Global Fractional Vegetation Cover Estimation Algorithm for VIIRS Reflectance Data Based on Machine Learning Methods

Duanyang Liu,Mu Xia,Zhiqiang Xiao,Xiangqin Wei,Yunjun Yao,Yuwei Li,Kun Jia,Linqing Yang,Shunlin Liang

doi:10.3390/rs10101648

Abstract

Fractional vegetation cover (FVC) is an essential input parameter for many environmental and ecological models. Recently, several global FVC products have been generated using remote sensing data. The Global LAnd Surface Satellite (GLASS) FVC product, which is generated from Moderate Resolution Imaging Spectroradiometer (MODIS) data, has attained acceptable performance. However, the original MODIS operation design lifespan has been exceeded. The Visible Infrared Imaging Radiometer Suite (VIIRS) onboard the Suomi National Polar-Orbiting Partnership (S-NPP) satellite was designed to be the MODIS successor. Therefore, developing an FVC estimation algorithm for VIIRS data is important for maintaining continuous FVC estimates in case of MODIS failure. In this study, a global FVC estimation algorithm for VIIRS surface reflectance data was proposed based on machine learning methods, which investigated the performances of back propagating neural networks (BPNNs), general regression networks (GRNNs), multivariate adaptive regression splines (MARS), and Gaussian process regression (GPR). The training samples were extracted from the GLASS FVC product and corresponding reconstructed VIIRS surface reflectance in 2013 over the global sampling locations. The VIIRS reflectances of red and near infrared (NIR) bands were the input variables for these machine learning methods. The theoretical performances and independent validation results indicated that the four machine learning methods could achieve similar and reliable FVC estimates. Regarding the FVC estimation accuracy, the GPR method achieved the best performance (R2 = 0.9019, RMSE = 0.0887). The MARS method had the obvious advantage of computational efficiency. Furthermore, the FVC estimates achieved good spatial and temporal continuities. Therefore, the proposed FVC estimation algorithm for VIIRS data can potentially generate reliable global FVC data for related applications.

Highlights

Fractional vegetation cover (FVC), which is defined as the fraction of green vegetation seen from the nadir [1,2,3], is an important biophysical parameter for many environmental and ecological models
Current global or regional FVC products are mainly derived from remote sensing data, such as the Polarization and Directionality of the Earth’s Reflectance (POLDER), Medium Resolution Imaging Spectrometer (MERIS), Spinning-Enhanced Visible and Infrared Imager (SEVIRI), Advanced Very High Resolution Radiometer (AVHRR), SPOT/VEGETATION and Moderate Resolution Imaging Spectroradiometer (MODIS) data [4,5,6,7]
The ground-test indicates that the radiometric performances of nadir Horizontal Sptial Resolution (HSR) and Noise Equivalent Temperature Difference (NEdT) between MODIS and Visible Infrared Imaging Radiometer Suite (VIIRS) sensor are different when they are normalized to the same spatial scale and radiance level [8]

Summary

Introduction

Fractional vegetation cover (FVC), which is defined as the fraction of green vegetation seen from the nadir [1,2,3], is an important biophysical parameter for many environmental and ecological models. The ground-test indicates that the radiometric performances of nadir Horizontal Sptial Resolution (HSR) and Noise Equivalent Temperature Difference (NEdT) between MODIS and VIIRS sensor are different when they are normalized to the same spatial scale and radiance level [8]. Since these changes and differences, the land surface parameter estimation algorithms or related methods for MODIS data should be reconsidered for VIIRS data. Several land surface parameter estimation algorithms were developed for VIIRS data, such as land surface albedo, leaf area index (LAI) and fraction of absorbed photosynthetically active radiation (FAPAR), to continue generating the corresponding datasets in case of MODIS failure [14,15]. Developing a global FVC estimation algorithm for VIIRS data to succeed the FVC estimation by MODIS data is significant and the main goal of this study

Objectives

Findings

Discussion

Conclusion