Acquisition of the Wide Swath Signiﬁcant Wave Height From HY-2C Through Deep Learning

The signiﬁcant wave height (SWH) is of great importance in industries such as ocean engineering, marine resource development, shipping and transportation. Haiyang-2C (HY-2C), the 2nd operational satellite of China’s marine dynamic exploration series, can provide all-weather, all-day, global observations of wave height, wind, and temperature. In this paper, a deep learning approach is applied to build a wide swath model based on the SWH from the altimeter and the wind speed from the scatterometer of HY-2C. Two validation sets, 1-month data at 6-minute intervals and 1-day data with an interval of 10 s, are fed into the trained model. Experiments indicate that the extending nadir SWH yields a real-time wide swath grid product along track, which can be oﬀered as support for oceanographic study, and it is superior to take the swell characteristics of ERA5 into account as the input of wide swath SWH model. In conclusion, the veriﬁcation results demonstrate the eﬀectiveness and feasibility of the wide swath SWH model.


Introduction
Significant wave height (SWH) is the most widely utilized wave parameter in climate assessment and various marine industries.Providing in situ observations, wave buoys are traditional measurement tools of SWH that can provide diverse and comprehensive information and are studied extensively in researches [1 -3].However, the single-point measurement has sparse, irregular, and limited spatial coverage, thus wider spatial coverage is of general interest.Satellite altimeters can quickly and accurately measure the global sea surface height, and their measurement accuracy has reached the centimeter level.The acquired SWH from Geosat [4], Jason-1 and Envisat [5], SARAL/AltiKa [6 -8], Sentinel 3A and 3B [9 -10], Haiyang-2 series [11 -14], Chinese-French Oceanography Satellite (CFOSAT) [15][16] altimeter (ALT) are validated by comparison with those of the buoys from the National Data Buoy Center.For the ALT data, the measurements remain restricted to the nadir tracks, which greatly limits the number of observations.Haiyang-2C (HY-2C), China's third marine dynamic environment satellite, is subordinate to the HY-2 marine remote sensing satellite series.HY-2C combines visible/infrared and microwave sensors, with high-precision orbit measurement, orbit determination capabilities, and all-weather, all-day, and global detection capabilities.
Thus, it provides support services for marine resources development, marine environmental protection, and national defense construction, etc.
Deep learning is a class of efficient algorithms for learning representative and discriminative input features in a hierarchical manner [17], which has become a hot  topic in various fields, particularly in marine remote sensing, such as classifying oceanographic objects from Synthetic Aperture Radar (SAR) data [18], retrieving sea surface wind speed in SAR images [19][20], providing higher accuracy wave parameters [21][22][23], etc.It is worth noting that Wang et al. [24] developed a deep learning approach for retrieving the SWH over an extended swath via a CFOSAT with simultaneous wind and wave observations.As a matter of fact, we attempt to find a more specific deep neural network using fewer input features to retrieve a wider swath of SWH.The gate recurrent unit (GRU) network is designed to solve the gradient disappearance problem that occurs in standard recurrent neural network, and is a popular and creditable choice because of its simple structure, fast training speed, and dominant effect.
In this paper, we adopt a deep learning method to obtain a wide swath SWH from simultaneous observations of radar ALT and microwave scatterometer (SCA) of HY-2C.The structure of this paper can be summarized as follows: Section 2 introduces the characteristics of HY-2C and ERA5, as well as adopted method and datasets.Section 3 compares and analyzes the performance of the model.Finally, Section 4 concludes this paper.

Data and Method
Haiyang-2C (HY-2C) was successfully launched on September 21, 2020 at the Jiuquan Satellite Launch Center in Inner Mongolia, China.Unlike the HY-2B satellite in a polar orbit, the HY-2C satellite operates in an inclined orbit [25], which travels at an altitude of 1336 km and presents an orbital inclination angle of 66 °.Thus, it achieves the purpose of accelerating satellite revisit to the area within 70 degrees north south from the equator, shortening the observations interval of the region, and improving the observations efficiency.HY-2C, the first large-scale inclined orbit remote sensing satellite, was constructed under the National Civil Space Infrastructure Plan [26].The satellite adopts an orbit with regression periods of 10 and 400 days in the early and later stage, respectively.
The main function of the ALT is to measure the global sea surface height, SWH and gravity field parameters and the ALT has an external calibration working mode that can cover the complete calibration area.Its operating frequency denotes13.58GHz, 5.25 GHz, pulse limited footprint is better than 2 km, and the range accuracy of marine nadir point is better than 2 cm.Although the HY-2C ALT provides SWH in Ku and C bands, we select only Ku-band measurements as experimental data in this paper due to its higher accuracy, and the fact that the C-band is designed mainly to modify the path delay caused by ionosphere during Ku-band ALT [27].
HY-2C carries a Ku-band rotating pencil-beam SCA in a non-sun-synchronous orbit.
As the main payload of marine dynamic environment, SCA has a coverage rate of not less than 90% in the global sea area for 1 to 2 days.Its main function is to measure the wind vector field (Figure 1), and the accuracy of wind direction and wind speed measurement are better than 15 °and 1.5 m/s, respectively.It also has an external calibration working mode with an operating frequency of 13.256 GHz and two beams, which are HH polarization for the internal beam and VV polarization for the external beam.Moreover, Wang et al. [28] verified the wind product of the SCA and believed its great availability.

Results and analysis
Wide-dimensional fields have more information and data volume.We utilize the wind speed and SWH simultaneously retrieved by HY-2C as features and the SWH obtained by ERA5 as labels, so that a wide swath model can be built.It is well known that the ALT data are generated almost per second.Based on the dual consideration of runtime and the amount of data, we extract the nadir SWH at six-minute intervals and filter the data with a length of 15,360 samples in the training set.While for the validation set, we execute the same operation with an integration length of 2500 observations.The swell and wind wave information in ERA5 has a certain effect on the building of wide swath SWH model, for which we gather the relevant data after matching based on the latitude and longitude of the nadir SWH, and apply them as the input features of Experiments 2 and 3, respectively.The other parameters and settings remain unchanged.
The processed datasets are fed into the GRU model, thereby the validation set results are shown in Table 1.Three columns of data with a length of 300 on the leftmost, center, and rightmost sides of wide swath SWH are selected as representatives to further analyze the performance of different stages.In Table 2, the three columns numerical results of Experiment 1 are shown that the center column has better results than the other two columns under arbitrary segmented data.The reason for this phenomenon may be that the larger the distance between both sides of the nadir SWH and the center, the less the importance of the wind in the modeling process, and the worse the effect on the nadir SWH.
In the segmented data, the validation results of the three columns for Interval 1 are the worst among those for all intervals.For Interval  2), which locates in the middle of validation set and remains superior, is selected to display the range and validation results of the three columns of data, as shown in Figure 4. Comparing Figure 4a-c, it can be found that the center column can evaluate the peaks, while SWH on the leftmost and rightmost columns are generally underestimated at the peaks and slightly overestimated at the troughs, which are consistent with the experimental results obtained in Table 2.Although the red line is not as good as the blue line in Figure 4b for some peaks, it has a better fit between 1 and 5 m.To summarize, the

Citation:
Wang, J.; Yu, T.; Deng F.; Ruan Z.; Jia Y. Acquisition of the Wide Swath Significant Wave Height From HY-2C Through Deep Learning.Remote Sens. 2021, 13, x. https://doi.org/10.3390Note:MDPI stays neutral with regard to jurisdictional claims in published maps and institutional affiliations.Copyright: © 2021 by the authors.Submitted for possible open access publication under the terms and conditions of the Creative Commons Attribution (CC BY) license (https://creativecommons.org/license s/by/4.0/).

First, the
nadir SWH obtained by ALT is employed to select the wind speed of SCA, where the time difference is less than 5 s, and we spatially choose the closest wind column.Approximately eight months (from Sep. 25, 2020 to Jun. 1, 2021) of the HY-2C and ERA5 collected datasets are considered and matched.In the configuration cases, the matching criteria are set within 100 km for geographical distance and half an hour for temporal difference.Then the validation set is divided by a length of 300, and the statistical results are analyzed through the leftmost, center and rightmost columns located in the wide swath SWH, in order to illustrate the performance of the wide swath SWH model in each segmented interval.Finally, the results of the 1-day validation set at 10-second intervals are discussed, and two small areas are selected and drawn separately to demonstrate the validation effect of the wide swath SWH model at different ranges of numerical variation.

Figure 1 .Figure 2 .Figure 3 .
Figure 1.Information of the wind speed from SCA and the Ku-band SWH from ALT are obtained simultaneously from HY-2C on May 1, 2021.

Table 1 .
Numerical results of the validation set in the GRU model with different input features.
Experiment 3 increases 0.0288 m, implying more inefficient the model output.Wind wave mainly exhibits sharp peak, which is prone to wave breaking when the wind remains strong, while swell presents smoother, with long and regular wave lines.The wide swath SWH model concentrates on long-term features in the process of learning wind and wave characteristics, while for wind wave, it behaves as local features.Overall, we mainly focus on the first two experiments in the following analysis.
5, its leftmost and rightmost columns show superior values, its center column is excellent and second only to the center column for Interval 4. We count the total number of points with SWH less than 1 m (troughs) and greater than 7 m (peaks) for each phase.Results indicate that Interval 1 has 332 minimal and maximal points, and these local features gradually disappear during the process of training, resulting in inferior performance.Surprisingly, Interval 5 has only 85 extreme points, thus dominates the results.Based on the above analysis, Interval 5 (bolder words in Table

Table 2 .
The numerical results of the segmented data on the leftmost, center, and rightmost columns in Experiment 1.