Remote Sensing · 2023 · 18 citations · 57 references
Natural ResourcesForestryLandscape Change DetectionLandscape Pattern AnalysisRemote SensingLand Cover Change DetectionRemote Sensing Change DetectionVegetation Change DetectionVegetation Cover AssessmentVegetation IndicesVegetation MonitoringAlpine EcosystemsEcosystem ChangeFractional Vegetation Cover EstimationGradient Boosting TreesGrassland MonitoringSatellite-based Vegetation MonitoringVegetation Cover Change DetectionVegetation Cover Mapping
Fractional vegetation coverage (FVC) is an important indicator of ecosystem change. At present, FVC products are mainly concentrated at low and medium spatial resolution and lack high temporal and spatial resolution, which brings certain challenges to the fine monitoring of ecological environments. In this study, we evaluated the accuracy of four remote sensing inversion models for FVC based on high-spatial-resolution Sentinel-2 imagery and unmanned aerial vehicle (UAV) field-measured FVC data in 2019. Then the inversion models were optimized by constructing a multidimensional feature dataset. Finally, the Source Region of the Yellow River (SRYR) FVC product was created using the best inversion model, and the spatial-temporal variation characteristics of the FVC in the region were analyzed. The study’s findings revealed that: (1) The accuracies of the four FVC inversion models were as follows: the Gradient Boosting Decision Tree (GBDT) model (R2 = 0.967, RMSE = 0.045) > Random Forest (RF) model (R2 = 0.962, RMSE = 0.049) > Support Vector Machine (SVM) model (R2 = 0.925, RMSE = 0.072) > Pixel Dichotomy (PD) model (R2 = 0.869, RMSE = 0.097). (2) Constructing a multidimensional feature dataset to optimize the driving data can improve the accuracy of the inversion model. NDVI and elevation are important factors affecting the accuracy of machine learning inversion algorithms, and the visible blue band is the most important feature factor of the GBDT model. (3) The FVC in the SRYR gradually increased from west to east and from north to south. The change trajectories of grassland FVC from 2017 to 2022 were not significant. The areas that tend to improve were mainly distributed in the southeast (1.31%), while the areas that tend to degrade were mainly distributed in the central and northwest (1.89%). This study provides a high-spatial-resolution FVC inversion optimization scheme, which is of great significance for the fine monitoring of alpine grassland ecological environments.
57
Corinna Cortes, Vladimir Vapnik · Machine Learning · 1995 · 40.5K citations · Full text
Overview of the radiometric and biophysical performance of the MODIS vegetation indices
Alfredo Huete, Kamel Didan, Tomoaki Miura et al. · Remote Sensing of Environment · 2002 · 9.6K citations
Agriculture, Ecology, Geography +14
A soil-adjusted vegetation index (SAVI)
Alfredo Huete · Remote Sensing of Environment · 1988 · 7.7K citations
A modified soil adjusted vegetation index
Jiaguo Qi, Abdelghani Chehbouni, Alfredo Huete et al. · Remote Sensing of Environment · 1994 · 3.3K citations