Accurate estimation of the satellite‐based global terrestrial latent heat flux (LE) at high spatial and temporal scales remains a major challenge. In this study, we introduce a Bayesian model averaging (BMA) method to improve satellite‐based global terrestrial LE estimation by merging five process‐based algorithms. These are the Moderate Resolution Imaging Spectroradiometer (MODIS) LE product algorithm, the revised remote‐sensing‐based Penman‐Monteith LE algorithm, the Priestley‐Taylor‐based LE algorithm, the modified satellite‐based Priestley‐Taylor LE algorithm, and the semi‐empirical Penman LE algorithm. We validated the BMA method using data for 2000–2009 and by comparison with a simple model averaging (SA) method and five process‐based algorithms. Validation data were collected for 240 globally distributed eddy covariance tower sites provided by FLUXNET projects. The validation results demonstrate that the five process‐based algorithms used have variable uncertainty and the BMA method enhances the daily LE estimates, with smaller root mean square errors (RMSEs) than the SA method and the individual algorithms driven by tower‐specific meteorology and Modern Era Retrospective Analysis for Research and Applications (MERRA) meteorological data provided by the NASA Global Modeling and Assimilation Office (GMAO), respectively. The average RMSE for the BMA method driven by daily tower‐specific meteorology decreased by more than 5 W/m² for crop and grass sites, and by more than 6 W/m² for forest, shrub, and savanna sites. The average coefficients of determination (R²) increased by approximately 0.05 for most sites. To test the BMA method for regional mapping, we applied it for MODIS data and GMAO‐MERRA meteorology to map annual global terrestrial LE averaged over 2001–2004 for spatial resolution of 0.05°. The BMA method provides a basis for generating a long‐term global terrestrial LE product for characterizing global energy, hydrological, and carbon cycles.

Wine grape quality and quantity are affected by vine growing conditions during critical phenological stages. Field observations of vine growth stages are too sparse to fully capture the spatial variability of vine conditions. In addition, traditional grape yield prediction methods are time consuming and require large amount grape samples. Remote sensing data provide detailed spatial and temporal information regarding vine development that is useful for vineyard management. In this study, Landsat surface reflectance products from 2013 and 2014 were used to map satellite-based Normalized Difference Vegetation Index (NDVI) and leaf area index (LAI) over two Vitis vinifera L. cv. Pinot Noir vineyards in California, USA. The spatial correlation between grape yield maps and the interpolated daily time series (LAI and NDVI) was quantified. NDVI and LAI were found to have similar performance as a predictor of spatial yield variability, providing peak correlations of 0.8 at specific times during the growing season, and the timing of this peak correlation differed for the two years of study. In addition, correlations with maximum and seasonal-cumulative vegetation indices were also evaluated, and showed slightly lower correlations with the observed yield maps. Finally, the within-season grape yield predictability was examined using a simple strategy in which the relationship between grape yield and vegetation indices were calibrated with limited ground measurements. This strategy has a strong potential to improve the accuracy and efficiency of yield estimation in comparison with traditional approaches used in the wine grape growing industry.

Timely and accurate estimation of the area and distribution of crops is vital for food security. Optical remote sensing has been a key technique for acquiring crop area and conditions on regional to global scales, but great challenges arise due to frequent cloudy days in southern China. This makes optical remote sensing images usually unavailable. Synthetic aperture radar (SAR) could bridge this gap since it is less affected by clouds. The recent availability of Sentinel-1A (S1A) SAR imagery with a 12-day revisit period at a high spatial resolution of about 10 m makes it possible to fully utilize phenological information to improve early crop classification. In deep learning methods, one-dimensional convolutional neural networks (1D CNNs), long short-term memory recurrent neural networks (LSTM RNNs), and gated recurrent unit RNNs (GRU RNNs) have been shown to efficiently extract temporal features for classification tasks. However, due to the complexity of training, these three deep learning methods have been less used in early crop classification. In this work, we attempted to combine them with an incremental classification method to avoid the need for training optimal architectures and hyper-parameters for data from each time series. First, we trained 1D CNNs, LSTM RNNs, and GRU RNNs based on the full images’ time series to attain three classifiers with optimal architectures and hyper-parameters. Then, starting at the first time point, we performed an incremental classification process to train each classifier using all of the previous data, and obtained a classification network with all parameter values (including the hyper-parameters) at each time point. Finally, test accuracies of each time point were assessed for each crop type to determine the optimal time series length. A case study was conducted in Suixi and Leizhou counties of Zhanjiang City, China. To verify the effectiveness of this method, we also implemented the classic random forest (RF) approach. The results were as follows: (i) 1D CNNs achieved the highest Kappa coefficient (0.942) of the four classifiers, and the highest value (0.934) in the GRU RNNs time series was attained earlier than with other classifiers; (ii) all three deep learning methods and the RF achieved F measures above 0.900 before the end of growth seasons of banana, eucalyptus, second-season paddy rice, and sugarcane; while, the 1D CNN classifier was the only one that could obtain an F-measure above 0.900 for pineapple before harvest. All results indicated the effectiveness of the solution combining the deep learning models with the incremental classification approach for early crop classification. This method is expected to provide new perspectives for early mapping of croplands in cloudy areas.