Filling GRACE data gap using an innovative transformer-based deep learning approach

doi:10.1016/j.rse.2024.114465

2024-12-01

PRE

Longhao Wang

Yongqiang Zhang *

DOI：10.1016/j.rse.2024.114465

原文链接

原文求助

摘要

En 中文

The terrestrial water storage anomaly (TWSA), derived from the Gravity Recovery and Climate Experiment (GRACE) and its successor, the GRACE Follow-on (GRACE-FO) satellite, presents a remarkable opportunity for extreme weather detection and the enhancement of environmental protection. However, the practical utility of GRACE data is challenged by an 11-month data gap and several months of missing data. To address this limitation, we have developed an innovative transformer-based deep learning model for data gap-filling. This model incorporates a self-attention mechanism using causal convolution, allowing the neural network to capture the local context of GRACE time series data. It takes into account various factors such as temperature (T), precipitation (P), and evapotranspiration (ET). We trained the model using a global dataset of 10,000 time series pixels and applied it to fill all the time gaps. The validation results demonstrate its robustness, with an average root mean square error (RMSE) of 6.18 cm and Nash-Sutcliffe efficiency (NSE) of 0.906. Notably, the Transformer- based method outperforms other state-of-the-art approaches in arid regions. The incorporation of T, P, and ET has further enhanced the accuracy of gap filling, with an average RMSE decrease of 7.5 %. This study has produced a reliable gap-filling product that addresses 11-month data gaps and 24 isolated gaps, ensuring the continuity of GRACE data for various scholarly applications. Moreover, our Transformer approach holds important potential for surpassing traditional methods in predicting and filling gaps in remote sensing data and gridded observations.

Keyword:

Gap filling

GRACE

Terrestrial water storage anomaly

Transformer

期刊

Remote Sensing of Environment

IF:

11.4

论文数:

1.1W

被引数:

9.4W

机构

chinese academy of sciences

学者数:

56.7W

论文数: 45.0W

被引数: 704

引用论文

Reconstructing GRACE-type time-variable gravity from the Swarm satellites

SCIENTIFIC REPORTS

IF3.9

2021-01-13

OAAI

Richter, H. Maja P.; Lueck, Christina; Klos, Anna; Sideris, Michael G.; Rangelova, Elena; Kusche, Juergen

Coupled estimation of 500 m and 8-day resolution global evapotranspiration and gross primary production in 2002-2017 2002-2017年500 m和8天分辨率的全球蒸散量和总初级生产的耦合估算

REMOTE SENSING OF ENVIRONMENT

IF11.4

2019-03-01

525

PREAI

Zhang, Yongqiang; Kong, Dongdong; Gan, Rong; Chiew, Francis H. S.; McVicar, Tim R.; Zhang, Qiang; Yang, Yuting

Evaluation of 18 satellite- and model-based soil moisture products using in situ measurements from 826 sensors

HYDROLOGY AND EARTH SYSTEM SCIENCES

IF5.8

2021-01-04

222

OAAI

Beck, Hylke E.; Pan, Ming; Miralles, Diego G.; Reichle, Rolf H.; Dorigo, Wouter A.; Hahn, Sebastian; Sheffield, Justin; Karthikeyan, Lanka; Balsamo, Gianpaolo; Parinussa, Robert M.; van Dijk, Albert I. J. M.; Du, Jinyang; Kimball, John S.; Vergopolan, Noemi; Wood, Eric F.

ON THE PRESSURE DEPENDENCE OF REACTION RATES

Canadian Journal of Chemistry

IF0

1966-09-15

OAAI

H. S. Golinkin; W. G. Laidlaw; J. B. Hyne

Endophytic Bacillus cereus ERBP—Clitoria ternatea interactions: Potentials for the enhancement of gaseous formaldehyde removal

Environmental and Experimental Botany

IF0

2016-06-01

PREAI

Gholamreza Khaksar; Chairat Treesubsuntorn; Paitip Thiravetyan