Application of Convolutional Neural Network on Lei Bamboo Above-Ground-Biomass (AGB) Estimation Using Worldview-2

Di’en Zhu,Fangjie Mao,Zihao Huang,Luofan Dong,Shaobai He,Junlong Zheng,Meng Zhang,Ning Han,Huaqiang Du,Hua Liu,Xuejian Li

doi:10.3390/rs12060958

Di’en Zhu, Fangjie Mao + Show 9 more

Open Access

https://doi.org/10.3390/rs12060958

Copy DOI

Abstract

Above-ground biomass (AGB) directly relates to the productivity of forests. Precisely, AGB mapping for regional forests based on very high resolution (VHR) imagery is widely needed for evaluation of productivity. However, the diversity of variables and algorithms and the difficulties inherent in high resolution optical imagery make it complex. In this paper, we explored the potentials of the state-of-art algorithm convolutional neural networks (CNNs), which are widely used for its high-level representation, but rarely applied for AGB estimation. Four experiments were carried out to compare the performance of CNNs and other state-of-art Machine Learning (ML) algorithms: (1) performance of CNN using bands, (2) performance of Random Forest (RF), support vector regression (SVR), artificial neural network (ANN) on bands, and vegetation indices (VIs). (3) Performance of RF, SVR, and ANN on gray-level co-occurrence matrices (GLCM), and exploratory spatial data analysis (ESDA), and (4) performance of RF, SVR, and ANN based on all combined data and ESDA+VIs. CNNs reached satisfactory results (with R2 = 0.943) even with limited input variables (i.e., only bands). In comparison, RF and SVR with elaborately designed data obtained slightly better accuracy than CNN. For examples, RF based on GLCM textures reached an R2 of 0.979 and RF based on all combined data reached a close R2 of 0.974. However, the results of ANN were much worse (with the best R2 of 0.885).

Highlights

The above ground biomass (AGB) of forests is related to the productivity of forests, carbon cycle, and habitation in terrestrial ecosystems [1,2]
The experiments were designed as 5 parts: (1) classification map is produced using Random Forest (RF), (2) convolutional neural networks (CNNs) was used to estimate AGB with bands as inputs, (3) RF, support vector regression (SVR), and artificial neural network (ANN) are individually applied on the widely applied variables, and (4) according to the performances of all these methods, several relatively better methods were selected for mapping AGB with land-use cover map
AGB Mapping After comparison among all the variables that we took into consideration, gray-level co-occurrence matrices (GLCM) textures were chosen for AGB mapping and the window sizes of each algorithm were selected based on Table 6

Summary

Introduction

The above ground biomass (AGB) of forests is related to the productivity of forests, carbon cycle, and habitation in terrestrial ecosystems [1,2]. Medium and low spatial resolution spectral images, such as Landsat TM (Thematic mapper), Landsat OLI (Operational Land Imager) imageryand the Moderate Resolution Imaging Spectroradiometer (MODIS) products, have been investigated for decades since spectrums indirectly relate to plant growth status [2,7,15,16] Scholars used these data to reveal climate change and environmental shifts at impressive scales [17,18]. Drawbacks inherent in CNNs and VHSR images constrain the use of CNNs for biomass estimation: spatial heterogeneity and, especially, the lack of sufficient training samples [41]. The assumptions are: (1) spatial information highly relates to AGB in VHSR images and (2) CNNs could, to some extent, Remote Sens. The radiance image was atmospherically corrected and transformed into canopy reflectance using the Fast Line-of-Sight Atmospheric Analysis of Spectral Hypercubes (FLAASH) algorithm

Variables Extraction

Machine Learning Algorithms

Experiment Design

Bands and VIs

Combined Features

AGB Estimation Using Different Variables

Experimental Settings

Findings

Conclusions