Accurate and timely crop mapping using remote sensing technology is crucial for precision agriculture, yield estimation, and food security. Deep learning models trained with proper loss functions are widely used in crop mapping and have achieved promising results. However, most of the existing loss functions focus on loss optimization in a universal way, i.e., problems regarding sample imbalance, and neglect the uniqueness of crop mapping task, for which its target often shows phenological characteristics. Given this, this letter proposes a crop phenological prior cross entropy loss (PPCE) function, which focuses on guiding the training processing in the direction where crops can be better identified. It is practical and easy to use. The phenological prior is quantified using normalized difference yellow index and normalized difference vegetation index obtained in different growing periods. Under the supervision of PPCE, if a crop pixel is misclassified to other class, the prior knowledge will increase the contribution of its loss to the final loss and thus guide the network to extract more discriminative features for crop mapping. To demonstrate the performance of PPCE, five widely used loss functions combined with three typical deep learning models (LSTM, DNN, and 1D-CNN) are compared. Experimental results show better performance of PPCE than the existing loss functions with different deep learning models.

Satellite Calibration Spectrometer (SCS) onboard HY-1C/HY-1D could support a direct calibration using the Simultaneous Nadir Overpass (SNO) approach for imaging spectroradiometers with various band configurations on the same or different satellite platforms by providing precise hyperspectral radiance after onboard calibration employing a solar diffuser (SD). However, a unique phenomenon was discovered in the analysis of annual variations of onboard calibration coefficients of the SCS. Although the solar calibration scheme employing an SD was used, a season-dependent oscillation still existed, and the oscillation trend of calibration coefficients is highly correlated with the variation trend of solar beta angle. In this article, we analyzed the entire solar calibration results of SCS from HY-1C using more than three years of data and discovered that season-dependent oscillation is primarily due to the variations in the transmittance of the solar attenuation screen affected by satellite platform attitude. Furthermore, an accurate variation model of the incident angle on the solar attenuation screen was developed, and the findings demonstrate that the season-dependent oscillation of onboard calibration coefficients of SCS could be effectively removed. Finally, the model established in this article is validated by optical simulation, which shows its consistency and reliability.

Massive floatingSargassumblooms have occurred frequently in many parts of the global ocean, and satellite remote sensing provides an effective way to monitor their spatiotemporal variation. However, coarse-resolution satellite data often suffer from a data gap in nearshore waters and detection uncertainty ofSargassumamount especially for smaller patches. These limitations may be ameliorated by high-resolution satellite data, yet such great potential is hindered by the lack of reliable and easy-to-implement methods to detectSargassumslicks. Here, combining the visible and near-infrared top-of-atmosphere reflectance (RTOA) data with random forest model, a new method namely theRTOA-RF model was designed to automatically detectSargassumfrom high-resolution satellite imagery with four wavebands. Specifically, this model was successfully applied to various satellite sensors, including Gaofen1-Wide Field View Multispectral Camera (WFV; 16m), GF2 - Multispectral Scanner (4m), Gf6-WFV (16m), Huanjing1A/B - Charge Coupled Device (30m), Haiyang1C/D - Coastal Zone Imager (50m). Comparisons with visual inspection and cross-index indicated that all achieved satisfactory performance for detectingSargassumslicks, with the overall accuracy andKappavalues greater than 96% and 88% respectively. The sensitivity analysis of the model as example of different sensors suggested theRTOA-RF model can effectively identifySargassumfeatures under complex ocean background, cloud cover and sun glint, even under conditions of surface wave glitter and weakSargassumfeature with low false positive rate (Sargassum, but importantly provide thought for developing detection method of macroalgae blooms in global water.

Characterizing the uncertainties in buoy ocean wave records is critical not only for understanding the limitations ofin situwave measurements, but also for interpreting the implied accuracies of the remotely sensed products in which these buoy data are used as validation references. This letter preliminarily assesses the error of long-period swell heights (Hss) representing specific directional wave partition energy observed from deep-water buoys moored in the northeast Pacific. We propose a buoyHsserror estimation method by combining dual and triple collocation using data derived from buoys, two kinds of space-borne radars and numerical simulations. Compared to traditional methods, the proposed approach can reveal “absolute” errors (with respect to the underlying truth) from buoyHss, accepting and then confirming that swell heights from buoy, satellite and model are all uncertain. This study simultaneously employs ocean swell products derived from synthetic/real aperture radars (Sentinel-1A/B and CFOSAT/SWIM) and WaveWatch III® ocean wave model hindcasts to diagnose the accuracy of theHssvalues observed by buoys of National Data Buoy Center (NDBC) and Coastal Data Information Program (CDIP) during the period from July 2019 to October 2021. We quantify that the NDBC’s 3-m heave-pitch-roll buoy (CDIP’s Waverider buoy) recordedHsshave root-mean-square error of 0.17 m (0.12 m), or have about 10.65% (7.06%) uncertainty relative to the meanHssvalue (approximately 1.6 m). Our findings imply that the reference value uncertainties should be taken into account when understanding direct satelliteHssvalidation against buoyin situ.

Deep learning (DL)-based methods incorporating convolutional neural networks (CNNs) and recurrent neural networks (RNNs) have been successfully applied to change detection in satellite time series. However, traditional RNNs assume identical time interval between image sequences, which hardly meets the real case in satellite time series because of clouds and shadows. In this letter, a novel irregular-time-distanced recurrent CNN (IRCNN) is proposed. IRCNN consists of three sub-networks: a multi-branch Siamese CNN, irregular-time-distanced long short-term memory (ILSTM), and fully connected (FC) layers. Superior to the existing methods, IRCNN can account for temporal dependency among time series with irregular time distances. It is end-to-end trainable with samples generated using an automatic annotation generation method, which is proposed based on the prior knowledge from the continuous change detection and classification (CCDC) approach. IRCNN was tested over five study areas using Landsat time series collected between 2013 and 2020. Experiments demonstrate the effectiveness and stability of the proposed network with better performance, compared to the state-of-the-art approaches in terms of both qualitative and quantitative aspects. Our IRCNN Pytorch code and data are available athttps://github.com/thebinyang/IRCNN.

The total mean square slope (mss) of large-scale (in comparison with the scale of radar wavelengths) ocean waves can describe the roughness of the ocean surface. This important parameter has found many applications and can be determined by the dependence of large-scale mss on azimuthal angles. The Surface Waves Investigation and Monitoring instrument onboard the China France Oceanography Satellite (CFOSAT) can provide a two-dimensional (2D) normalized backscattering radar cross section (NRCS) for 2D global ocean-surface wave detection. In this paper, the 2D NRCS is used to calculate the total large-scale mss via two methods. The first method is constructed from regression, while the second scheme is derived from a three-solution method. Finally, the total large-scale mss are calculated using these methods, and the map of the distribution of the global total mss is presented for the first time. Our results show that the two sources of total large-scale mss obtained are consistent with each other. CFOSAT can provide a 2D total large-scale mss map and be used as a new data resource for global applications.

The Chinese Ocean Color and Temperature Scanner (COCTS) on board HY-1 series satellites has two thermal infrared channels with the spectrum range of 10.30-11.40 μm and 11.40-12.50 μm for sea surface temperature (SST) observations. To reprocess the Haiyang-1B (HY-1B) COCTS SST, the Bayesian cloud detection and optimal estimation (OE) SST retrieval were applied to COCTS data in this study. The Bayesian cloud detection algorithm that has been developed is based on the Bayes’ theorem and uses simulation of COCTS observations. The MODerate resolution atmospheric TRANsmission (MODTRAN) model was used for simulation of COCTS brightness temperatures. SSTs were retrieved from COCTS by OE from 2009 to 2011 in the northwest Pacific. Comparison of COCTS OE SST with in situ SST showed that the COCTS SSTs are cooler than buoy measurements by –0.23 °C on average, and the standard deviation (SD) of differences was 0.51 °C. A large component of the mean difference is attributable to the cool skin effect at the ocean surface (typically –0.15 to –0.2 °C), the remainder being attributable to simulation and calibration biases. The mean difference of COCTS OE SST with matched skin temperatures from the Advanced Along Track Scanning Radiometer (AATSR) is closer to zero, being –0.09 °C, with a SD of 0.49 °C. These validation results of COCTS OE SST demonstrate that Bayesian cloud detection and OE SST retrieval algorithm work well for improving COCTS SST accuracy, and show the potential of these methods to help develop SST products for operational HY-1 satellites, HY-1C and HY-1D.

The data quality of the satellite-retrieved water-leaving reflectance (Rrs) depends on the accuracy of radiometric calibration and the performance of atmospheric correction. A radiometric calibration scheme (RCS) has been developed to ensure the accuracy of Rrs through the gain adjustment factors (GAFs) to adjust the satellite calibrated data. The GAF is obtained from the ratio of the simulated reflectance at the top of atmosphere to the calibrated values. The simulated reflectance is computed by a satellite image simulation model (SISM) based on a dataset of climatological global Rrs images according to the same geometric angles of the image pixels. The dataset, taken as a kind of the pseudo-invariant calibration sites for in situ measurements, is generated from the average of standard satellite-retrieved Rrs during more than two decades (1997–2019). The SISM inputs the aerosol properties retrieved from the satellite level 1B data (L1B) and uses the same algorithms of the data-processing system. The results show that the accuracy of the calibration of the website downloaded Chinese Ocean Color and Temperature Scanner on the Haiyang-1C satellite (COCTS/HY-1C) is beyond the requirement of the operational data-processing system (higher than 10%). The daily GAFs can be used to recalibrate the L1B data and monitor the daily sensor degradations. The influences of GAFs are assessed on different meteorological conditions, indicating that the values decrease with the increase of the aerosol optical depths (AODs) but the average of the GAF image is little affected by the meteorological conditions. The uncertainty of GAFs was tested by the different inputs of Rrs values and the results show that they are actually little affected by errors of the Rrs inputs. Therefore, the RCS, taking the advantage of vicarious calibration, offers a tool to recalibrate the COCTS/HY-1C L1B data for the data reprocessing system.

The HY-2 series scatterometers (HSCAT) are now providing global Ku-band radar observations. In order to build two-decade normalized radar cross section ($\sigma ^{\circ }$) datasets with high quality and high stability, increased attention should first be paid to the instrument variations caused by space environments. The HY-2B scatterometer (HSCAT-B) has operated to yield a two-year dataset in orbit. The monitoring of long-term ocean calibration results and telemetric temperatures indicate that beam radiometric imbalances and long-term instability exist in$\sigma ^{\circ }$due to the gain variations related to temperature changes. Such variations will result in estimated$\sigma ^{\circ }$biases with a peak-to-peak of approximately 0.5 dB. Gain-related calibration models depicting the functions of temperatures were developed using ocean calibration results. The beam radiometric imbalances were corrected using linear gain compensation models of antenna temperatures. The long-term instability was corrected using a linear dependence on microwave front-end and antenna temperatures. Following gain-related calibration, the beam imbalances and long-term instability of the HSCAT-B$\sigma ^{\circ }$were eliminated. The seasonal responses over the Amazon rainforest were also found to correspond to the QuikSCAT$\sigma ^{\circ }$measurements, with amplitudes of approximately 0.15 dB for the morning passes and approximately 0.1 dB for the evening passes. The corrected$\sigma ^{\circ }$will be more suitable for the generation of climate data records. In addition, with the exception of the prelaunch thermal vacuum test, the external calibrations using natural targets are considered to be alternative approaches to gain-related calibrations due to the temperature variations of radar electronics.

Nowadays, Sentinel-1 (S-1) synthetic aperture radars (SARs) operating in wave mode and the real aperture radar (RAR) called Surface Waves Investigation and Monitoring (SWIM) onboard the China-France Oceanography SATellite (CFOSAT) are the only two kinds of spaceborne radars providing directional ocean wave information globally. To quantify the absolute uncertainties in the swell wave heights of a specific wave system (Hss) observed from these two spaceborne sensors, a triple colocation error model is exploited via WaveWatch III (WW3) wave model hindcasts for the first time. After implementing spatiotemporal collocation, cross-assigning swell partitions, and rejecting suspicious data, a database of the optimal-matched Hss triplets (S-1, SWIM, and WW3) is determined over a one-year period (June 2020 to June 2021). Qualitatively, traditional dual intercomparisons indicate the inconsistency between the Hss from both SAR and RAR radars in terms of systematic biases. Furthermore, the triple collocated error analysis quantitively reveals that, at a global scale, SWIM onboard CFOSAT has the least uncertainty in Hss (~0.2 m root-mean-square error (RMSE) and ~11% scatter index (SI)) compared with S-1 SAR (0.35-0.50 m RMSE and 17% - 26% SI depending on incidence modes) and WW3, under the assumption that the random errors of the three data sources are independent, indicating that the newly launched SWIM instrument is an invaluable resource of directional wave information for the scientific community. The results are discussed with respect to regional error characteristics along with a feasible explanation of error sources. The findings could be helpful for better understanding and synergistically exploiting the Hss datasets from these two spaceborne radars.

The comparison and verification of ocean wave spectrum by remote sensing and by in-situ measurements at the spectral level is quite rare, because the use of the traditional comparison method lead to very limited spatio-temporal matching pairs. In this paper, a new comparison method is proposed. With this method, under different sea conditions (wind wave mainly/swell mainly) and sea surface conditions (wind speed smaller than 20m/s, significant wave height from 1m to 7m), mean directional wave height spectra from SWIM (Surface Waves Investigation and Monitoring) are compared at the spectral level to the buoy counterparts, in different classes of sea-state. This includes the comparison of the omni-directional wave height spectrum and the directional function at the peak wave number. The comparison results show that under medium and high sea conditions, wave directional spectra provided by the SWIM beams at 8 ° and 10 ° incidence have a high consistency with those from buoy data. Under low sea conditions, the measurement bias of SWIM wave directional spectra mainly comes from three phenomena which are, by order of importance, an abnormal lifting of spectral energy caused by non- wave components at low wave numbers (parasitic peak), from the non-linear surfboard effect in the radar imaging mechanism and from a slight underestimation of speckle noise spectral density.

Change detection in time series is among the most critical problems in earth monitoring and attracts extensive attention in the remote sensing community. The task is, however, nontrivial because available images are irregularly collected due to interference by clouds and shadows. Traditional recurrent neural networks neglect such information and thus degrade the possibility of distinguishing pseudochanges (caused by intra-annual and inter-annual dynamics) and real changes. To this end, we proposed an unsupervised time-distance-guided convolutional recurrent network (UTRNet) for change detection in irregularly collected images. UTRNet is distinctive because the influence of pseudochanges can be suppressed by adopting a novel time-distance-guided long short-term memory (TLSTM) unit, in which input and forget gates are modified to adapt to irregular time distances. To the best of our knowledge, this is the first time that the influence of pseudochanges can be suppressed using irregular time distances. Moreover, to make UTRNet more applicable, a weighted prechange detection model is proposed to extract the most reliable training samples automatically. In the training process, unlike existing approaches that only care about changed and unchanged sample imbalance, our UTRNet also pays attention to imbalance between hard and easy samples and proposes a new focal weighted cross-entropy loss, which helps to make the training process focus on hard changed samples. The proposed UTRNet is validated on Landsat 8 time series data collected over nine typical scenes in the 2013-2021 period. Qualitative and quantitative comparisons with several state-of-the-art methods suggest the superior performance of UTRNet. Our dataset and codes are available at https://github.com/thebinyang/UTRNet.

Optical remote sensing is applied in the identification, classification, and quantification of weathered oil spills. The automatic detection of oil spills through optical imaging is yet a challenge, because various oils under different sunglint reflections have complex optical image characteristics. Generally, there are two types of weathered oil spills, namely, non-emulsified oil slicks (NEOS) and oil emulsions (OE), which show different image characteristics under various sunglint reflections. The Coastal Zone Imager (CZI) onboard China’s HaiYang-1C/D (HY-1C/D) satellites can provide multispectral images with high spatial resolution and wide coverage for operational monitoring of oil spills. In this study, we applied an adaptive dynamic detector incorporating a built in oil–water mixture distribution classifier, specifically for different sunglint reflections, to automatically extract oil spills from CZI images. The spatial heterogeneity distribution of various oil spills could be quantified using a novel separability index, and then, the optimal oil–water segmentation proportion and scale could be obtained. Oil spills are discriminated and extracted under different sunglint reflections, with the variable scale detector implemented by tiling sliding windows of classifiers on detection images, from which respective volumes are derived with lower uncertainties. This approach also uses spatial and spectral ancillary information to improve weathered oils extraction confidence. The results show stable variable-scale extraction accuracies of approximately 90% and 80% for NEOS and EO, respectively. Therefore, the spatio–spectral–distribution comprehensive feature provides a new approach for the automatic extraction of oil spills from optical remote sensing images.

The coastal zone imager (CZI) onboard HY-1C satellite provides a new data source to monitor the lake environments. Here, we provided a preliminary evaluation for the applications of CZI on inland lakes and a comparison with the in situ, Landsat-8 operational land imager (OLI), and Sentinel-2 multispectral instrument (MSI) measurements. First, the in-orbit signal-to-noise ratios (SNRs) were estimated based on homogenous ocean pixels. SNRs of CZI reached ~200:1 in the visible bands and ~150:1 at the near-infrared bands, which are comparable with the OLI and slightly higher than those of the MSI. Then, the performance of 6SV and fast line-ofsight atmospheric analysis of hypercubes (FLAASH) models on the retrievals of remote sensing reflectance (Rrs) from CZI measurements was evaluated. 6SV-derived Rrs showed higher accuracy than that of FLAASH, validated by the synchronous in situ (R2≃ 0.50, absolute percent difference (APD) ≃20%) and OLI-derived Rrs (R2≃ 0.75, APD ≃5%). Finally, the abilities of CZI to observe cyanobacterial bloom, suspended particular matter (SPM), and chlorophyll-a (Chla) were assessed. CZIderived, the area of cyanobacterial bloom and SPM, showed good agreements with the results yielded by the OLI and MSI data on May 24, 2019, in Lake Taihu (R2= 0.68, root-mean-square error (RMSE) = 9.68 mg/L, APD = 13.52% for SPM). While CZI only has four wide bands, Chla derived by CZI using an empirical algorithm was relatively consistent with MSI-derived values. CZI demonstrated a decent performance in monitoring the environments of large lakes, and it is expected to add the bands for atmospheric correction and further works in the small-medium lakes in the future.

Ocean color satellite sensors have become an indispensable component in the Earth Observing System, in which the use of multiple ocean color satellite sensors not only improves the spatiotemporal coverage of the global oceans but also maintains the continuity of the data products for long-term monitoring. In this research, the performance of a new ocean color satellite sensor Chinese Ocean Color and Temperature Scanner (COCTS) from HY1C launched in September 2018 is thoroughly evaluated with two important aspects: the signal-to-noise ratio (SNR) at the top of the atmosphere and the uncertainty in the remote-sensing reflectance Rrs) products. The results showed that the SNR of the COCTS can satisfy the requirements of the ocean color applications, and the uncertainty in the Rrs at the blue bands in the ocean waters meets the demand of less than 5%. A further comparison with other well-known ocean color sensors indicates that not only the COCTS can provide reliable ocean color data but also the processing system is robust and reliable. These results provide a solid base for merging the COCTS products with other ocean color sensors for the studies of ocean biogeochemistry.

The Chinese ocean color and temperature scanner (COCTS) onboard the HY-1C satellite was launched on September 7, 2018, and has been providing global multispectral Earth observation data as a new spaceborne sensor for ocean color detection since September 10, 2018. In this study, an atmospheric correction algorithm using a composite of the algorithms developed by Wang and Gordon (1994) and Heet al.(2004) and a chlorophyll-a concentration retrieval method that is a composite of the OC4 and color index (CI) algorithms are used to derive the global chlorophyll-a concentration from COCTS. The retrieval products are validated againstin situdata measured in the East China Sea and the South China Sea during the in-orbit testing activity for the HY-1C satellite with an unbiased percentage difference (UPD) of 39%, and the data are also validated against the Aerosol Robotic Network-Ocean Color (AERONET-OC) data with a UPD of 39%. The daily global chlorophyll-a concentration from COCTS with a gridded resolution of 9.2 km and a time period from September 10, 2018 to February 29, 2020 is compared with the same products from MODIS and VIIRS. The UPDs of COCTS against MODIS onboard Terra are approximately 20%, and the mean biases (in logarithm form) are approximately zero. Examples of chlorophyll-a concentration retrieval results in specific cases along the eastern coast of China and the Kuroshio Current are also presented to show the performance of the algorithms used in this study. The retrieval and evaluation results show that COCTS onboard HY-1C demonstrates satisfactory performance for global chlorophyll-a concentration observations.

The first rotating fan beam scatterometer onboard China-France Oceanography Satellite (CFOSAT) was successfully launched on October 29, 2018. CFOSAT SCATterometer (CSCAT) is dedicated to the monitoring of sea surface wind vectors but also provides valuable data for the applications over land and Polar Regions. This article provides an overview of the relevant procedures of CSCAT data processing, including onboard signal processing and operational ground processing. Then a post-launch analysis is carried out to evaluate the first results of CSCAT L1 and L2 products. It shows that the CSCAT instrument is generally stable in terms of noise measurements and internal calibration, unless there is any important change in the system configuration. Specifically, the CSCAT backscatter (σθ) precision and wind quality are studied using a set of collocated ancillary data. The σθprecision degrades as wind speed decreases, and it is relatively low at high incidence angles (e.g., θ >46°). In particular, backscatter estimation of the horizontally polarized beam should be further improved by correcting the noise subtraction factor. The retrieved CSCAT winds are in good agreement with the European Centre for Medium Range Weather Forecasts (ECMWF) winds, the Advanced Scatterometer (ASCAT) winds, as well as the buoy winds. However, due to unresolved calibration and interbeam consistency problems, the wind quality degrades remarkably for the out-swath and the nadir-region wind vector cells, implying that the σθcalibration should be improved in the future updates.

The China-France Oceanography Satellite (CFOSAT) to be launched in October 2018 will carry two innovative payloads, i.e., the surface wave investigation and monitoring instrument and the rotating fan-beam scatterometer [CFOSAT scatterometer (CFOSCAT)]. Both instruments, operated in Ku-band microwave frequency, are dedicated to the measurement of sea surface wave spectra and wind vectors, respectively. This paper provides an overview of the system definition and characteristics of the CFOSCAT instrument. A prelaunch analysis is carried out to estimate the scatterometer backscatter and wind quality based on the developed CFOSCAT simulator prototype. The overall simulation includes two parts: first, a forward model is developed to simulate the ocean backscatter signals, accounting for both instrument and geophysical noise. Second, a wind inversion processor is used to retrieve wind vectors from the outputs of the forward model. The benefits and challenges of the novel observing geometries are addressed in terms of the CFOSCAT wind retrieval. The simulations show that the backscatter accuracy and the retrieved wind quality of CFOSCAT are quite promising and meet the CFOSAT mission requirements.

Rotating fan-beam scatterometer (RFSCAT) is a new type of satellite scatterometer that was proposed about one decade ago.However, just as other rotating scatterometers, relatively larger wind retrieval errors occur in the nadir and outer regions than in the middle regions of the swath. In order to address this problem, a modified wind vector retrieval algorithm for RFSCAT is presented in this paper. The new algorithm is featured with adaptively extending the range of wind direction for each wind vector cell position across the whole swath according to the distribution histogram of the retrieved wind direction bias. Simulation experiments demonstrated that the new established algorithm can effectively improve the wind direction retrieval accuracy in the nadir and outer regions of the RFSCAT swath.