADARSAT-2 Quad-Polarization SAR Imagery Based on Co- and Cross-Polarization Ratio

Zhao,

Xie,

Perrie

et al. 2024

Arctic sea ice detection is very important in global climate research, Arctic ecosystem protection, ship navigation and human activities. In this paper, by combining the co-pol ratio (HH/VV) and two kinds of cross-pol ratio (HV/VV, HV/HH), a novel sea ice detection method is proposed based on RADARSAT-2 quad-polarization synthetic aperture radar (SAR) images. Experimental results suggest that the co-pol ratio shows promising capability in sea ice detection at a wide range of incidence angles (25–50°), while the two kinds of cross-pol ratio are more applicable to sea ice detection at small incidence angles (20–35°). When incidence angles exceed 35°, wind conditions have a great effect on the performance of the cross-pol ratio. Our method is validated by comparison with the visual interpretation results. The overall accuracy is 96%, far higher than that of single polarization ratio (PR) parameter-based methods. Our method is suitable for sea ice detection in complex sea ice and wind conditions.