scholarly journals Vegetation change detection based on time series analysis by Apache Spark and RasterFrame

2021 ◽  
Vol 62 (1) ◽  
pp. 42-52
Author(s):  
Dung Mai Thi Nguyen ◽  
Thu Hoai Thi Vu ◽  
Keyword(s):  
Time Series ◽  
Large Scale ◽  
Data Science ◽  
Vegetation Change ◽  
Environmental Changes ◽  
Satellite Image ◽  
Image Data ◽  
Apache Spark ◽  
Raster Data ◽  
Average Value

Spatial big data has a large scale and complex, therefore, it cannot be collected, managed, and analyzed by traditional data analytic software shortly. These platforms in many situations are restricted to vectors data. However, the raster data generated by the sensors on the enormous number of satellites now needs to be processed in parallel on the cluster environment. The article introduces the satellite image data analyzing method using the RasterFrames library on the Apache Spark platform. The RasterFrames library examines raster data for Python, Scala, and SQL, bringing the power of Spark DataFrames to access to Earth Observation, cloud computing, and data science. In the experimental part, the NDVI and the change in the average value of NDVI in the time series are calculated to demonstrate the vegetation mantle changes in Phu Tho province. These results are the reference data source in the assessment of weather, climate, and environmental changes in the study area during that time.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 1.91% to 6.69%. <div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Apache Spark Accelerated Deep Learning Inference for Large Scale Satellite Image Analytics

2020 ◽  
Vol 13 ◽  
pp. 271-283 ◽  
Author(s):  
Dalton Lunga ◽  
Jonathan Gerrand ◽  
Lexie Yang ◽  
Christopher Layton ◽  
Robert Stewart
Keyword(s):  
Deep Learning ◽  
Large Scale ◽  
Satellite Image ◽  
Apache Spark

scholarly journals Apply Remote Sensing to Monitoring Dynamics of Built Environmental in The Core Area and The Border of Sokok City

2020 ◽  
Author(s):  
Silvia Evandi
Keyword(s):  
Environmental Changes ◽  
Confusion Matrix ◽  
Satellite Image ◽  
Early Period ◽  
Land Development ◽  
Image Data ◽  
Space Technology ◽  
Image Transformation ◽  
Test Technique ◽  
Landsat Satellite

The development of unmanned satellite space technology is increasingly willing, the emergence of medium resolution satellites with sensitivity and spectral variants such as Landsat is very effective in observing environmental changes, while the purpose of this study is to monitor the development of built-in land using image transformation techniques, estimating built-in land changes. The research method uses the NDVI image transformation technique, NDBI and Built Up Index, with Landsat satellite image data obtained from USGS. Accuracy sampling is done by purposive sampling with confusion matrix accuracy test technique. The research results were found. developed land for the period 2004 - 2010 with a percentage of 19.25%, for stages 2010 - 2018 with a percentage of 30.25%. The land development was built based on the area of ​​the highest sub-district in the Kubung area in the early period with a percentage of 7.20% then in the second period with a percentage of 32.23%. The quality of the accuracy of the results of image analysis using confusion matrix technique with an image accuracy level in a field sample of 185 with an image accuracy of 86.04%.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Extracting multilayer networks from Sentinel-2 satellite image time series

2020 ◽  
Vol 8 (S1) ◽  
pp. S26-S42 ◽  
Author(s):  
Roberto Interdonato ◽  
Raffaele Gaetano ◽  
Danny Lo Seen ◽  
Mathieu Roche ◽  
Giuseppe Scarpa
Keyword(s):  
Remote Sensing ◽  
Time Series ◽  
Satellite Image ◽  
European Space Agency ◽  
Image Data ◽  
Earth Observation ◽  
Supervised Machine Learning ◽  
Machine Learning Techniques ◽  
Case Scenario ◽  
Sentinel 2

AbstractNowadays, modern Earth Observation systems continuously generate huge amounts of data. A notable example is the Sentinel-2 Earth Observation mission, developed by the European Space Agency as part of the Copernicus Programme, which supplies images from the whole planet at high spatial resolution (up to 10 m) with unprecedented revisit time (every 5 days at the equator). In this data-rich scenario, the remote sensing community is showing a growing interest toward modern supervised machine learning techniques (e.g., deep learning) to perform information extraction, often underestimating the need for reference data that this framework implies. Conversely, few attention is being devoted to the use of network analysis techniques, which can provide a set of powerful tools for unsupervised information discovery, subject to the definition of a suitable strategy to build a network-like representation of image data. The aim of this work is to provide clues on how Satellite Image Time Series can be profitably represented using complex network models, by proposing a methodology to build a multilayer network from such data. This is the first work to explore the possibility to exploit this model in the remote sensing domain. An example of community detection over the provided network in a real-case scenario for the mapping of complex land use systems is also presented, to assess the potential of this approach.

scholarly journals Self-Supervised Pre-Training of Transformers for Satellite Image Time Series Classification

2020 ◽  
Author(s):  
Yuan Yuan ◽  
Lei Lin
Keyword(s):  
Time Series ◽  
Deep Learning ◽  
Large Scale ◽  
Temporal Structure ◽  
Satellite Image ◽  
Fine Tuning ◽  
Small Scale ◽  
Model Parameters ◽  
Learning Approaches ◽  
Wide Range

<div>Satellite image time series (SITS) classification is a major research topic in remote sensing and is relevant for a wide range of applications. Deep learning approaches have been commonly employed for SITS classification and have provided state-of-the-art performance. However, deep learning methods suffer from overfitting when labeled data is scarce. To address this problem, we propose a novel self-supervised pre-training scheme to initialize a Transformer-based network by utilizing large-scale unlabeled data. In detail, the model is asked to predict randomly contaminated observations given an entire time series of a pixel. The main idea of our proposal is to leverage the inherent temporal structure of satellite time series to learn general-purpose spectral-temporal representations related to land cover semantics. Once pre-training is completed, the pre-trained network can be further adapted to various SITS classification tasks by fine-tuning all the model parameters on small-scale task-related labeled data. In this way, the general knowledge and representations about SITS can be transferred to a label-scarce task, thereby improving the generalization performance of the model as well as reducing the risk of overfitting. Comprehensive experiments have been carried out on three benchmark datasets over large study areas. Experimental results demonstrate the effectiveness of the proposed method, leading to a classification accuracy increment up to 2.38% to 5.27%. The code and the pre-trained model will be available at https://github.com/linlei1214/SITS-BERT upon publication.</div><div><b>This work has been submitted to the IEEE for possible publication. Copyright may be transferred without notice, after which this version may no longer be accessible.</b></div>

scholarly journals Land Cover Maps Production with High Resolution Satellite Image Time Series and Convolutional Neural Networks: Adaptations and Limits for Operational Systems

2019 ◽  
Author(s):  
Andrei Stoian ◽  
Vincent Poulain ◽  
Jordi Inglada ◽  
Victor Poughon ◽  
Dawa Derksen
Keyword(s):  
Neural Networks ◽  
Time Series ◽  
High Resolution ◽  
Land Cover ◽  
Convolutional Neural Networks ◽  
Satellite Image ◽  
Image Data ◽  
Design Decision ◽  
Land Cover Maps ◽  
Sentinel 2

The Sentinel-2 satellite mission offers high resolution multispectral time series image data, enabling the production of detailed land cover maps globally. At this scale, the trade-off between processing time and result quality is a central design decision. Currently, this machine learning task is usually performed using pixelwise classification methods. The radical shift of the computer vision field away from hand engineered image features and towards more automation by representation learning comes with many promises, including higher quality results and less engineering effort. In this paper we assess fully convolutional neural networks architectures as replacements for a Random Forest classifier in an operational context for the production of high resolution land cover maps with Sentinel-2 time series at the country scale. Our contributions include a framework for working with Sentinel-2 L2A time series image data, an adaptation of the U-Net model for dealing with sparse annotation data while maintaining high resolution output, and an analysis of those results in the context of operational production of land cover maps.

Sign in / Sign up

Export Citation Format

Share Document