RESUMO
Grassland is the vegetation type with the widest coverage on the Qinghai-Tibet Plateau. Under the influence of multiple factors, such as global climate change and human activities, grassland is undergoing temporal and spatially different disturbances and changes, and they have a significant impact on the grassland ecosystem of the Qinghai-Tibet Plateau. Therefore, timely and dynamic monitoring of grassland disturbances and distinguishing the reasons for the changes are essential for ecological understanding and management. The purpose of this research is to propose a knowledge-based strategy to realize grassland dynamic distribution mapping and analysis of grassland disturbance changes in the region that are suitable for the Qinghai-Tibet Plateau. The purpose of this study is to propose an analysis algorithm that uses first annual mapping and then establishes temporal disturbance rules, which is applicable to the integrated exploration of disturbance changes in highland-type grasslands. The characteristic indexes of greenness and disturbance indices in the growing period were constructed and integrated with deep neural network learning to dynamically map the grassland for many years. The overall accuracy of grassland mapping was 94.11% and that of Kappa was 0.845. The results show that the area of grassland increased by 11.18% from 2001 to 2017. Then, the grassland disturbance change analysis method is proposed in monitoring the grassland distribution range, and it is found that the area of grassland with significant disturbance change accounts for 10.86% of the total area of the Qinghai-Tibet Plateau, and the disturbance changes are specifically divided into seven types. Among them, the type of degradation after disturbance mainly occurs in Tibet, whereas the main types of vegetation greenness increase in Qinghai and Gansu. At the same time, the study finds that climate change, altitude, and human grazing activities are the main factors affecting grassland disturbance changes in the Qinghai-Tibet Plateau, and there are spatial differences.
RESUMO
Spatiotemporal explicit information on paddy rice distribution is essential for ensuring food security and sustainable environmental management. Paddy rice mapping algorithm through the Combined Consideration of Vegetation phenology and Surface water variations (CCVS) has been efficiently applied based on the 8day composites time series datasets. However, the great challenge for phenology-based algorithms introduced by unpromising data availability in middle/high spatial resolution imagery, such as frequent cloud cover and coarse temporal resolution, remained unsolved. This study addressed this challenge through developing an automatic and Adaptive paddy Rice Mapping Method (ARMM) based on the cloud frequency and spectral separability. The proposed ARMM method was tested on the Landsat 8 Operational Land Imager (OLI) image (path/row 118/028) in the Songnen Plain in Northeast China in 2015. First, the whole study region was automatically and adaptively subdivided into undisturbed and disturbed regions through a per-pixel strategy based on Landsat image data availability during key phenological stage. Second, image objects were extracted from approximately cloud-free images in disturbed and undisturbed regions, respectively. Third, phenological metrics and other feature images from individual or multiple images were developed. Finally, a flexible automatic paddy rice mapping strategy was implemented. For undisturbed region, an object-oriented CCVS method was utilized to take the full advantages of phenology-based method. For disturbed region, Random Forest (RF) classifier was exploited using training data from CCVS-derived results in undisturbed region and feature images adaptively selected with full considerations of spectral separability and the spatiotemporal coverage. The ARMM method was verified by 473 reference sites, with an overall accuracy of 95.77% and kappa index of 0.9107. This study provided an efficient strategy to accommodate the challenges of phenology-based approaches through transferring knowledge in parts of a satellite scene with finer time series to targets (other parts) with deficit data availability.
