Optical Satellite Image Time Series Analysis for Environment Applications: From Classical Methods to Deep Learning and Beyond

Molinier, Matthieu; Miettinen, Jukka; Ienco, Dino; Qiu, Shi; Zhu, Zhe

doi:10.1002/9781119882299.ch4

Cited by 6 publications

(3 citation statements)

References 153 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In scenarios lacking readily available SSL models, initiating training from scratch can be resource-intensive. Additionally, the methodology currently does not account for the multitemporality of gradual changes [85], focusing instead on bi-temporal inputs. Future efforts aim to address this gap.…”

Section: E Strengths and Limitations Of The Proposed Methodologymentioning

confidence: 99%

Forest Disturbance Detection via Self-Supervised and Transfer Learning With Sentinel-1&2 Images

Kuzu,

Antropov,

Molinier

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

In this study, we examine the potential of leveraging self-supervised learning (SSL) and transfer learning methodologies for forest disturbance mapping using Earth Observation (EO) data. Our focus is on natural disturbances caused by windthrow and snowload damages. Particularly, we investigate the potential of knowledge distillation-based contrastive learning approaches to obtain comprehensive representations of forest structure changes using Copernicus Sentinel-1 and Sentinel-2 satellite imagery. Leveraging pre-trained backbone models from knowledge distillation, we employ transfer learning based on Deep Change Vector Analysis (DCVA) to delineate forest changes. We demonstrate developed approaches on two use-cases, namely mapping windthown forest using bi-temporal Sentinel-1 and Sentinel-2 images, and mapping forest areas damaged by excessive snowload using bi-temporal Sentinel-1 images. Developed self-supervised models were compared in a benchmarking exercise. The best results were provided by pixel-level contrastive learning for Sentinel-1 based snowload damage mapping with an overall accuracy of 84% and F1 score of 0.567, and for Sentinel-2 based forest windthrow mapping with an overall accuracy of 76.5% and F1 score of 0.692. We expect that developed methodologies can be useful for mapping also other types of forest disturbances using Copernicus Sentinel images or similar EO data. Our findings underscore the potential of SSL and transfer learning for enhancing forest disturbance detection using EO.

show abstract

Section: E Strengths and Limitations Of The Proposed Methodologymentioning

confidence: 99%

Forest Disturbance Detection via Self-Supervised and Transfer Learning With Sentinel-1&2 Images

Kuzu,

Antropov,

Molinier

et al. 2024

IEEE J. Sel. Top. Appl. Earth Observations Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…A feature space of more than a few dozens to even hundreds of dimensions could be created from the electromagnetic radiation (EMR) that is recorded at different wavelengths, the texture of the spectral bands, and the intra-annual/inter-annual temporal trajectory from the time series observations, which could be further used to determine the land cover based on image classification (Gómez et al, 2016;Pouliot and Latifovic, 2016) or to estimate the biophysical/ biochemical parameters based on machine learning or regression from empirical models (Garbulsky et al, 2011;Lin et al, 2020;Verrelst et al, 2015). Recently, the deep-learning-based approaches, particularly Convolutional Neural Network (CNN), have shown better performance in land cover classification compared to the traditional machinelearning-based methods (Kussul et al, 2017;Liu et al, 2021b;Pouliot et al, 2021), and are capable of incorporating the spatial domain of the remote sensing data by automatically extracting a suitable representation of the remote sensing data through a hierarchy of spatial filters at different sizes, which avoids the feature creation and selection processes that most traditional machine learning methods require in advance for preparation of the classification predictors (Molinier et al, 2021).…”

Section: What -Change Targetmentioning

confidence: 99%

Remote Sensing of Land Change: A Multifaceted Perspective

Zhu¹,

Qiu²,

Su³

2022

Preprint

View full text Add to dashboard Cite

show abstract

“…Change detection studies have developed an increasing number of algorithms with a well established exploitation of multi-temporal earth observations. [15] In general, sequential data have been exploited with remarkable success in domains such as time series forecasting and natural language processing, by using recurrent neural network (RNN) based approaches.…”

mentioning

confidence: 99%

A Learnable Model With Calibrated Uncertainty Quantification for Estimating Canopy Height From Spaceborne Sequential Imagery

Alagialoglou

Manakos

Heurich

et al. 2022

IEEE Trans. Geosci. Remote Sensing

View full text Add to dashboard Cite

Global-scale canopy height mapping is an important tool for ecosystem monitoring and sustainable forest management. Various studies have demonstrated the ability to estimate canopy height from a single spaceborne multi-spectral image using end-to-end learning techniques. In addition to texture information of a single-shot image, our study exploits multi-temporal information of image sequences to improve estimation accuracy. We adopt a convolutional variant of a long short-term memory (LSTM) model for canopy height estimation from multi-temporal instances of Sentinel-2 products. Furthermore, we utilize deep ensembles technique for meaningful uncertainty estimation on the predictions and post-processing isotonic regression model for calibrating them. Our lightweight model (∼ 320k trainable parameters) achieves mean absolute error (MAE) of 1.29m in a European test area of 79km 2 . It outperforms state-of-the-art methods based on single-shot spaceborne images as well as costly airborne images, while providing additional confidence maps that are shown to be well calibrated. Moreover, the trained model is shown to be transferable in a different country of Europe using a fine-tuning area of as low as ∼ 2km 2 with M AE = 1.94m.

show abstract

Optical Satellite Image Time Series Analysis for Environment Applications: From Classical Methods to Deep Learning and Beyond

Cited by 6 publications

References 153 publications

Forest Disturbance Detection via Self-Supervised and Transfer Learning With Sentinel-1&2 Images

Forest Disturbance Detection via Self-Supervised and Transfer Learning With Sentinel-1&2 Images

Remote Sensing of Land Change: A Multifaceted Perspective

A Learnable Model With Calibrated Uncertainty Quantification for Estimating Canopy Height From Spaceborne Sequential Imagery

Contact Info

Product

Resources

About