Abstract

Satellite image time series (SITS) is a sequence of satellite images that record a given area at several consecutive times. The aim of such sequences is to use not only spatial information but also the temporal dimension of the data, which is used for multiple real-world applications, such as classification, segmentation, anomaly detection, and prediction. Several traditional machine learning algorithms have been developed and successfully applied to time series for predictions. However, these methods have limitations in some situations, thus deep learning (DL) techniques have been introduced to achieve the best performance. Reviews of machine learning and DL methods for time series prediction problems have been conducted in previous studies. However, to the best of our knowledge, none of these surveys have addressed the specific case of works using DL techniques and satellite images as datasets for predictions. Therefore, this paper concentrates on the DL applications for SITS prediction, giving an overview of the main elements used to design and evaluate the predictive models, namely the architectures, data, optimization functions, and evaluation metrics. The reviewed DL-based models are divided into three categories, namely recurrent neural network-based models, hybrid models, and feed-forward-based models (convolutional neural networks and multi-layer perceptron). The main characteristics of satellite images and the major existing applications in the field of SITS prediction are also presented in this article. These applications include weather forecasting, precipitation nowcasting, spatio-temporal analysis, and missing data reconstruction. Finally, current limitations and proposed workable solutions related to the use of DL for SITS prediction are also highlighted.

Highlights

  • Numerous satellites orbit the Earth and provide users with a large quantity of data such as optical and radar images

  • We reviewed recent publications that involve the use of deep learning (DL) algorithms for satellite image time series prediction

  • The designed models are optimized by the stochastic gradient descent (SGD), adaptive moment (Adam), and RMSProp optimizers during the learning step

Read more

Summary

Introduction

Numerous satellites orbit the Earth and provide users with a large quantity of data such as optical and radar images. When there is missing or corrupt data in the sequence, input variables are multiple and the relationship between observations are complex and non-linear; these classical techniques do not produce satisfactory results To overcome these issues, machine learning (ML) algorithms, which are part of artificial intelligence (AI), have been proposed. This paper presents, in a single document, the main elements necessary to design and evaluate DL models for SITS prediction (data, methods, and parameters), and provides an excellent starting point for researchers interested in the field. It describes the major applications of SITS prediction using DL methods, including weather forecasting, precipitation nowcasting, spatio-temporal analysis, and missing data reconstruction.

Survey Methodology
Generalities
Main DL Architectures
Description of Satellite Images
Description of the SITS Prediction Problem
Weather Forecasting
Precipitation Nowcasting
Spatio-Temporal Analysis
Missing Data Reconstruction
Deep Learning-Based Methods for SITS Prediction
RNN-Based Models
Convolutional LSTM
Hybrid Models
LSTM–AdaBoost
Convolutional LSTM Auto-Encoder
DeepstepFE
Optimizer
Evaluation Metrics
Computer Vision Metrics
Statistical Metrics
Processing Metrics
Limitations in the Use of DL for SITS Prediction
Limits Related to Training Dataset Availability
Preprocessing of Datasets
Architecture of DL-Networks
Complexity of SI
Generalization of DL Models
Conclusions

Talk to us

Join us for a 30 min session where you can share your feedback and ask us any queries you have

Schedule a call

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.