Abstract
Fractional vegetation cover (FVC) is a critical land surface parameter, and several large-scale FVC products have been generated based on remote sensing data. Among these existing products, the global land surface satellite (GLASS) FVC product, derived from moderate resolution imaging spectroradiometer (MODIS) 500 m reflectance data (MOD09A1), has achieved complete spatial-temporal continuity and satisfying accuracy. To further improve the spatial resolution of GLASS FVC product, this study developed a novel FVC estimation algorithm for MODIS 250 m reflectance data based on a recurrent neural network with the long short-term memory unit (RNN-LSTM). The RNN-LSTM was established using sequence training samples derived from the MODIS 250 m reflectance and GLASS FVC products, which were conducted over three vegetation types in mid-West China. Additionally, two machine learning methods, including the back propagation neural network (BPNN) and multivariate adaptive regression splines (MARS), were used to compare with the proposed method. The evaluation results showed that RNN-LSTM derived FVC had reliable spatial-temporal continuity and good consistency with the GLASS FVC product. Furthermore, the smooth temporal profiles of the RNN-LSTM FVC estimation indicated that the proposed method was capable of capturing the temporal characteristics of vegetation growth and reducing the uncertainties from the atmosphere and radiation. Finally, an independent validation case in the Heihe area indicated that the RNN-LSTM algorithm achieved the best accuracy (R2 = 0.8081, rmse = 0.0951) compared with the BPNN (R2 = 0.7320, rmse = 0.1127) and MARS (R2 = 0.7361, rmse = 0.1117). This study provides a new approach by showing the potential of the RNN-LSTM method for land surface parameter estimation and related research.
Highlights
A S THE essential component of the terrestrial ecosystem, vegetation plays a crucial role in energy exchange and biogeochemical and hydrological cycling processes [1]–[3]
The adopted cloud detection method was capable of addressing the contaminated values in moderate resolution imaging spectroradiometer (MODIS) reflectance data. This operation effectively improved the quality of MODIS reflectance data, which is crucial for the accuracy of Fractional vegetation cover (FVC) estimation
This study proposed a MODIS 250 m FVC estimation algorithm based on the recurrent neural network (RNN)-long short-term memory (LSTM) method, which could improve the spatial resolution of the global land surface satellite (GLASS) FVC product
Summary
A S THE essential component of the terrestrial ecosystem, vegetation plays a crucial role in energy exchange and biogeochemical and hydrological cycling processes [1]–[3]. Fractional vegetation cover (FVC), defined as the fraction of green vegetation as seen from nadir [4], is usually used to describe the growth state of land surface vegetation [5]. FVC plays an essential role in monitoring vegetation growth and driving the earth system models [6]–[9]. FVC data contributed to the improvement of surface air temperature simulation in climate models [10], and reduced the prediction error of Budyko’s hydrological model over medium spatial scales [11]. Large-scaled FVC estimation with high accuracy is essential to successfully model these land surface processes [9], [13], [14]
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
More From: IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Disclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.