As the largest and highest alpine ecoregion in the world, the Qinghai–Tibetan Plateau (QTP) is extremely sensitive to climate change and has experienced extraordinary warming during the past several decades; this has greatly affected various ecosystem processes in this region such as vegetation production and phenological change. Therefore, numerous studies have investigated changes in vegetation dynamics on the QTP using the satellite-derived normalized-difference vegetation index (NDVI) time-series data provided by the Moderate-Resolution Imaging Spectroradiometer (MODIS). However, the highest spatial resolution of only 250 m for the MODIS NDVI product cannot meet the requirement of vegetation monitoring in heterogeneous topographic areas. In this study, therefore, we generated an 8-day and 30 m resolution NDVI dataset from 2000 to 2020 for the QTP through the fusion of 30 m Landsat and 250 m MODIS NDVI time-series data. This dataset, referred to as QTP-NDVI30, was reconstructed by employing all available Landsat 5/7/8 images (>100,000 scenes) and using our recently developed gap-filling and Savitzky–Golay filtering (GF-SG) method. We improved the original GF-SG approach by incorporating a module to process snow contamination when applied to the QTP. QTP-NDVI30 was carefully evaluated in both quantitative assessments and visual inspections. Compared with reference Landsat images during the growing season in 100 randomly selected subregions across the QTP, the reconstructed 30 m NDVI images have an average mean absolute error (MAE) of 0.022 and a spatial structure similarity (SSIM) above 0.094. We compared QTP-NDVI30 with upscaled cloud-free PlanetScope images in some topographic areas and observed consistent spatial variations in NDVI between them (averaged SSIM = 0.874). We further examined an application of QTP-NDVI30 to detect vegetation green-up dates (GUDs) and found that QTP-NDVI30-derived GUD data show general agreement in spatial patterns with the 250 m MODIS GUD data, but provide richer spatial details (e.g., GUD variations at the subpixel scale). QTP-NDVI30 provides an opportunity to monitor vegetation and investigate land-surface processes in the QTP region at fine spatiotemporal scales.

Spatiotemporal data fusion is a methodology to generate images with both high spatial and temporal resolution. Most spatiotemporal data fusion methods generate the fused image at a prediction date based on pairs of input images from other dates. The performance of spatiotemporal data fusion is greatly affected by the selection of the input image pair. There are two criteria for selecting the input image pair: the ``similarity'' criterion, in which the image at the base date should be as similar as possible to that at the prediction date, and the ``consistency'' criterion, in which the coarse and fine images at the base date should be consistent in terms of their radiometric characteristics and imaging geometry. Unfortunately, the ``consistency'' criterion has not been quantitatively considered by previous selection strategies. We thus develop a novel method (called ``cross-fusion'') to address the issue of the determination of the base image pair. The new method first chooses several candidate input image pairs according to the ``similarity'' criterion and then takes the ``consistency'' criterion into account by employing all of the candidate input image pairs to implement spatiotemporal data fusion between them. We applied the new method to MODIS-Landsat Normalized Difference Vegetation Index (NDVI) data fusion. The results show that the cross-fusion method performs better than four other selection strategies, with lower average absolute difference (AAD) values and higher correlation coefficients in various vegetated regions including a deciduous forest in Northeast China, an evergreen forest in South China, cropland in North China Plain, and grassland in the Tibetan Plateau. We simulated scenarios for the inconsistency between MODIS and Landsat data and found that the simulated inconsistency is successfully quantified by the new method. In addition, the cross-fusion method is less affected by cloud omission errors. The fused NDVI time-series data generated by the new method tracked various vegetation growth trajectories better than previous selection strategies. We expect that the cross-fusion method can advance practical applications of spatiotemporal data fusion technology.

Hyperspectral imaging (HSI) effectively supports land cover (LC) classification in understanding nature–human interactions. The LC classification quality depends heavily on the input features. Combining convolutional neural network (CNN) and stacked spectral feature space patch (SSFSP) has proved effective in simultaneously exploiting spatial and spectral features for accurate LC classification. SSFSP is a stack of gridded spectral feature space images (GSIs) where the spatial and intensity distributions of LCs are derived and directly learned by CNN. However, the GSI set was not fully optimized for HSI classification. In this article, we propose an improved SSFSP (ISSFSP) to tackle this problem, by integrating SSFSP with a novel feature selection (FS) method called band combination search (BCS). BCS first defines a novel metric to measure the ability of a GSI to distinguish various LCs, and then uses a coarse-to-fine strategy to efficiently identify the optimal GSI set. Furthermore, BCS provides a classifier-free method for determining the appropriate number of GSIs after trading off accuracy and efficiency. We conducted experiments using three HSI datasets, ISSFSP and five state-of-the-art FS methods, and six classification models to validate the effectiveness of ISSFSP. ISSFSP obtained consistently highest accuracy (over 98% overall accuracy, 97% average accuracy, and 97% Kappa) using fewer bands and samples, indicating that ISSFSP significantly boosts the performance of CNN while reducing the dependence on model structure and sample quality. In short, ISSFSP can automatically provide promising spectral features for CNN-based HSI classification regarding classification accuracy and model independency, showing great potential for practical applications.