Mapping Forest Canopy Height over Continental China Using Multi-Source Remote Sensing Data

Xiliang Ni,Sungho Choi,Yuli Shi,Taejin Park,Xuejun Wang,Ranga Myneni,Yuke Zhou,Chunxiang Cao

doi:10.3390/rs70708436

Abstract

Spatially-detailed forest height data are useful to monitor local, regional and global carbon cycle. LiDAR remote sensing can measure three-dimensional forest features but generating spatially-contiguous forest height maps at a large scale (e.g., continental and global) is problematic because existing LiDAR instruments are still data-limited and expensive. This paper proposes a new approach based on an artificial neural network (ANN) for modeling of forest canopy heights over the China continent. Our model ingests spaceborne LiDAR metrics and multiple geospatial predictors including climatic variables (temperature and precipitation), forest type, tree cover percent and land surface reflectance. The spaceborne LiDAR instrument used in the study is the Geoscience Laser Altimeter System (GLAS), which can provide within-footprint forest canopy heights. The ANN was trained with pairs between spatially discrete LiDAR metrics and full gridded geo-predictors. This generates valid conjugations to predict heights over the China continent. The ANN modeled heights were evaluated with three different reference data. First, field measured tree heights from three experiment sites were used to validate the ANN model predictions. The observed tree heights at the site-scale agreed well with the modeled forest heights (R = 0.827, and RMSE = 4.15 m). Second, spatially discrete GLAS observations and a continuous map from the interpolation of GLAS-derived tree heights were separately used to evaluate the ANN model. We obtained R of 0.725 and RMSE of 7.86 m and R of 0.759 and RMSE of 8.85 m, respectively. Further, inter-comparisons were also performed with two existing forest height maps. Our model granted a moderate agreement with the existing satellite-based forest height maps (R = 0.738, and RMSE = 7.65 m (R2 = 0.52, and RMSE = 8.99 m). Our results showed that the ANN model developed in this paper is capable of estimating forest heights over the China continent with a satisfactory accuracy. Forth coming research on our model will focus on extending the model to the estimation of woody biomass.

Highlights

Forests play a key role in the global climate system and carbon cycle
In order to solve those two problems degrading the accuracy of Geoscience Laser Altimeter System (GLAS)-based forest height maps, we proposed a new approach based on the artificial neural network (ANN)
China was generated from the feed-forward neural network (FFNN) using the gridded geospatial predictors (Figure 3a)

Summary

Introduction

Forests play a key role in the global climate system and carbon cycle. Forests store carbon in their above- and below-ground biomass [1]. As an important predictor of forest biomass and carbon stock, the vertical structure of forests has been well monitored in previous studies [2,3,4]. Light detection and ranging (LiDAR) remote sensing, is useful in the large-scale investigations of forest structural attributes, such as forest canopy height [2,5,6,7,8,9,10]. Because the GLAS data are spatially incomplete, multiple geospatial predictors were supplemented to obtain spatially-continuous forest height maps in recently-published approaches [2,3,5,13]. The GLAS data are highly sensitive to topographic features due to its large footprint size, which causes overestimations of forest height [14]. In order to solve those two problems degrading the accuracy of GLAS-based forest height maps, we proposed a new approach based on the artificial neural network (ANN)

Objectives

Methods

Results

Conclusion