Taking advantage of multiple new remote sensing data sources, especially from Chinese satellites, the CropWatch system has expanded the scope of its international analyses through the development of new indicators and an upgraded operational methodology. The approach adopts a hierarchical system covering four spatial levels of detail: global, regional, national (thirty-one key countries including China) and “sub-countries” (for the nine largest countries). The thirty-one countries encompass more that 80% of both production and exports of maize, rice, soybean and wheat. The methodology resorts to climatic and remote sensing indicators at different scales. The global patterns of crop environmental growing conditions are first analyzed with indicators for rainfall, temperature, photosynthetically active radiation (PAR) as well as potential biomass. At the regional scale, the indicators pay more attention to crops and include Vegetation Health Index (VHI), Vegetation Condition Index (VCI), Cropped Arable Land Fraction (CALF) as well as Cropping Intensity (CI). Together, they characterize crop situation, farming intensity and stress. CropWatch carries out detailed crop condition analyses at the national scale with a comprehensive array of variables and indicators. The Normalized Difference Vegetation Index (NDVI), cropped areas and crop conditions are integrated to derive food production estimates. For the nine largest countries, CropWatch zooms into the sub-national units to acquire detailed information on crop condition and production by including new indicators (e.g., Crop type proportion). Based on trend analysis, CropWatch also issues crop production supply outlooks, covering both long-term variations and short-term dynamic changes in key food exporters and importers. The hierarchical approach adopted by CropWatch is the basis of the analyses of climatic and crop conditions assessments published in the quarterly “CropWatch bulletin” which provides accurate and timely information essential to food producers, traders and consumers.

Reconstructing the missing data for cloud/shadow-covered optical satellite images has great significance for enhancing the data availability and multi-temporal analysis. In this study, we proposed a deep-learning-based method for cloud/shadow-covered missing data reconstruction for time-series Landsat images. Central to this method is the combined use of autoencoder, long-short-term memory (AE-LSTM)-based similar pixel clustering and for backward LSTM-based time-series prediction. First, manually delineated cloud/shadow-covered masks were overlaid onto multi-temporal satellite images to produce pixel-wise time-series data with masking values. Second, these pixel-wise time series were clustered by an AE-LSTM-based unsupervised method into multiple clusters, for searching similar pixels. Third, for each cluster of target images, a for-backward-LSTM-based model was established to restore missing values in time series data. Finally, reconstructed data were merged with cloud-free (image) regions to produce cloud-free time-series images. The proposed method was applied onto three datasets of multi-temporal Landsat-8 OLI images to restore cloud/shadow-covered images. The reconstruction results, showing an improvement of greater than 10% in normalized mean-square error compared to the state-of-the-art methods, demonstrated the effectiveness of the proposed method in time-series reconstruction for satellite images.

Accurate precipitation data at high spatiotemporal resolution are critical for land and water management at the basin scale. We proposed a downscaling framework for Tropical Rainfall Measuring Mission (TRMM) precipitation products through integrating Google Earth Engine (GEE) and Google Colaboratory (Colab). Three machine learning methods, including Gradient Boosting Regressor (GBR), Support Vector Regressor (SVR), and Artificial Neural Network (ANN) were compared in the framework. Three vegetation indices (Normalized Difference Vegetation Index, NDVI; Enhanced Vegetation Index, EVI; Leaf Area Index, LAI), topography, and geolocation are selected as geospatial predictors to perform the downscaling. This framework can automatically optimize the models’ parameters, estimate features’ importance, and downscale the TRMM product to 1 km. The spatial downscaling of TRMM from 25 km to 1 km was achieved by using the relationships between annual precipitations and annually-averaged vegetation index. The monthly precipitation maps derived from the annual downscaled precipitation by disaggregation. According to validation in the Great Mekong upstream region, the ANN yielded the best performance when simulating the annual TRMM precipitation. The most sensitive vegetation index for downscaling TRMM was LAI, followed by EVI. Compared with existing downscaling methods, the proposed framework for downscaling TRMM can be performed online for any given region using a wide range of machine learning tools and environmental variables to generate a precipitation product with high spatiotemporal resolution.

The net primary productivity (NPP) and aboveground biomass mapping of crops based on remote sensing technology are not only conducive to understanding the growth and development of crops but can also be used to monitor timely agricultural information, thereby providing effective decision making for agricultural production management. To solve the saturation problem of the NDVI in the aboveground biomass mapping of crops, the original CASA model was improved using narrow-band red-edge information, which is sensitive to vegetation chlorophyll variation, and the fraction of photosynthetically active radiation (FPAR), NPP, and aboveground biomass of winter wheat and maize were mapped in the main growing seasons. Moreover, in this study, we deeply analyzed the seasonal change trends of crops’ biophysical parameters in terms of the NDVI, FPAR, actual light use efficiency (LUE), and their influence on aboveground biomass. Finally, to analyze the uncertainty of the aboveground biomass mapping of crops, we further discussed the inversion differences of FPAR with different vegetation indices. The results demonstrated that the inversion accuracies of the FPAR of the red-edge normalized vegetation index (${\mathrm{NDVI}}_{\mathrm{red}-\mathrm{edge}}$) and red-edge simple ratio vegetation index (${\mathrm{SR}}_{\mathrm{red}-\mathrm{edge}}$) were higher than those of the original CASA model. Compared with the reference data, the accuracy of aboveground biomass estimated by the improved CASA model was 0.73 and 0.70, respectively, which was 0.21 and 0.13 higher than that of the original CASA model. In addition, the analysis of the FPAR inversions of different vegetation indices showed that the inversion accuracies of the red-edge vegetation indices ${\mathrm{NDVI}}_{\mathrm{red}-\mathrm{edge}}$ and ${\mathrm{SR}}_{\mathrm{red}-\mathrm{edge}}$ were higher than those of the other vegetation indices, which confirmed that the vegetation indices involving red-edge information can more effectively retrieve FPAR and aboveground biomass of crops.

In semi-arid pasture areas, drought may directly influence livestock production, cause economic losses, and accelerate the processes of desertification along with destructive human activities (i.e., overgrazing). The aim of this article is to analyze the disadvantages of several drought indices derived from remote sensing data and develop a new vegetation drought index (VDI) for monitoring of grassland drought with high temporal frequency (dekad) and fine spatial resolution (1 km). The site-based soil moisture data from the field campaign in 2014 and the fenced biomass values at nine sites from 2000 to 2015 were adopted for validation. The results indicate that the proposed VDI would better reflect the extent, severity, and changes of drought compared with single drought indices or the vegetation health index (VHI); specifically, the VDI is more closely related to site-based soil moisture, with R human increasing to approximately 0.07 compared with the VHI; and with normalized fenced biomass (NFB) values, with average R human increasing to approximately 0.11 compared with the VHI. However, the correlations between VHI and VDI with NFB values are relatively lower in desert steppe regions. Furthermore, regional drought-affected data (RDA) are used to ensure spatial consistency of the evaluation; the VDI map is in good agreement with the RDA map based on field measurements. The presented VDI shows reliable and stable drought monitoring ability, which will play an important role in the future drought monitoring of inland grassland.

Evapotranspiration (ET) is one of the components in the water cycle and the surface energy balance systems. It is fundamental information for agriculture, water resource management, and climate change research. This study presents a scheme for regional actual evapotranspiration estimation using multi-source satellite data to compute key land and meteorological variables characterizing land surface, soil, vegetation, and the atmospheric boundary layer. The algorithms are validated using ground observations from the Heihe River Basin of northwest China. Monthly data estimates at a resolution of 1 km from the proposed algorithms compared well with ground observation data, with a root mean square error (RMSE) of 0.80 mm and a mean relative error (MRE) of −7.11%. The overall deviation between the average yearly ET derived from the proposed algorithms and ground-based water balance measurements was 9.44% for a small watershed and 1% for the entire basin. This study demonstrates that both accuracy and spatial depiction of actual evapotranspiration estimation can be significantly improved by using multi-source satellite data to measure the required land surface and meteorological variables. This reduces dependence on spatial interpolation of ground-derived meteorological variables which can be problematic, especially in data-sparse regions, and allows the production of region-wide ET datasets.