Hyperspectral data has been widely used in species discrimination of plants with rich spectral information in hundreds of spectral bands, while the availability of hyperspectral data has hindered its applications in many specific cases. The successful operation of the Chinese satellite, Gaofen-5 (GF-5), provides potentially promising new hyperspectral dataset with 330 spectral bands in visible and near infrared range. Therefore, there is much demand for assessing the effectiveness and superiority of GF-5 hyperspectral data in plants species mapping, particularly mangrove species mapping, to better support the efficient mangrove management. In this study, mangrove forest in Mai Po Nature Reserve (MPNR), Hong Kong was selected as the study area. Four dominant native mangrove species were investigated in this study according to the field surveys. Two machine learning methods, Random Forests and Support Vector Machines, were employed to classify mangrove species with Landsat 8, Simulated Hyperion and GF-5 data sets. The results showed that 97 more bands of GF-5 over Hyperion brought a higher over accuracy of 87.12%, in comparison with 86.82% from Hyperion and 73.89% from Landsat 8. The higher spectral resolution of 5 nm in GF-5 was identified as making the major contribution, especially for the mapping of Aegiceras corniculatum. Therefore, GF-5 is likely to improve the classification accuracy of mangrove species mapping via enhancing spectral resolution and thus has promising potential to improve mangrove monitoring at species level to support mangrove management.

Incorporating optical and polarimetric synthetic-aperture radar (SAR) data to estimate impervious surface is useful but challenging due to their different geometric imaging mechanism and the high diversity of urban land covers. The recent development of deep convolutional networks (DCN) opens a promising opportunity by automatically extracting the deep features from both data sets. In this study, a small-patched DCN (SDCN) was designed to estimate the impervious surface from optical and SAR data. Benchmark methods, e.g., GoogLeNet, VGG16, ResNet50, and the support vector machine were employed for comparison. Two study sites in the most complex metropolitan of China, the Guangdong-Hong Kong-Macau Greater Bay Area, were selected to assess the proposed method. Experimental results indicated the effectiveness of proposed SDCN with a better accuracy outperforming other benchmark methods. Furthermore, we found that 60%–80% of training samples performed comparably with the whole training set, indicating that a large number of training samples may not be necessary in all cases, depending on the settings of some factors (e.g., number of epochs). Generally, SDCN appears more suitable than other methods in terms of combining the optical and SAR data and improved the accuracy of estimating impervious surface.

Numerous studies on environmental modeling and ecological process lay emphasis on the fundamental information of the impervious surface area (ISA). However, accurate ISA extraction from high-resolution satellite images remains challenging due to both the high diversity of land covers and shadow effects from tall buildings and trees. To address the problem, a discriminative Optical-SAR-LiDAR dictionary sparse representation classification (OSLD-SRC) method was proposed using high-resolution WorldView-2, GeoEye-1, TerraSAR-X, and airborne LiDAR data. First, it used multisource data and fuzzy samples by low-pass filtering (LPF) to solve the problem of roads and buildings misclassification; second, it learned the Optical-SAR-LiDAR dictionary for nonshadow and shadow classes, and then used discriminative sparse coding method for classification to reduce the shadow effects and improve the ISA extraction accuracy. Experimental results demonstrated the effectiveness of the proposed method.

Change detection is an important task in earth observation. In the past few years, significant progress has been made in supervised change detection research. However, change labels are extremely expensive. Semi-supervised change detection has attracted increasing attention. In semi-supervised change detection, the problem of scarcity of positive samples is magnified. Moreover, the imbalance of change types (e.g., disappearance and appearance) exacerbates the missing detection phenomenon. To address the above problems, we propose a semi-supervised change detection method: CutMix-CD, which incorporates the change-aware CutMix augmentation into the consistency framework of change detection. The semi-supervised learning framework enriches change contexts and places special emphasis on the comparative process, facilitating more robust representations of changes with improved generalization capabilities. Firstly, mixed samples are synthesized using the change-aware CutMix operation. Then, we developed a student path and a teacher path to predict the changes of original samples and mixed samples respectively. Finally, the consistency loss is conducted between the two predictions to help the model learn change information of unlabeled samples. In addition, an unsupervised feature constraint loss is proposed to further optimize the change features. Experiments on four datasets validate the effectiveness of CutMix-CD. It can effectively alleviate the overfitting problem for unbalanced types of changes, and even outperforms the fully-supervised methods for some challenging samples. The code will be released in https://github.com/SQD1/CutMixCD.

Satellites have different revisit frequencies (i.e., temporal resolutions), ranging from daily to monthly. The satellite revisit frequencies suitable for accurately monitoring the phenology of deciduous broad-leaved forests (DBF) are not well-known. To fill this knowledge gap, this study used MODIS Daily Nadir BRDF-Adjusted images to simulate EVI time series with a wide range of temporal resolutions from daily to 52 days, to investigate the impacts of satellite revisit frequency on monitoring spatial and temporal patterns of spring phenology, i.e., the start of season (SOS), of DBF in North America. Then, these EVI time series were used to extract SOS by two common phenology extraction methods (i.e., relative threshold and curvature methods). Our results reveal that 1 ) low temporal resolutions cannot accurately reconstruct real vegetation growth profile, which generally causes a false early SOS detection, 2 ) the impact of temporal resolutions is nonlinear. The accuracy of SOS detection from data with relatively high frequencies (e.g., 7 days) is only slightly lower than that from daily time series but the accuracy decreases largely with low frequencies, and 3 ) validation with ground observations from PhenoCam Network stations and an experiment using three real satellite datasets (i.e., MODIS, Landsat 8, and Sentinel-2) confirm the findings from our simulation study. This study suggests that satellites with medium temporal resolutions, such as Sentinel-2 and Landsat 8, could extract reliable phenology metrics in non-cloudy regions.