Using An Attention-Based LSTM Encoder-Decoder Network for Near Real-Time Disturbance Detection

Accurate prediction of future observations based on past data is the key to near real-time disturbance detection using satellite image time series (SITS). To overcome the limitations of existing methods, we present an attention-based long-short-term memory (LSTM) encoder-decoder model in which the h...

Full description

Saved in:
Bibliographic Details
Published in:IEEE journal of selected topics in applied earth observations and remote sensing Vol. 13; pp. 1819 - 1832
Main Authors: Yuan, Yuan, Lin, Lei, Huo, Lian-Zhi, Kong, Yun-Long, Zhou, Zeng-Guang, Wu, Bin, Jia, Yan
Format: Journal Article
Language:English
Published: Piscataway IEEE 2020
The Institute of Electrical and Electronics Engineers, Inc. (IEEE)
Subjects:
Accuracy
Attention mechanism
Coders
Detection
Early warning systems
encoder–decoder
False alarms
Forecasting
Hidden Markov models
Image detection
Long short-term memory
long-short-term memory (LSTM)
Mapping
Methods
Model accuracy
near real-time disturbance detection
Predictions
Predictive models
Real time
Real-time systems
Remote sensing
satellite image time series (SITS)
Satellite imagery
Satellites
Spaceborne remote sensing
Spectroradiometers
Time series
Time series analysis
Warning systems
ISSN:1939-1404, 2151-1535
Online Access:Get full text
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary:Accurate prediction of future observations based on past data is the key to near real-time disturbance detection using satellite image time series (SITS). To overcome the limitations of existing methods, we present an attention-based long-short-term memory (LSTM) encoder-decoder model in which the historical time series of a pixel is encoded with a bidirectional LSTM encoder while the future time series is produced by another LSTM decoder. An attention mechanism is integrated into the encoder-decoder model to align the input time series with the output time series and to dynamically choose the most relevant contextual information while forecasting. Based on the proposed model, we develop a framework for near real-time disturbance detection and verify its effectiveness in the case of burned area mapping. The prediction accuracy of the proposed model is evaluated using moderate resolution imaging spectroradiometer (MODIS) time series and compared with state-of-the-art models. Experimental results show that our model achieves the best results in terms of lower prediction error and higher model fitness. We also evaluate the disturbance detection ability of the proposed framework. The proposed approach improves the detection rate of disturbances while suppressing false alarms, and increases the temporal accuracy. We suggest that the proposed methods provide new tools for enhancing current early warning systems in real time.
Bibliography:ObjectType-Article-1
SourceType-Scholarly Journals-1
ObjectType-Feature-2
content type line 14
ISSN:1939-1404
2151-1535
DOI:10.1109/JSTARS.2020.2988324