Abstract:Sea ice type is the key parameter of Arctic sea ice monitoring. Microwave remote sensors with medium incidence and normal incidence modes are the primary detection methods for sea ice types. The Surface Wave Investigation and Monitoring instrument (SWIM) on the China-France Oceanography Satellite (CFOSAT) is a new type of sensor with a small incidence angle detection mode that is different from traditional remote sensors. The method of sea ice detection using SWIM data is also under development. The research r… Show more
“…The overall accuracy (OA) and F1 score (F1s) that are defined as seen in 'Supplementary Material' file are used to evaluate the abilities of classifiers for sea ice recognition. The introduction of classifiers is in terms of our previous work and other researches (Liu et al, 2015;Rinne and Similä, 2016;Shen et al, 2017a;Shen et al, 2017b;Jiang et al, 2019;Liu et al, 2022), so three classifiers are chosen for sea ice and sea water separation in this study, including the random forest (RF), k-nearest neighbors (KNN) and support vector machine (SVM). Then, the optimal classifier is chosen from the three ones, which is used to obtain the best feature combination.…”
Section: Methodsmentioning
confidence: 99%
“…In the discussion of our previous study, the inverse mean power (IMP) was useful to discriminate FYI and MYI (Liu et al, 2022). In this study, IMP is also introduced for sea ice and sea water separation.…”
Section: Swim Featuresmentioning
confidence: 97%
“…According to our previous work and other researches, eleven waveform features are extracted to assess the echo characteristics of SWIM at six small incidence angles (Laxon, 1994;Zygmuntowska et al, 2013;Rinne and Similä, 2016;Shen et al, 2017b;Shu et al, 2019;Liu et al, 2022). These features reflect the different waveform characteristics, for example, the power, structure, and overall characteristics of echo waveforms.…”
Section: Swim Featuresmentioning
confidence: 99%
“…Our previous study indicated that LEW and TEW did not yield satisfactory results, and the echo power (MAX) and waveform shape (TEW) could be combined to improve the effects on distinguishing between FYI and MYI (Liu et al, 2022). In this study, we expand this method to separate sea ice and sea water.…”
Section: Swim Featuresmentioning
confidence: 99%
“…Thus, SWIM data with the new observation mode can be used for sea ice recognition and contribute to sea ice monitoring methods and operational techniques. Our previous study focused on sea ice type classification (Liu et al, 2021;Liu et al, 2022), and a method to distinguish between sea ice and sea water was not fully established. In addition, two new features (Inverse mean power, IMP; Trailing edge slope, TES) were introduced for first-year ice (FYI) and multiyear ice (MYI) separation, but these features were not used for sea water recognition.…”
Sea ice recognition is one of the main tasks for sea ice monitoring in the Arctic and is also applied for the detection of other ocean phenomena. The Surface Wave Investigation and Monitoring (SWIM) instrument, as an innovative remote sensor that operates at multiple small incidence angles, is different from existing sensors with moderate and normal incidence modes for sea ice monitoring. Sea ice recognition at small incidence angles has rarely been studied. Moreover, SWIM uses a discrimination flag of sea ice and sea water to remove sea ice from sea wave products. Therefore, this research focuses on sea ice recognition in the Arctic based on SWIM data from October 2020 to April 2021. Eleven features are first extracted, and applied for the analysis of the waveform characteristics using the cumulative probability distribution (CPD) and mutual information measurement (MIM). Then, random forest (RF), k-nearest neighbor (KNN) and support vector machine (SVM) classifiers are built, and their abilities of sea ice recognition are assessed. The optimal classifier is the KNN method with Euclidean distance and k equal to 11. Feature combinations are also used to separate sea ice and sea water based on the KNN method to select the optimal combination. Thus, the optimal classifier-feature assembly at each small incidence angle is established, and the highest overall accuracy reaches 97.1%. Moreover, the application of the optimal classifier–feature assemblies is studied, and its performance is fairly good. These assemblies yield high accuracies in the short- and long-term periods of sea ice recognition, and the overall accuracies are greater than 93.1%. So, the proposed method satisfies the SWIM requirement of removing the sea ice effect. Moreover, sea ice extents and edges can be extracted from SWIM sea ice recognition results at a high level of precision greater than 94.8%. As a result, the optimal classifier–feature assemblies based on SWIM data express the effectiveness of the SWIM approach in sea ice recognition. Our work not only highlights the new sea ice monitoring technology of remote sensing at small incidence angles, but also studies the application of SWIM data in sea ice services.
“…The overall accuracy (OA) and F1 score (F1s) that are defined as seen in 'Supplementary Material' file are used to evaluate the abilities of classifiers for sea ice recognition. The introduction of classifiers is in terms of our previous work and other researches (Liu et al, 2015;Rinne and Similä, 2016;Shen et al, 2017a;Shen et al, 2017b;Jiang et al, 2019;Liu et al, 2022), so three classifiers are chosen for sea ice and sea water separation in this study, including the random forest (RF), k-nearest neighbors (KNN) and support vector machine (SVM). Then, the optimal classifier is chosen from the three ones, which is used to obtain the best feature combination.…”
Section: Methodsmentioning
confidence: 99%
“…In the discussion of our previous study, the inverse mean power (IMP) was useful to discriminate FYI and MYI (Liu et al, 2022). In this study, IMP is also introduced for sea ice and sea water separation.…”
Section: Swim Featuresmentioning
confidence: 97%
“…According to our previous work and other researches, eleven waveform features are extracted to assess the echo characteristics of SWIM at six small incidence angles (Laxon, 1994;Zygmuntowska et al, 2013;Rinne and Similä, 2016;Shen et al, 2017b;Shu et al, 2019;Liu et al, 2022). These features reflect the different waveform characteristics, for example, the power, structure, and overall characteristics of echo waveforms.…”
Section: Swim Featuresmentioning
confidence: 99%
“…Our previous study indicated that LEW and TEW did not yield satisfactory results, and the echo power (MAX) and waveform shape (TEW) could be combined to improve the effects on distinguishing between FYI and MYI (Liu et al, 2022). In this study, we expand this method to separate sea ice and sea water.…”
Section: Swim Featuresmentioning
confidence: 99%
“…Thus, SWIM data with the new observation mode can be used for sea ice recognition and contribute to sea ice monitoring methods and operational techniques. Our previous study focused on sea ice type classification (Liu et al, 2021;Liu et al, 2022), and a method to distinguish between sea ice and sea water was not fully established. In addition, two new features (Inverse mean power, IMP; Trailing edge slope, TES) were introduced for first-year ice (FYI) and multiyear ice (MYI) separation, but these features were not used for sea water recognition.…”
Sea ice recognition is one of the main tasks for sea ice monitoring in the Arctic and is also applied for the detection of other ocean phenomena. The Surface Wave Investigation and Monitoring (SWIM) instrument, as an innovative remote sensor that operates at multiple small incidence angles, is different from existing sensors with moderate and normal incidence modes for sea ice monitoring. Sea ice recognition at small incidence angles has rarely been studied. Moreover, SWIM uses a discrimination flag of sea ice and sea water to remove sea ice from sea wave products. Therefore, this research focuses on sea ice recognition in the Arctic based on SWIM data from October 2020 to April 2021. Eleven features are first extracted, and applied for the analysis of the waveform characteristics using the cumulative probability distribution (CPD) and mutual information measurement (MIM). Then, random forest (RF), k-nearest neighbor (KNN) and support vector machine (SVM) classifiers are built, and their abilities of sea ice recognition are assessed. The optimal classifier is the KNN method with Euclidean distance and k equal to 11. Feature combinations are also used to separate sea ice and sea water based on the KNN method to select the optimal combination. Thus, the optimal classifier-feature assembly at each small incidence angle is established, and the highest overall accuracy reaches 97.1%. Moreover, the application of the optimal classifier–feature assemblies is studied, and its performance is fairly good. These assemblies yield high accuracies in the short- and long-term periods of sea ice recognition, and the overall accuracies are greater than 93.1%. So, the proposed method satisfies the SWIM requirement of removing the sea ice effect. Moreover, sea ice extents and edges can be extracted from SWIM sea ice recognition results at a high level of precision greater than 94.8%. As a result, the optimal classifier–feature assemblies based on SWIM data express the effectiveness of the SWIM approach in sea ice recognition. Our work not only highlights the new sea ice monitoring technology of remote sensing at small incidence angles, but also studies the application of SWIM data in sea ice services.
scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.