This paper developed an approach, the window-based validation set for support vector data description (WVS-SVDD), to determine optimal parameters for support vector data description (SVDD) model to map specific land cover by integrating training and window-based validation sets. Compared to the conventional approach where the validation set included target and outlier pixels selected visually and randomly, the validation set derived from WVS-SVDD constructed a tightened hypersphere because of the compact constraint by the outlier pixels which were located neighboring to the target class in the spectral feature space. The overall accuracies for wheat and bare land achieved were as high as 89.25% and 83.65%, respectively. However, target class was underestimated because the validation set covers only a small fraction of the heterogeneous spectra of the target class. The different window sizes were then tested to acquire more wheat pixels for validation set. The results showed that classification accuracy increased with the increasing window size and the overall accuracies were higher than 88% at all window size scales. Moreover, WVS-SVDD showed much less sensitivity to the untrained classes than the multi-class support vector machine (SVM) method. Therefore, the developed method showed its merits using the optimal parameters, tradeoff coefficient (C) and kernel width (s), in mapping homogeneous specific land cover. Full article

Remote sensing technology plays an important role in monitoring rapid changes of the Earth's surface. However, sensors that can simultaneously provide satellite images with both high temporal and spatial resolution haven’t been designed yet. This paper proposes an improved spatial and temporal adaptive reflectance fusion model (STARFM) with the help of an Unmixing-based method (USTARFM) to generate the high spatial and temporal data needed for the study of heterogeneous areas. The results showed that the USTARFM had higher accuracy than STARFM methods in two aspects of analysis: individual bands and of heterogeneity analysis. Taking the predicted NIR band as an example, the correlation coefficients (r) for the USTARFM, STARFM and unmixing methods were 0.96, 0.95, 0.90, respectively (p-value < 0.001); Root Mean Square Error (RMSE) values were 0.0245, 0.0300, 0.0401, respectively; and ERGAS values were 0.5416, 0.6507, 0.8737, respectively. The USTARM showed consistently higher performance than STARM when the degree of heterogeneity ranged from 2 to 10, highlighting that the use of this method provides the capacity to solve the data fusion problems faced when using STARFM. Additionally, the USTARFM method could help researchers achieve better performance than STARFM at a smaller window size from its heterogeneous land surface quantitative representation. Full article

In recent decades, the monitoring of vegetation dynamics has become crucial because of its important role in terrestrial ecosystems. In this study, a satellite-derived normalized difference vegetation index (NDVI) was combined with climate factors to explore the spatiotemporal patterns of vegetation change during the growing season, as well as their driving forces in China from 2001 to 2012. Our results showed that the growing season NDVI increased continuously during 2001–2012, with a linear trend of 1.4%/10 years (p < 0.01). The NDVI in north China mainly exhibited an increasing spatial trend, but this trend was generally decreasing in south China. The vegetation dynamics were mainly at a moderate intensity level in both the increasing and decreasing areas. The significantly increasing trend in the NDVI for arid and semi-arid areas of northwest China was attributed mainly to an increasing trend in the NDVI during the spring, whereas that for the north and northeast of China was due to an increasing trend in the NDVI during the summer and autumn. Different vegetation types exhibited great variation in their trends, where the grass-forb community had the highest linear trend of 2%/10 years (p < 0.05), followed by meadow, and needle-leaf forest with the lowest increasing trend, i.e., a linear trend of 0.3%/10 years. Our results also suggested that the cumulative precipitation during the growing season had a dominant effect on the vegetation dynamics compared with temperature for all six vegetation types. In addition, the response of different vegetation types to climate variability exhibited considerable differences. In terms of anthropological activity, our statistical analyses showed that there was a strong correlation between the cumulative afforestation area and NDVI during the study period, especially in a pilot region for ecological restoration, thereby suggesting the important role of ecological restoration programs in ecological recovery throughout China in the last decade. Full article

Vegetation phenology is considered a sensitive indicator of terrestrial ecosystem response to global climate change. We used a satellite-derived normalized difference vegetation index to investigate the spatiotemporal changes in the green-up date over the Three-Rivers Headwater Region (TRHR) from 1999 to 2013 and characterized their driving forces using climatic data sets. A significant advancement trend was observed throughout the entire study area from 1999 to 2013 with a linear tendency of 6.3 days/decade (p < 0.01); the largest advancement trend was over the Yellow River source region (8.6 days/decade, p < 0.01). Spatially, the green-up date increased from the southeast to the northwest, and the green-up date of 87.4% of pixels fell between the 130th and 150th Julian day. Additionally, about 91.5% of the study area experienced advancement in the green-up date, of which 80.2%, mainly distributed in areas of vegetation coverage increase, experienced a significant advance. Moreover, it was found that the green-up date and its trend were significantly correlated with altitude. Statistical analyses showed that a 1-°C increase in spring temperature would induce an advancement in the green-up date of 4.2 days. We suggest that the advancement of the green-up date in the TRHR might be attributable principally to warmer and wetter springs. Full article

Remote sensing provides timely, economic, and objective data over a large area and has become the main data source for land cover/use area estimation. However, the classification results cannot be directly used to calculate the area of a given land cover/use type because of classification errors. The main purpose of this study is to explore the performance and stability of several model-assisted estimators in various overall accuracies of classification and sampling fractions. In this study, the confusion matrix calibration direct estimator, confusion matrix calibration inverse estimator, ratio estimator, and simple regression estimator were implemented to infer the areas of several land cover classes using simple random sampling without replacement in two experiments: a case study using simulation data based on RapidEye images and that using actual RapidEye and Huan Jing (HJ)-1A images. In addition, the simple estimator using a simple random sample without replacement was regarded as a basic estimator. The comparison results suggested that the confusion matrix calibration estimators, ratio estimator, and simple regression estimator could provide more accurate and stable estimates than the simple random sampling estimator. In addition, high-quality classification data played a positive role in the estimation, and the confusion matrix inverse estimators were more sensitive to the classification accuracy. In the simulated experiment, the average deviation of a confusion matrix calibration inverse estimator decreased by about 0.195 with the increasing overall accuracy of classification; otherwise, the variation of the other three model-assisted estimators was 0.102. Moreover, the simple regression estimator was slightly superior to the confusion matrix calibration estimators and required fewer sample units under acceptable classification accuracy levels of 70%–90%. Full article