Estimation of global evapotranspiration based on deep neural network combined with AMSR2 and MODIS data

doi:10.11873/j.issn.1004-0323.2022.6.958.

Remote Sensing Technology and Application

Download:

PDF (1299KB)
Export: BibTeX | EndNote (RIS)

Abstract The surface evapotranspiration (ET) is a key component of the water and energy cycles and has critical value for applications. This study is aimed to develop a reliable and efficient deep neural network (DNN) model for all-weather global daily ET estimation with high spatial resolution, using remote sensing MODIS datasets, microwave AMSR2 brightness temperature products and digital elevation DEM data as input. The study used 148 site observations over six representative land cover types from FLUXNET and AmeriFlux to train and validate DNN models. The results showed that the DNN model can effectively established the relationship between satellite (MODIS, AMSR2) data and ET, and the mean absolute error (MAE) of ET estimation results for the six land cover types ranged from 0.16 to 0.63 mm/day, and the root mean square error (RMSE) ranged from 0.27 to 0.89 mm/day, and the coefficient of determination (R2) of all land types were > 0.7, except for bare land, where the R2 was 0.37. By comparing the ET estimation in this study with the ET products of MOD16A2 and GLEAM, the results demonstrated that the spatial distribution characteristics of the three ET products were similar and the ET values were very close with global average daily ET of 0~4 mm/day over 2020.

Key words: Evapotranspiration MODIS AMSR2 Deep neural network

Received: 29 October 2021 Published: 25 May 2022

ZTFLH:

TP79

	Service
	E-mail this article
	Add to my bookshelf
	Add to citation manager
	E-mail Alert
	RSS
	Articles by authors
	LIAO Kuo
	PENG Zhong
	JIANG Ya-Zhen
	DANG Hui-Fei

Cite this article:

. Estimation of global evapotranspiration based on deep neural network combined with AMSR2 and MODIS data. Remote Sensing Technology and Application, 0, (): 0-0.

URL:

http://www.rsta.ac.cn/EN/10.11873/j.issn.1004-0323.2022.6.958. OR http://www.rsta.ac.cn/EN/Y0/V/I/0

[1]	. [J]. Remote Sensing Technology and Application, 1991, 6(1): 48 -53 .
[2]	FAN Yan-guo, ZHANG Lei, SUN Yuan-fang, WU Teng-teng, ZHU Hao. The Research of Land Use Classification Monitoring of Yellow River Delta Region Using RS[J]. Remote Sensing Technology and Application, 2010, 25(1): 45 -49 .
[3]	LI Li, ZHANG Zhi-qiang, AN Pei-jun. Development Trend of Remote Sensors Based on Co-word Analysis[J]. Remote Sensing Technology and Application, 2010, 25(3): 442 -450 .
[4]	Hou Shanshan,Lei Liping,Guan Xianhua. A General Introduction to Greenhouse Gases Observing Satellite (GOSAT) and Its Products[J]. Remote Sensing Technology and Application, 2013, 28(2): 269 -275 .
[5]	XIU Li-na, LIU Xiang-nan. Current Status and Future Direction of the Study on Artificial Neural Network Classification Processing in Remote Sensing[J]. Remote Sensing Technology and Application, 2003, 18(5): 339 -345 .
[6]	BAI Yan-Fen, MA Hai-Zhou, ZHANG Bao-Cheng, LIANG Ji, LI Zhe, LI Hong-Yi, HAO Xiao-Hua, WANG Jian. Eco-environmental Vulnerability Analysis around Qinghai Lake Based on RS and GIS Technology[J]. Remote Sensing Technology and Application, 2009, 24(5): 635 -641 .
[7]	HU Tan-gao, ZHANG Jin-shui, PAN Yao-zhong,ZHU Wen-quan. Image Retrieval Based on Limited Hue Value on Information Entropy[J]. Remote Sensing Technology and Application, 2007, 22(4): 543 -548 .
[8]	HOU Hui-shu,YANG Hong-ye . A General Introduction to MODIS Snow Productsand Its Researching Application[J]. Remote Sensing Technology and Application, 2009, 24(2): 252 -256 .
[9]	. [J]. Remote Sensing Technology and Application, 2013, 28(3): 353 -354 .
[10]	Pan Yingqi,Jia Li. Retrieval of Land Surface Temperature Using a Classified Split-window Algorithm from MTSAT-1R Data[J]. Remote Sensing Technology and Application, 2015, 30(4): 626 -637 .

Viewed

Full text

Abstract

Cited

Shared

Discussed