Accurate prediction of food crop yield is of great significance for global food security and regional trade stability. Since remote sensing data collected from unmanned aerial vehicle (UAV) platforms have the features of flexibility and high resolution, these data can be used as samples to develop regional regression models for accurate prediction of crop yield at a field scale. The primary objective of this study was to construct regional prediction models for winter wheat yield based on multi-spectral UAV data and machine learning methods. Six machine learning methods including Gaussian process regression (GPR), support vector machine regression (SVR) and random forest regression (RFR) were used for the construction of the yield prediction models. Ten vegetation indices (VIs) extracted from canopy spectral images of winter wheat acquired from a multi-spectral UAV at five key growth stages in Xuzhou City, Jiangsu Province, China in 2021 were selected as the variables of the models. In addition, in situ measurements of wheat yield were obtained in a destructive sampling manner for prediction algorithm modeling and validation. Prediction results of single growth stages showed that the optimal model was GPR constructed from extremely strong correlated VIs (ESCVIs) at the filling stage (R² = 0.87, RMSE = 49.22 g/m², MAE = 42.74 g/m²). The results of multiple stages showed GPR achieved the highest accuracy (R² = 0.88, RMSE = 49.18 g/m², MAE = 42.57 g/m²) when the ESCVIs of the flowering and filling stages were used. Larger sampling plots were adopted to verify the accuracy of yield prediction; the results indicated that the GPR model has strong adaptability at different scales. These findings suggest that using machine learning methods and multi-spectral UAV data can accurately predict crop yield at the field scale and deliver a valuable application reference for farm-scale field crop management.

Typhoons can be serious natural disasters for the sustainability and development of society. The development of a typhoon usually involves a pre-existing weather disturbance, warm tropical oceans, and a large amount of moisture. This implies that a large variation in the atmospheric water vapor over the path of a typhoon can be used to study the characteristics of the typhoon. This is the reason that the variation in precipitable water vapor (PWV) is often used to capture the signature of a typhoon in meteorology. This study investigates the usability of real-time PWV retrieved from global navigation satellite systems (GNSS) for typhoons’ characterizations, and especially, the following aspects were investigated: (1) The correlation between PWV and atmospheric parameters including pressure, temperature, precipitation, and wind speed; (2) water vapor transportation during a typhoon period; and (3) the correlation between the movement of a typhoon and the transportation of water vapor. The case study selected for this research was Super Typhoon Mangkhut that occurred in mid-September 2018 in Hong Kong. The PWV time series were obtained from a conversion of GNSS-derived zenith total delays (ZTDs) using observations at 10 stations selected from the Hong Kong GNSS continuously operating reference stations (CORS) network, which are also located along the path of the typhoon. The Bernese GNSS Software (ver. 5.2) was used to obtain the ZTDs; and the root mean square (RMS) of the differences between the GNSS-ZTDs and International GNSS Service post-processed ZTDs time series was less than 8 mm. The RMS of the differences between the GNSS-PWVs (i.e., the ZTDs converted PWVs) and radiosonde-derived PWVs (RS-PWVs) time series was less than 2 mm. The changes in PWV reflect the variation in wind speed during the typhoon period to a certain degree, and their correlation coefficient was 0.76, meaning a significant positive correlation. In addition, a new approach was proposed to estimate the direction and speed of a typhoon’s movement using the time difference of PWV arrival at different sites. The direction and speed estimated agreed well with the ones published by the China Meteorological Administration. These results suggest that GNSS-derived PWV has a great potential for the monitoring and even prediction of typhoon events, especially for near real-time warnings.

Global navigation satellite systems (GNSS) has been applied to the sounding of precipitable water vapor (PWV) due to its high accuracy and high spatiotemporal resolutions. PWV obtained from GNSS (GNSS-PWV) can be used to investigate extreme weather phenomena, such as the formation mechanism and prediction of rainfalls. In the study, a new, improved model for rainfall forecasting was developed based on GNSS data and rainfall data for the 9-year period from 2010 to 2018 at 66 stations located in the USA. The new model included three prediction factors—PWV value, PWV increase, maximum hourly PWV increase. The two key tasks involved for the development of the model were the determination of the thresholds for each prediction factor and the selection of the optimal strategy for using the three prediction factors together. For determining the thresholds, both critical success index (CSI) and true skill statistic (TSS) were tested, and results showed that TSS outperformed CSI for all rainfall events tested. Then, various strategies by combining the three prediction factors together were also tested, and results indicated that the best forecast result was from the case that any two of the prediction factors were over their own thresholds. Finally, the new model was evaluated using the GNSS data for the 2-year period from 2019 to 2020 at the above mentioned 66 stations, and the probability of detection (POD) and false-alarms rate (FAR) were adopted to measure the model performances. Over the 66 stations, the POD values ranged from 73% to 97% with the mean of 87%, and the FARs ranged from 26% to 77% with the mean of 53%. Moreover, it was also found that both POD and FAR values were related to the region of the station; e.g., the results at the stations that are located in humid regions were better than the ones located in dry regions. All these results suggest the feasibility and good performance of using GNSS-PWV for forecasting rainfall.

The ionospheric total electron content (TEC) is an important ionospheric parameter, and it is widely utilized in research such as space weather prediction and precise positioning. However, it is still challenging to develop an ionospheric TEC prediction model with high accuracy. In this study, a new ionospheric TEC model over China was developed using the bidirectional long short‐term memory (bi‐LSTM) method and observations from 257 ground‐based global navigation satellite system (GNSS) stations in the Crustal Movement Observation Network of China from January 2018 to December 2021. The root mean square errors of the bi‐LSTM‐based model’s 1 and 2 hr ahead predictions on the test data set (from June 2021 to December 2021) are 1.12 and 1.68 TECU, respectively, which are 75/50/32% and 72/48/22% smaller than those of the IRI‐2016, artificial neural network and LSTM‐based models, correspondingly. The bi‐LSTM‐based model shows the best performance, which is most likely due to the fact that the sequence information in both forward and backward directions is taken into consideration in the new model. In addition, the diurnal variation, seasonal variation of the ionospheric TEC, and variations under geomagnetic storm conditions are successfully captured by the bi‐LSTM‐based model. Moreover, the TEC maps resulting from the bi‐LSTM model agree well with those obtained from the final ionospheric product from the Chinese Academy of Sciences. Hence, the new model can be a good choice for the investigation of the spatiotemporal variation trend in the ionosphere and GNSS navigation.

The convolutional neural network (CNN) method has been widely used in the classification of hyperspectral images (HSIs). However, the efficiency and accuracy of the HSI classification are inevitably degraded when small samples are available. This study proposes a multidimensional CNN model named MDAN, which is constructed with an attention mechanism, to achieve an ideal classification performance of CNN within the framework of few-shot learning. In this model, a three-dimensional (3D) convolutional layer is carried out for obtaining spatial–spectral features from the 3D volumetric data of HSI. Subsequently, the two-dimensional (2D) and one-dimensional (1D) convolutional layers further learn spatial and spectral features efficiently at an abstract level. Based on the most widely used convolutional block attention module (CBAM), this study investigates a convolutional block self-attention module (CBSM) to improve accuracy by changing the connection ways of attention blocks. The CBSM model is used with the 2D convolutional layer for better performance of HSI classification purposes. The MDAN model is applied for classification applications using HSI, and its performance is evaluated by comparing the results with the support vector machine (SVM), 2D CNN, 3D CNN, 3D–2D–1D CNN, and CBAM. The findings of this study indicate that classification results from the MADN model show overall classification accuracies of 97.34%, 96.43%, and 92.23% for Salinas, WHU-Hi-HanChuan, and Pavia University datasets, respectively, when only 1% HSI data were used for training. The training and testing times of the MDAN model are close to those of the 3D–2D–1D CNN, which has the highest efficiency among all comparative CNN models. The attention model CBSM is introduced into MDAN, which achieves an overall accuracy of about 1% higher than that of the CBAM model. The performance of the two proposed methods is superior to the other models in terms of both efficiency and accuracy. The results show that the combination of multidimensional CNNs and attention mechanisms has the best ability for small-sample problems in HSI classification.

Water vapor is one of the most important parameters in climatic studies. MODerate-resolution Imaging Spectroradiometer (MODIS) is a key instrument and can provide spatially continuous precipitable water vapor (PWV) products. This study was focused on the performance evaluation of the MODIS near-infrared PWV product (MOD-NIR-PWV) over China. For a comprehensive assessment of the performance of MOD-NIR-PWV, PWV retrieved from the measurements at the global navigation satellite systems (GNSS) stations (i.e., GNSS-PWV) and the ERA5 reanalysis dataset (ERA-PWV) from 2013 to 2018 were used as the reference. To investigate the suitability of using ERA-PWV as the reference for the evaluation, ERA-PWV was compared to the high-accuracy GNSS-PWV at 246 GNSS stations and PWV retrieved from radiosonde observations (RS-PWV) at 78 radiosonde stations over China. The results showed that the mean bias and mean root-mean-square (RMS) of the differences between ERA-PWV and GNSS-PWV across all the stations were 0.5 and 1.7 mm, respectively, and the mean correlation coefficient of the two datasets was above 0.96. The values were 0.4 and 1.9 mm and 0.97, respectively, for the differences between ERA-PWV and RS-PWV. This suggests the suitability of ERA-PWV as the reference for the evaluation of MOD-NIR-PWV. In addition, MOD-NIR-PWV was compared with both GNSS-PWV and ERA-PWV, and their mean bias and mean RMS were 2.9 and 3.8 mm (compared to GNSS-PWV) and 2.1 and 3.0 mm (compared to ERA-PWV), respectively. The positive bias values and the non-normal distribution of the differences between MOD-NIR-PWV and both reference datasets imply that a considerable systematic overestimation of MOD-NIR-PWV over China may exist. To mitigate the systematic bias, ERA-PWV was utilized as the sample data due to its spatial continuities, and a grid-based calibration model was developed based on the annual and semiannual periodicities in the differences between MOD-NIR-PWV and ERA-PWV at each grid point. After applying the calibration model to correct MOD-NIR-PWV, the calibrated MOD-NIR-PWV was compared with ERA-PWV and GNSS-PWV for precision and accuracy analysis, respectively. The comparison showed that the model could significantly improve the precision by 94% and accuracy by 53%, which manifested the effectiveness of the calibration model in improving the performance of MOD-NIR-PWV over China.