A Modified KNN Method for Mapping the Leaf Area Index in Arid and Semi-Arid Areas of China

Fugen Jiang,Andrew R Smith,Guangxing Wang,Hua Sun,Hua Liu,Mykola Kutia

doi:10.3390/rs12111884

Abstract

As an important vegetation canopy parameter, the leaf area index (LAI) plays a critical role in forest growth modeling and vegetation health assessment. Estimating LAI is helpful for understanding vegetation growth and global ecological processes. Machine learning methods such as k-nearest neighbors (kNN) and random forest (RF) with remote sensing images have been widely used for mapping LAI. However, the accuracy of mapping LAI in arid and semi-arid areas using these methods is limited due to remote and large areas, the high cost of collecting field data, and the great spatial variability of the vegetation canopy. Here, a novel and modified kNN method was presented for mapping LAI in arid and semi-arid areas of China using Sentinel-2 and Landsat 8 images with field data collected in Ganzhou and Kangbao of China. The modified kNN was developed by integrating the traditional kNN estimation and RF classification. The results were compared with those from kNN and RF regression alone using three sets of input predictors: (i) spectral reflectance bands (input 1); (ii) vegetation indices (input 2); and (iii) a combination of spectral reflectance bands and vegetation indices (input 3). Our analysis showed that in Ganzhou, the red-edge bands of the Sentinel-2 image had a high correlation with LAI. Using the red-edge band-derived vegetation indices increased the accuracy of mapping LAI compared with using other spectral variables. Among the three sets of input predictors, input 3 resulted in the highest prediction accuracy. Based on the combination, the values of RMSE obtained by the traditional kNN, RF, and modified kNN were 0.526, 0.523, and 0.372, respectively, and the modified kNN significantly improved the accuracy of LAI prediction by 29.3% and 28.9% compared with the kNN and RF alone, respectively. A similar improvement was achieved for input 1 and input 2. In Kangbao, the improvement of the prediction accuracy obtained by the modified kNN was 31.4% compared with both the kNN and RF. Therefore, this study implied that the modified kNN provided the potential to improve the accuracy of mapping LAI in arid and semi-arid regions using the images.

Highlights

Monitoring vegetation conditions and ecological processes can increase our understanding of ecosystem net primary production, photosynthesis, plant health, and global climate change [1]
During the random forest (RF) tuning process, the importance ranks of spectral variables in terms of their contributions to the decrease of root mean square error (RMSE) were produced for three sets of spectral variables in Ganzhou (Figure 2a,c,e)
The results showed that using the set input 3 reduced the RMSE by 5.1%, 7.6%, and 7.2% compared with the set input 1, and by 2.4%, 5.3%, and 3.9% compared with the set input 2, based on the traditional k-nearest neighbors (kNN), RF, and modified kNN, respectively

Summary

Introduction

Monitoring vegetation conditions and ecological processes can increase our understanding of ecosystem net primary production, photosynthesis, plant health, and global climate change [1]. As one of the key biophysical parameters of plant communities, the value of the leaf area index (LAI) is an important metric that has been widely used for mapping and monitoring vegetation dynamics and health. Linear and nonlinear regression models account for the relationship between LAI and spectral variables from images, but do not consider the mechanism of the relationship and usually neglect the spatial heterogeneity of LAI. As a result, these models have low estimation accuracies [7]

Objectives

Methods

Results

Discussion

Conclusion