To achieve high-precision forecasting of different grades of albacore fishing grounds in the South Pacific Ocean, we used albacore fishing data and marine environmental factors data from 2009 to 2019 as data sources. An ensemble learning model (ELM) for albacore fishing grounds forecasting was constructed based on six machine learning algorithms. The overall accuracy (ACC), fishing ground forecast precision (P) and recall (R) were used as model accuracy evaluation metrics, to compare and analyze the accuracy of different machine learning algorithms for fishing grounds forecasting. We also explored the forecasting capability of the ELM for different grades of fishing grounds. A quantitative evaluation of the effects of different marine environmental factors on the forecast accuracy of albacore tuna fisheries was conducted. The results of this study showed the following: (1) The ELM achieved high accuracy forecasts of albacore fishing grounds (ACC = 86.92%), with an overall improvement of 4.39~19.48% over the machine learning models. (2) A better forecast accuracy (R2 of 81.82–98%) for high-yield albacore fishing grounds and a poorer forecast accuracy (R1 of 47.37–96.15%) for low-yield fishing grounds were obtained for different months based on the ELM; the high-yield fishing grounds were distributed in the sea south of 10° S. (3) A feature importance analysis based on RF found that latitude (Lat) had the greatest influence on the forecast accuracy of albacore tuna fishing grounds of different grades from February to December (0.377), and Chl-a had the greatest influence on the forecast accuracy of albacore tuna fishing grounds of different grades in January (0.295), while longitude (Lon) had the smallest effect on the forecast of different grades of fishing grounds (0.037).
Developing a unified chlorophyll-a (Chla) inversion algorithm for cross-water types is a significant challenge owing to the insufficiency of input features and training samples. Although machine learning algorithms can build a consistent model for different trophic waters, the accuracy of the inversion is dependent on the quality of the extended features. Here, we designed a novel hybrid framework called CHLNET, which combines a one-dimensional convolutional neural network (1D CNN) and support vector regression (SVR). The 1D CNN is used to extract features from the original band features, and the SVR is used to perform a fit of Chla. CHLNET is trained and tested using match-up pairs of SeaWiFS remote sensing reflectance [Rrs(λ)] in situ with Chla ranging from 0.009 mg/m³ to 138.046 mg/m³, which covers mostly ocean water types. Performance metrics in the log space of CHLNET were better than those of the state-of-the-art algorithms on the testing dataset, and CHLNET had the best overall performance with the largest cover area in the star plot. The frequency distribution of predicted Chla by CHLNET was more consistent with that of in situ Chla. While the spatial pattern was not smooth in low Chla concentration waters, CHLNET demonstrated excellent mapping ability at the global and local scales in high Chla concentration waters. Through the band-shift method, which transfers the Rrs(λ) of MERIS and MODIS-Aqua to the Rrs(λ) of SeaWiFS in the visible spectral range, CHLNET obtained better accuracy than the blended algorithm of OCx and CI on MERIS and MODIS-Aqua matchups, which validates the generalization of CHLNET on cross-sensor types. The results indicate that CHLNET avoids the drawbacks of manually constructing extended features and the need for merging water type-appropriate algorithms for Chla retrieval, as well as provides a new idea for unified Chla concentration inversion across water types. Thus, CHLNET may serve as an alternative approach for Chla inversion.
The prior zenith hydrostatic delay (ZHD) is an essential parameter for the Global Navigation Satellite System (GNSS) and very long baseline interferometry (VLBI) high-precision data processing. Meanwhile, the precise ZHD facilitates the separation of the high-precision zenith wet delay (ZWD) to derive precipitable water vapor (PWV). This paper analyzes the temporal variations in the residuals between GPT3 ZHD and reference ZHD from radiosonde (RS) sites, and a calibrated GPT3 (CGPT3) model is proposed for the site-specific ZHD estimation in the Chinese mainland and its surrounding areas based on the annual, semi-annual, and diurnal variations in residuals. Based on the validation using modeling RS data, the mean absolute error (MAE) and root mean square (RMS) of the CGPT3 model are 7.3 and 9.6 mm, respectively. The validation with RS ZHD not involved in the modeling suggests that the MAE and RMS of the CGPT3 model are 7.9 and 10.2 mm, respectively. These results show improvements of 16.8%/16.8% and 14.3%/13.6%, respectively, compared with the MAE and RMS of the GPT3 model and the newly proposed model (GTrop). In addition, the CGPT3 model has excellent spatial and temporal stability in the study area.
An accurate estimation of zenith wet delay (ZWD) is crucial for global navigation satellite system (GNSS) positioning and GNSS-based precipitable water vapor (PWV) inversion. The forecast Vienna Mapping Function 3 (VMF3-FC) is a forecast product provided by the Vienna Mapping Functions (VMF) data server based on the European Centre for Medium-Range Weather Forecasts (ECMWF)-based numerical weather prediction (NWP) model. The VMF3-FC can provide ZWD at any time and for any location worldwide; however, it has an uneven accuracy distribution and fails to match the application requirements in certain areas. To address this issue, in this study, a calibrated model for VMF3-FC ZWD, named the XZWD model, was developed by utilizing observation data from 492 radiosonde sites globally from 2019–2021 and the eXtreme Gradient Boosting (XGBoost) algorithm. The performance of the XZWD model was validated using 2022 observation data from the 492 radiosonde sites. The XZWD model yields a mean bias of −0.03 cm and a root-mean-square error (RMSE) of 1.64 cm. The XZWD model outperforms the global pressure and temperature 3 (GPT3) model, reducing the bias and RMSE by 94.64% and 58.90%, respectively. Meanwhile, the XZWD model outperforms VMF3-FC, with a reduction of 92.68% and 6.29% in bias and RMSE, respectively. Furthermore, the XZWD model reduces the impact of ZWD accuracy by latitude, height, and seasonal variations more effectively than the GPT3 model and VMF3-FC. Therefore, the XZWD model yields higher stability and accuracy in global ZWD forecasting.
The west-central South China Sea upwelling event is a critical process that regulates the climate and marine ecosystem in the region. In this study, we used sea surface temperature (SST) satellite data from 2000 to 2018 to analyze the spatial and temporal characteristics of upwelling in the west-central South China Sea and combined the wind field data to investigate the effects of wind direction and speed on upwelling. We divided the upwelling sea area into three regions based on the different shoreline angles along the eastern coast of the South China Peninsula: OU_1, OU_2, and OU_3. Our results showed that the upwelling events occurred mainly from May to September in the OU_1 and OU_2 waters. The empirical orthogonal function (EOF) decomposition of the monthly mean SST moment level field indicated a cyclical interannual variation of upwelling in the west-central South China Sea. The correlation analysis showed that wind direction changes have a significant impact on the upwelling intensity center, with the upwelling intensity center moving towards high latitudes and away from the coast when the wind direction changes from north to east. When the wind direction changes from east to south, the upwelling intensity center moves towards low latitudes and near the coast. The average lag time of upwelling events to the wind field in the central and western South China Sea was 38.9 h, with OU_2 showing a longer response time than the other seas. Our study provides important insights into the mechanisms governing upwelling in the west-central South China Sea, which can effectively promote the rational use of ecological resources and provide a scientific basis for marine ecological protection in the region.