Precipitable water vapor (PWV) plays a vital role in climate research, especially for Antarctica in which meteorological observations are insufficient due to the adverse climate and topography therein. Reanalysis data sets provide a great opportunity for Antarctic water vapor research. This study investigates the climatological PWV means, variability and trends over Antarctica from four reanalyses, including the fifth generation of European Centre for Medium-Range Weather Forecasts (ECMWF) Reanalysis (ERA5), the Second Modern-Era Retrospective analysis for Research and Applications (MERRA-2), Japanese 55-year Reanalysis (JRA-55) and National Centers for Environmental Prediction/Department of Energy (NCEP/DOE), in the period of 2001–2018 based on radiosonde and GNSS observations. PWV data from the ERA5, MERRA-2, JRA-55 and NCEP/DOE have been evaluated by radiosonde and GNSS observations, showing that ERA5 and MERRA-2 perform better than JRA-55 and NCEP/DOE with mean root mean square (RMS) errors below 1.2 mm. The climatological PWV mean distribution over Antarctica roughly shows a decreasing trend from west to east, with the highest content in summer and the lowest content in winter. The PWV variability is generally small over Antarctica, showing a seasonal dependence that is larger in the cold season and smaller in the warm season. PWV trends for all reanalyses at most Antarctic regions are insignificant and most reanalyses present overall drying trends from 2001 to 2018, except for ERA5 exhibiting a moistening trend. PWV trends also show seasonal and regional dependence. All reanalyses are generally consistent with radiosonde and GNSS observations in reproducing the PWV means (mean differences within 1.1 mm), variability (mean differences within 3%) and trends (mean differences within 6.4% decade⁻¹) over Antarctica, except for NCEP/DOE showing spurious variability and trends in East Antarctica. Results can help us further understand these four reanalysis PWV products and promote climate research in Antarctica.

Discriminating marsh vegetation is critical for the rapid assessment and management of wetlands. The study area, Honghe National Nature Reserve (HNNR), a typical freshwater wetland, is located in Northeast China. This study optimized the parameters (mtry and ntrees) of an object-based random forest (RF) algorithm to improve the applicability of marsh vegetation classification. Multidimensional datasets were used as the input variables for model training, then variable selection was performed on the variables to eliminate redundancy, which improved classification efficiency and overall accuracy. Finally, the performance of a new generation of Chinese high-spatial-resolution Gaofen-1 (GF-1) and Ziyuan-3 (ZY-3) satellite images for marsh vegetation classification was evaluated using the improved object-based RF algorithm with accuracy assessment. The specific conclusions of this study are as follows: (1) Optimized object-based RF classifications consistently produced more than 70.26% overall accuracy for all scenarios of GF-1 and ZY-3 at the 95% confidence interval. The performance of ZY-3 imagery applied to marsh vegetation mapping is lower than that of GF-1 imagery due to the coarse spatial resolution. (2) Parameter optimization of the object-based RF algorithm effectively improved the stability and classification accuracy of the algorithm. After parameter adjustment, scenario 3 for GF-1 data had the highest classification accuracy of 84% (ZY-3 is 74.72%) at the 95% confidence interval. (3) The introduction of multidimensional datasets improved the overall accuracy of marsh vegetation mapping, but with many redundant variables. Using three variable selection algorithms to remove redundant variables from the multidimensional datasets effectively improved the classification efficiency and overall accuracy. The recursive feature elimination (RFE)-based variable selection algorithm had the best performance. (4) Optical spectral bands, spectral indices, mean value of green and NIR bands in textural information, DEM, TWI, compactness, max difference, and shape index are valuable variables for marsh vegetation mapping. (5) GF-1 and ZY-3 images had higher classification accuracy for forest, cropland, shrubs, and open water.

Tropospheric delay is a major error source in the Global Navigation Satellite System (GNSS), and the weighted mean temperature (T_m) is a key parameter in precipitable water vapor (PWV) retrieval. Although reanalysis products like the National Centers for Environmental Prediction (NCEP) and the European Center for Medium-Range Weather Forecasts (ECMWF) Re-Analysis-Interim (ERA-Interim) data have been used to calculate and model the tropospheric delay, T_m, and PWV, the limitations of the temporal and spatial resolutions of the reanalysis data have affected their performance. The release of the fifth-generation accurate global atmospheric reanalysis (ERA5) and the second Modern-Era Retrospective analysis for Research and Applications (MERRA-2) provide the opportunity to overcome these limitations. The performances of the zenith tropospheric delay (ZTD), zenith wet delay (ZWD), T_m, and zenith hydrostatic delay (ZHD) of ERA5 and MERRA-2 data from 2016 to 2017 were evaluated in this work using GNSS ZTD and radiosonde data over the globe. Taking GNSS ZTD as a reference, the ZTD calculated from MERRA-2 and ERA5 pressure-level data were evaluated in temporal and spatial scales, with an annual mean bias and root mean square (RMS) of 2.3 and 10.9 mm for ERA5 and 4.5 and 13.1 mm for MERRA-2, respectively. Compared to radiosonde data, the ZHD, ZWD, and T_m derived from ERA5 and MERRA-2 data were also evaluated on temporal and spatial scales, with annual mean bias values of 1.1, 1.7 mm, and 0.14 K for ERA5 and 0.5, 4.8 mm, and –0.08 K for MERRA-2, respectively. Meanwhile, the annual mean RMS was 4.5, 10.5 mm, and 1.03 K for ERA5 and 4.4, 13.6 mm, and 1.17 K for MERRA-2, respectively. Tropospheric parameters derived from MERRA-2 and ERA5, with improved temporal and spatial resolutions, can provide a reference for GNSS positioning and PWV retrieval.

Citrus has become a pivotal industry for the rapid development of agriculture and increasing farmers’ incomes in the main production areas of southern China. Knowing how to diagnose and control citrus huanglongbing has always been a challenge for fruit farmers. To promptly recognize the diagnosis of citrus huanglongbing, a new classification model of citrus huanglongbing was established based on MobileNetV2 with a convolutional block attention module (CBAM-MobileNetV2) and transfer learning. First, the convolution features were extracted using convolution modules to capture high-level object-based information. Second, an attention module was utilized to capture interesting semantic information. Third, the convolution module and attention module were combined to fuse these two types of information. Last, a new fully connected layer and a softmax layer were established. The collected 751 citrus huanglongbing images, with sizes of 3648 × 2736, were divided into early, middle, and late leaf images with different disease degrees, and were enhanced to 6008 leaf images with sizes of 512 × 512, including 2360 early citrus huanglongbing images, 2024 middle citrus huanglongbing images, and 1624 late citrus huanglongbing images. In total, 80% and 20% of the collected citrus huanglongbing images were assigned to the training set and the test set, respectively. The effects of different transfer learning methods, different model training effects, and initial learning rates on model performance were analyzed. The results show that with the same model and initial learning rate, the transfer learning method of parameter fine tuning was obviously better than the transfer learning method of parameter freezing, and that the recognition accuracy of the test set improved by 1.02~13.6%. The recognition accuracy of the citrus huanglongbing image recognition model based on CBAM-MobileNetV2 and transfer learning was 98.75% at an initial learning rate of 0.001, and the loss value was 0.0748. The accuracy rates of the MobileNetV2, Xception, and InceptionV3 network models were 98.14%, 96.96%, and 97.55%, respectively, and the effect was not as significant as that of CBAM-MobileNetV2. Therefore, based on CBAM-MobileNetV2 and transfer learning, an image recognition model of citrus huanglongbing images with high recognition accuracy could be constructed.

Mangrove-forest classification by using deep learning algorithms has attracted increasing attention but remains challenging. The current studies on the transfer classification of mangrove communities between different regions and different sensors are especially still unclear. To fill the research gap, this study developed a new deep-learning algorithm (encoder–decoder with mixed depth-wise convolution and cascade upsampling, MCCUNet) by modifying the encoder and decoder sections of the DeepLabV3+ algorithm and presented three transfer-learning strategies, namely frozen transfer learning (F-TL), fine-tuned transfer learning (Ft-TL), and sensor-and-phase transfer learning (SaP-TL), to classify mangrove communities by using the MCCUNet algorithm and high-resolution UAV multispectral images. This study combined the deep-learning algorithms with recursive feature elimination and principal component analysis (RFE–PCA), using a high-dimensional dataset to map and classify mangrove communities, and evaluated their classification performance. The results of this study showed the following: (1) The MCCUNet algorithm outperformed the original DeepLabV3+ algorithm for classifying mangrove communities, achieving the highest overall classification accuracy (OA), i.e., 97.24%, in all scenarios. (2) The RFE–PCA dimension reduction improved the classification performance of deep-learning algorithms. The OA of mangrove species from using the MCCUNet algorithm was improved by 7.27% after adding dimension-reduced texture features and vegetation indices. (3) The Ft-TL strategy enabled the algorithm to achieve better classification accuracy and stability than the F-TL strategy. The highest improvement in the F1–score of Spartina alterniflora was 19.56%, using the MCCUNet algorithm with the Ft-TL strategy. (4) The SaP-TL strategy produced better transfer-learning classifications of mangrove communities between images of different phases and sensors. The highest improvement in the F1–score of Aegiceras corniculatum was 19.85%, using the MCCUNet algorithm with the SaP-TL strategy. (5) All three transfer-learning strategies achieved high accuracy in classifying mangrove communities, with the mean F1–score of 84.37~95.25%.

Combining deep learning and UAV images to map wetland vegetation distribution has received increasing attention from researchers. However, it is difficult for one multi-classification convolutional neural network (CNN) model to meet the accuracy requirements for the overall classification of multi-object types. To resolve these issues, this paper combined three decision fusion methods (Majority Voting Fusion, Average Probability Fusion, and Optimal Selection Fusion) with four CNNs, including SegNet, PSPNet, DeepLabV3+, and RAUNet, to construct different fusion classification models (FCMs) for mapping wetland vegetations in Huixian Karst National Wetland Park, Guilin, south China. We further evaluated the effect of one-class and multi-class FCMs on wetland vegetation classification using ultra-high-resolution UAV images and compared the performance of one-class classification (OCC) and multi-class classification (MCC) models for karst wetland vegetation. The results highlight that (1) the use of additional multi-dimensional UAV datasets achieved better classification performance for karst wetland vegetation using CNN models. The OCC models produced better classification results than MCC models, and the accuracy (average of IoU) difference between the two model types was 3.24–10.97%. (2) The integration of DSM and texture features improved the performance of FCMs with an increase in accuracy (MIoU) from 0.67% to 8.23% when compared to RGB-based karst wetland vegetation classifications. (3) The PSPNet algorithm achieved the optimal pixel-based classification in the CNN-based FCMs, while the DeepLabV3+ algorithm produced the best attribute-based classification performance. (4) Three decision fusions all improved the identification ability for karst wetland vegetation compared to single CNN models, which achieved the highest IoUs of 81.93% and 98.42% for Eichhornia crassipes and Nelumbo nucifera, respectively. (5) One-class FCMs achieved higher classification accuracy for karst wetland vegetation than multi-class FCMs, and the highest improvement in the IoU for karst herbaceous plants reached 22.09%.