Satellite Image Sequences Research Articles

The evolution of agricultural areas in a Saharan region by satellite imagery (landsat, sentinel) case of the Oued Righ region, Algeria

During this study, our objective was to systematically identify predominant spatiotemporal trends related to the evolution of agricultural perimeters in a Saharan region, specifically the oases of Oued Righ in Algeria. To achieve this, we used satellite imagery data. The chronological sequence of satellite images covering the Oued Righ region, situated in the Northeastern Sahara of Algeria, was meticulously established. Spatial remote sensing proved to be an essential tool, providing us with up-to-date and geo-referenced data regarding vegetation. We used a time series of Landsat (8, 4-5, 7) and Sentinel 2 images covering Oued Righ from 1984 to 2024, using bands 4, 3, 2, and 5, 4, 3 infrared. These images offered precise insights into the actual vegetation development in the study area, eliminating any guesswork. Our analysis relied on vegetation indices, notably the NDVI (Normalized Difference Vegetation Index), allowing us to objectively and scientifically monitor the evolution of this perimeter.

Large-scale unsupervised spatio-temporal semantic analysis of vast regions from satellite images sequences

Temporal sequences of satellite images constitute a highly valuable and abundant resource for analyzing regions of interest. However, the automatic acquisition of knowledge on a large scale is a challenging task due to different factors such as the lack of precise labeled data, the definition and variability of the terrain entities, or the inherent complexity of the images and their fusion. In this context, we present a fully unsupervised and general methodology to conduct spatio-temporal taxonomies of large regions from sequences of satellite images. Our approach relies on a combination of deep embeddings and time series clustering to capture the semantic properties of the ground and its evolution over time, providing a comprehensive understanding of the region of interest. The proposed method is enhanced by a novel procedure specifically devised to refine the embedding and exploit the underlying spatio-temporal patterns. We use this methodology to conduct an in-depth analysis of a 220 km2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$^2$$\\end{document} region in northern Spain in different settings. The results provide a broad and intuitive perspective of the land where large areas are connected in a compact and well-structured manner, mainly based on climatic, phytological, and hydrological factors.

TinyPredNet: A Lightweight Framework for Satellite Image Sequence Prediction

Satellite image sequence prediction aims to precisely infer future satellite image frames with historical observations, which is a significant and challenging dense prediction task. Though existing deep learning models deliver promising performance for satellite image sequence prediction, the methods suffer from quite expensive training costs, especially in training time and GPU memory demand, due to the inefficiently modeling for temporal variations. This issue seriously limits the lightweight application in satellites such as space-borne forecast models. In this article, we propose a lightweight prediction framework TinyPredNet for satellite image sequence prediction, in which a spatial encoder and decoder model the intra-frame appearance features and a temporal translator captures inter-frame motion patterns. To efficiently model the temporal evolution of satellite image sequences, we carefully design a multi-scale temporal-cascaded structure and a channel attention-gated structure in the temporal translator. Comprehensive experiments are conducted on FengYun-4A (FY-4A) satellite dataset, which show that the proposed framework achieves very competitive performance with much lower computation cost compared to state-of-the-art methods. In addition, corresponding interpretability experiments are conducted to show how our designed structures work. We believe the proposed method can serve as a solid lightweight baseline for satellite image sequence prediction.

Enhancing Satellite Image Sequences through Multi-Scale Optical Flow-Intermediate Feature Joint Network

Satellite time-series data contain information in three dimensions—spatial, spectral, and temporal—and are widely used for monitoring, simulating, and evaluating Earth activities. However, some time-phase images in the satellite time series data are missing due to satellite sensor malfunction or adverse atmospheric conditions, which prevents the effective use of the data. Therefore, we need to complement the satellite time series data with sequence image interpolation. Linear interpolation methods and deep learning methods that have been applied to sequence image interpolation lead to large errors between the interpolation results and the real images due to the lack of accurate estimation of pixel positions and the capture of changes in objects. Inspired by video frame interpolation, we combine optical flow estimation and deep learning and propose a method named Multi-Scale Optical Flow-Intermediate Feature Joint Network. This method learns pixel occlusion and detailed compensation information for each channel and jointly refines optical flow and intermediate features at different scales through an end-to-end network together. In addition, we set a spectral loss function to optimize the network’s learning of the spectral features of satellite images. We have created a time-series dataset using Landsat-8 satellite data and Sentinel-2 satellite data and then conducted experiments on this dataset. Through visual and quantitative evaluation of the experimental results, we discovered that the interpolation results of our method retain better spectral and spatial consistency with the real images, and that the results of our method on the test dataset have a 7.54% lower Root Mean Square Error than other approaches.

TS-Track: Trajectory Self-Adjusted Ship Tracking for GEO Satellite Image Sequences via Multi-Level Supervision Paradigm

TS-Track: Trajectory Self-Adjusted Ship Tracking for GEO Satellite Image Sequences via Multi-Level Supervision Paradigm

Ocean Color Image Sequences Reveal Diurnal Changes in Water Column Stability Driven by Air–Sea Interactions

The southward propagation of cold-air frontal boundaries into the Gulf of Mexico region initiates a cascade of coupled air–sea processes that manifests along the coastlines as an apparent brightness anomaly in the ocean color signals. Our hypothesis is that the color anomaly is largely due to the turbulent resuspension of sedimentary particles. Initially, there is significant wind-driven ocean turbulence as the frontal boundary passes, followed by the potential for sustained convective instability due to significant heat losses from the ocean surface. These cold front events occur during boreal autumn, winter, and into early spring, and the latter episodes occur in the context of the seasonally recurring thermal stratification of shelf waters. Here, we show that as stratification reasserts thermal stability in the waning days of a cold front episode, daily to hourly ocean color patterns are temporally coherent with the air–sea heat flux changes and the resulting impact on water column stability. Concomitant results from a nested, data-assimilative, and two-way coupled ocean-atmosphere numerical modeling system provides both corroboration and insight into how surface air–sea fluxes and in-water turbulent mixing manifest as hourly changes in apparent surface water turbidity due to the potential excitation and settling of reflective particles. A simple model of particle mixing and settling driven by the simulated turbulence mimics patterns seen in the satellite image sequences. This study offers a preview of potential application areas that may emerge following the launch of a dedicated ocean color geostationary sensor.

Factors Influencing Four Decades of Forest Change in Guizhou Province, China

Globally, the loss of forest vegetation is a significant concern due to the crucial roles that forests play in the Earth’s system, including the provision of ecosystem services, participation in biogeochemical cycles, and support for human well-being. Forests are especially critical in mountains environments, where deforestation can lead to accelerated biodiversity loss, soil erosion, flooding, and reduced agricultural productivity, as well as increased poverty rates. In response to these problems, China has implemented a series of ecological restoration programs aimed at restoring forests. However, there is a lack of knowledge as to whether the forest cover is increasing or decreasing, as well as the relative roles played by natural and human factors in forest change. Here, we aim to address these issues by analyzing the pattern and process of the forest changes in Guizhou province, a typical mountainous karst area with a fragile environment in southwestern China, between 1980 and 2018, and evaluating the extent to which these forest changes were influenced by natural and anthropogenic driving forces. Using a temporal sequence of satellite images and a Markov model, we found that the forest cover increased by 468 km2, and that over 33% of the cropland in Guizhou province was converted into forest between 1980 and 2018, with the most significant increases in the forest cover occurring in Qiandongnan. Through correlation analyses and generalized linear model (GLM) regression, we demonstrate that management factors exerted a more significant positive impact on the forest cover than climate change. While the mean annual precipitation and temperature were mostly stable during the period studied, the effects of population and gross domestic product (GDP) on the forest changes weakened, and the influence of land-use change markedly increased. These findings provide valuable information for resource managers engaging in forest protection, deforestation prevention, and ecological restoration in similar regions.

Exploiting Spatial–Temporal Dynamics for Satellite Image Sequence Prediction

Satellite image sequence prediction is a challenging and significant task. Existing deep learning methods for the task make predictions mainly based on low-level pixel-wise features, which fail to model the sophisticated spatial-temporal features of satellite image sequences and deliver unsatisfactory performance. In this paper, we present a Hierarchical Spatial-Temporal network (HSTnet) for satellite image sequence prediction. With a carefully designed hierarchical feature extraction mechanism, HSTnet can learn effective spatial-temporal features from both pixel level and patch level. In addition, to better capture patch-level spatial-temporal dynamics, a dual-branch Transformer is proposed to model patch-level spatial and temporal features, respectively. Comprehensive experiments on the FY-4A satellite dataset demonstrate the superiority and effectiveness of our proposed method HSTnet over state-of-the-art approaches.

Learning Spatial–Temporal Consistency for Satellite Image Sequence Prediction

Learning Spatial–Temporal Consistency for Satellite Image Sequence Prediction

Comparison of Optical Flow Derivation Techniques for Retrieving Tropospheric Winds from Satellite Image Sequences

Abstract This study introduces a validation technique for quantitative comparison of algorithms that retrieve winds from passive detection of cloud- and water vapor–drift motions, also known as atmospheric motion vectors (AMVs). The technique leverages airborne wind-profiling lidar data collected in tandem with 1-min refresh-rate geostationary satellite imagery. AMVs derived with different approaches are used with accompanying numerical weather prediction model data to estimate the full profiles of lidar-sampled winds, which enables ranking of feature tracking, quality control, and height-assignment accuracy and encourages mesoscale, multilayer, multiband wind retrieval solutions. The technique is used to compare the performance of two brightness motion, or “optical flow,” retrieval algorithms used within AMVs, 1) patch matching (PM; used within operational AMVs) and 2) an advanced variational optical flow (VOF) method enabled for most atmospheric motions by new-generation imagers. The VOF AMVs produce more accurate wind retrievals than the PM method within the benchmark in all imager bands explored. It is further shown that image regions with low texture and multilayer-cloud scenes in visible and infrared bands are tracked significantly better with the VOF approach, implying VOF produces representative AMVs where PM typically breaks down. It is also demonstrated that VOF AMVs have reduced accuracy where the brightness texture does not advect with the mean wind (e.g., gravity waves), where the image temporal noise exceeds the natural variability, and when the height assignment is poor. Finally, it is found that VOF AMVs have improved performance when using fine-temporal refresh-rate imagery, such as 1- versus 10-min data.

ANALYSIS OF DYNAMICAL CHANGES FROM LARGE SET OF REMOTE SENSING IMAGES

Basic elements of changes on the multi-temporal satellite image and their basic sets of dynamic objects are formulated and defined, for which the main characteristics define the dynamic object as an area of motion. Such dependents of objects are inherited not only between objects and their dynamic groups. In such a case, the concept of dynamic objects in a multi-temporal sequence of satellite images has been developed based on the formalization of processes occurring on a change stream. A specific methodology has been developed to select a dynamic object from a dynamic group based on the analysis of the changing characteristics of the object’s environment. It means that objects in a group have similar changing for separate characteristics. Such objects are included in specified ranges and are combined into dynamic groups. Characteristics dynamic group is characterized by changing every object of it. The monitoring is performed for such a group. The technique includes six stages: image acquisition and pre-processing, image scene segmentation and selection of regions, image scene analysis for segmented areas, control of compliance with the conditions for behavioral characteristics, and classification of the behavioral line of objects in the region. As a result, it is possible to describe the properties of the group’s behavior and objects in the group as separate characteristics. The control of fulfillment of conditions for the behavioral characteristic is carried out to control the object as a dynamic group element. Thus, monitoring is carried out as a control for the motion of many objects rather than images.

Object Tracking Based on Satellite Videos: A Literature Review

Video satellites have recently become an attractive method of Earth observation, providing consecutive images of the Earth’s surface for continuous monitoring of specific events. The development of on-board optical and communication systems has enabled the various applications of satellite image sequences. However, satellite video-based target tracking is a challenging research topic in remote sensing due to its relatively low spatial and temporal resolution. Thus, this survey systematically investigates current satellite video-based tracking approaches and benchmark datasets, focusing on five typical tracking applications: traffic target tracking, ship tracking, typhoon tracking, fire tracking, and ice motion tracking. The essential aspects of each tracking target are summarized, such as the tracking architecture, the fundamental characteristics, primary motivations, and contributions. Furthermore, popular visual tracking benchmarks and their respective properties are discussed. Finally, a revised multi-level dataset based on WPAFB videos is generated and quantitatively evaluated for future development in the satellite video-based tracking area. In addition, 54.3% of the tracklets with lower Difficulty Score (DS) are selected and renamed as the Easy group, while 27.2% and 18.5% of the tracklets are grouped into the Medium-DS group and the Hard-DS group, respectively.

Objective Detection of a Tropical Cyclone’s Center Using Satellite Image Sequences in the Northwest Pacific

A tropical cyclone (TC) is one of the most destructive natural disasters that can cause heavy loss of life and property. Determining a TC’s center is crucial to TC forecasting. It is difficult to locate the center of a TC during its formation stage and dissipation period. To address this problem, a novel objective algorithm called cloud motion wind (CMW) was proposed for detecting a TC’s center using infrared (IR) image sequences from a geostationary meteorology satellite. First, the optical flow model with weighted median filtering was utilized to build a cloud motion wind field. Second, the density matrix method was used to calculate the center of the TC. FY-2E (Fengyun-2E geostationary meteorological satellites) IR images of three TCs in the Northwest Pacific, Halong, Rammasun and Haiyan were analyzed using the proposed algorithm. The present algorithm estimated the track with an averaged track error of around 41 km. Experimental results compared with the observed track that was given by the China Meteorological Administration (CMA) show that the proposed method provided accurate estimates of the cyclone center. The present algorithm has the potential to be employed to assist forecasters to detect the track of imminent TC.

MSTCGAN: Multiscale Time Conditional Generative Adversarial Network for Long-Term Satellite Image Sequence Prediction

Satellite image sequence prediction is a crucial and challenging task. Previous studies leverage optical flow methods or existing deep learning methods on spatial-temporal sequence models for the task. However, they suffer from either oversimplified model assumptions or blurry predictions and sequential error accumulation issue, for a long-term forecast requirement. In this paper, we propose a novel Multi-Scale Time Conditional Generative Adversarial Network (MSTCGAN). To address the sequential error accumulation issue, MSTCGAN adopts a parallel prediction framework to produce the future image sequences by a one-hot time condition input. In addition, a powerful multi-scale generator is designed with the multi-head axial attention, which helps to carefully preserve the fine-grained details for appearance consistency. Moreover, we develop a temporal discriminator to address the blurry issue and maintain the motion consistency in prediction. Extensive experiments have been conducted on FengYun-4A satellite data set, and the results demonstrate the effectiveness and superiority of the proposed method over state-of-the-art approaches.

COCO-Net: A Dual-Supervised Network With Unified ROI-Loss for Low-Resolution Ship Detection From Optical Satellite Image Sequences

Low-resolution ship detection from optical satellite image sequences is critical in high-orbit remote sensing satellite applications. However, it is still a difficult problem due to the following challenges: 1) the size of the ship is tiny in the low-resolution image; 2) the ship target is dim and the contrast with the background is low; 3) the interference of cloud and fog covering is complex and changeable. For these reasons, the targets are easily lost during the detection. In fact, the Clearer the Objects against to the background, the more Confident the Observers can detect it. In light of these considerations, we propose a COCO-Net to detect the small dynamic objects on low-resolution images in this paper. First, the multi-frame images are associated by introducing motion information as an effective compensation for small object features. Second, an integrated dual-supervised network that processes single-level tasks hierarchically is presented to adaptively enhance the input data quality of object detection without being limited by diverse scene disturbances. Third, a unified ROI-loss scheme that modulates the loss function of the first component by introducing ROI-masks from the second component is utilized to make the first component also work for object detection. In addition, we construct a new dataset for the small dynamic object detection based on the GaoFen-4 satellite imagery. Comprehensive experiments on a self-assembled dataset from the GaoFen-4 satellite show the superior performance of the proposed method compared to state-of-the-art object detectors.

Application of Deep Learning Architectures for Satellite Image Time Series Prediction: A Review

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.

Total Surface Current Vector and Shear From a Sequence of Satellite Images: Effect of Waves in Opposite Directions

AbstractThe total surface current velocity (TSCV)—the horizontal vector quantity that advects seawater—is an essential climate variable, with few observations available today. The TSCV can be derived from the phase speed of surface gravity waves, and the estimates of the phase speeds of different wavelengths could give a measure of the vertical shear. Here, we combine 10‐m resolution Level‐1C of the Sentinel‐2 Multispectral Instrument, acquired with time lags up to 1 s, and numerical simulation of these images. Retrieving the near‐surface shear requires a specific attention to waves in opposing directions when estimating a single‐phase speed from the phase difference in an image pair. Opposing waves lead to errors in phase speeds that are most frequent for shorter wavelengths. We propose an alternative method using a least squares fit of the current speed and amplitudes of waves in opposing directions to the observed complex amplitudes of a sequence of three images. When applied to Sentinel‐2, this method generally provides more noisy estimate of the current. A byproduct of this analysis is the “opposition spectrum” which is a key quantity in the sources of microseisms and microbaroms. For future possible sensors, the retrieval of TSCV and shear can benefit from increased time lags, resolution, and exposure time of acquisition. These findings should allow new investigations of near‐surface ocean processes including regions of freshwater influence or internal waves, using existing satellite missions such as Sentinel‐2, and provide a basis for the design of future optical instruments.

Improving the consistency of multi-temporal land cover mapping of Laguna lake watershed using light gradient boosting machine (LightGBM) approach, change detection analysis, and Markov chain

The enhanced temporal capability of today's satellite sensors gives us large volumes of data to be processed, analysed, and visualized. Most of the conventional remote sensing software and land cover classification approaches, however, are only designed for single-date observations. To fully utilize the amount of data we receive and to improve land use/land cover mapping (LULC), technological advancements in machine learning, open-source processing, and GPU-accelerated hardware should be utilized. In this paper, a methodology for classification of temporal sequence of Sentinel-2 images was developed using open-source Python libraries. Light Gradient Boosting Machine, a machine learning algorithm that uses tree-based learning, was used to classify different land cover types based on a temporal sequence of Sentinel-2 satellite images. Although the use of powerful machine learning algorithm resulted to more accurate land cover maps, temporal inconsistencies are still pervasive when dealing with time series outputs. To remove these temporal inconsistencies that resulted from misclassifications, temporal land cover filter based on transition probability matrix was applied on the time series land cover maps to modify the illogical land cover transitions. Accuracy assessment revealed good performance of the approach, which produced higher overall accuracy.

Prediction of atmospheric motion vectors around typhoons using generative adversarial network

In this study, atmospheric motion vectors (AMVs) were derived from the satellite images predicted using a generative adversarial network (GAN) and a deep multi-scale frame prediction algorithm. The GAN was trained and tested with a sequence of the satellite images of a COMS satellite infrared-window channel under the 68 tropical cyclones. The inputs of the consecutive satellite images with 15-min interval were then processed using the trained GAN model to generate satellite images in the next time steps. To further enhance the model’s predictability, particle image velocimetry based on the theory of cross-correlation schemes was employed to the GAN-generated satellite image sequence and AMVs were produced. The GAN-derived AMVs were validated with the wind fields based on the numerical weather prediction (NWP) and radiosonde observations. The comparisons showed that the GAN-derived AMVs depicted the structure of atmospheric circulations with a certain level of accuracy. Through comparison with the radiosonde observations, the root-mean-square error and the wind speed bias of the GAN-derived AMVs were comparable to, and even smaller than those of the NWP-derived wind fields. The current approach may enhance the accuracy in predicting short-term wind velocity fields, which in turn may provide more realistic inputs in storm surge modeling.

Detection and Tracking Method of Maritime Moving Targets Based on Geosynchronous Orbit Satellite Optical Images

The GF-4 geosynchronous orbit satellite can observe a large area for a long time, but the unique characteristics of its optical remote sensing image restrict the detection of maritime targets. This paper proposes a maritime target detection and tracking method for the GF-4 satellite image sequence based on the differences in information between frames in the image sequence. First, a preprocessing method is proposed for the unique characteristics of the image. Then, the ViBe (Visual Background Extractor) algorithm is used to extract the targets in the image sequence. After detection, the DCF-CSR (discriminative correlation filters with channel and spatial reliability) is used as a tracker to track and correlate the detected target to complete the task of predicting and monitoring the targets’ movements. Finally, through the comparative analysis of experiments with several classic methods, the feasibility and effectiveness of this method are verified.