No abstract

High-precision canopy chlorophyll content (CCC) inversion for marsh vegetation is of great significance for marsh protection and restoration. However, it is difficult to collect the CCC measured data for marsh vegetation that matches the pixel scale of remote sensing image. This study proposes a new method based on unmanned aerial vehicle (UAV) multispectral images to obtain multi-scale marsh vegetation CCC sample data. A random forest (RF) regression algorithm was used to evaluate the application performance of GF-1 WFV, Landsat-8 OLI, and Sentinel-2 MSI satellite remote sensing data in marsh vegetation CCC inversion. In addition, parameter optimization of the RF regression model was used to construct an optimization algorithm suitable for marsh vegetation, and the importance of input variables was quantitatively evaluated. The results showed that the UAV multispectral images assisted in the acquisition of marsh vegetation CCC sample data, as the method expanded the number of CCC samples while quantifying the CCC sample data collection accuracy (R 2 ≥0.86, RMSE≤6.98 SPAD), which improved the CCC inversion accuracy compared with traditional sampling methods. Extracting pure vegetation pixels through binary classification reduces the uncertainty of the UAV-scale CCC inversion results. Parameter optimization of the RF regression model further improves the CCC inversion accuracy at GF-1 WFV, Landsat-8 OLI, and Sentinel-2 MSI scales. Among the three satellite remote sensing data, Sentinel-2 MSI achieved the highest CCC inversion accuracy for marsh vegetation (R 2 = 0.79, RMSE = 10.96 SPAD) due to the inclusion of red-edge bands that are more sensitive to vegetation properties. Red-edge Chlorophyll Index (Clred-edge) and Green Chlorophyll Index (Clgreen) have the highest influence on the CCC inversion accuracy among input variables. Index Terms-Canopy chlorophyll content, unmanned aerial vehicle (UAV), multi-scale remote sensing data, random forest (RF) regression, scale matching.

Wetland vegetation classification using deep learning algorithm and unmanned aerial vehicle (UAV) images have attracted increased attentions. However, there exist several challenges in mapping karst wetland vegetation due to its fragmentation, intersection, and high heterogeneity of vegetation patches. This study proposed a novel approach to classify karst vegetation in Huixian National Wetland Park, the largest karst wetland in China by fusing single-class SegNet classification using the maximum probability algorithm. A new optimized post-classification algorithm was developed to eliminate the stitching traces caused by SegNet model prediction. This paper evaluated the effect of multi-class and fusion of multiple single-class SegNet models with different EPOCH values on mapping karst vegetation using UAV images. Finally, this paper carried out a comparison of classification accuracies between object-based Random Forest (RF) and fusion of single-class SegNet models. The specific conclusions of this paper include the followings: (1) fusion of four single-class SegNet models produced better classification for karst wetland vegetation than multi-class SegNet model, and achieved the highest overall accuracy of 87.34%; (2) the optimized post-classification algorithm improved classification accuracy of SegNet model by eliminating splicing traces; (3) classification performance of single-class SegNet model outperformed multi-class SegNet model, and improved classification accuracy (F1-Score) ranging from 10 to 25%; (4) Fusion of single-class SegNet models and object-based RF classifier both produced good classifications for karst wetland vegetation, and achieved over 87% overall accuracy.

No abstract

No abstract