Densification and forecasting of Sentinel-2 time series from multimodal SAR and Optical satellite data using deep generative models

• URL: http://arxiv.org/abs/2605.04239v1
• Date: Tue, 05 May 2026 19:27:29 GMT
• Title: Densification and forecasting of Sentinel-2 time series from multimodal SAR and Optical satellite data using deep generative models
• Abstract summary: A growing body of work has focused on temporal densification and reconstruction of satellite image time series.<n>This work proposes a probabilistic deep learning framework for the densification and forecasting of Sentinel-2 time series.<n>Unlike most existing works, we propose to focus on the uncertainty of the generated images.
• Score: 40.97723509882159
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Optical satellite image time series are extensively used in many Earth observation applications, including agriculture, climate monitoring, and land surface analysis. However, clouds and swath edges result in irregular sampling along the temporal dimension, limiting continuous monitoring. To address this issue, a growing body of work has focused on temporal densification and reconstruction of satellite image time series, with the objective of filling missing or cloud-contaminated observations within the temporal extent of the available data. While these approaches improve temporal continuity, they are inherently restricted to the reconstruction of the gaps within the observed time periods, and do not address the prediction of future observations. This work proposes a probabilistic deep learning framework for the densification and forecasting of Sentinel-2 time series by generating optical images at arbitrary past or future dates. The approach leverages multimodal satellite data by jointly exploiting Sentinel-2 optical and Sentinel-1 SAR observations. Unlike most existing works, we propose to focus on the uncertainty of the generated images. Experimental results demonstrate effective densification and forecasting, on sparse and temporally misaligned time series.

Related papers

• From Observations to States: Latent Time Series Forecasting [65.98504021691666]
  We propose Latent Time Series Forecasting (LatentTSF), a novel paradigm that shifts TSF from observation regression to latent state prediction.<n>Specifically, LatentTSF employs an AutoEncoder to project observations at each time step into a higher-dimensional latent state space.<n>Our proposed latent objectives implicitly maximize mutual information between predicted latent states and ground-truth states and observations.
  arXiv  Detail & Related papers  (2026-01-30T20:39:44Z)
• Generating Fine-Grained Causality in Climate Time Series Data for Forecasting and Anomaly Detection [67.40407388422514]
  We design a conceptual fine-grained causal model named TBN Granger Causality. Second, we propose an end-to-end deep generative model called TacSas, which discovers TBN Granger Causality in a generative manner. We test TacSas on climate benchmark ERA5 for climate forecasting and the extreme weather benchmark of NOAA for extreme weather alerts.
  arXiv  Detail & Related papers  (2024-08-08T06:47:21Z)
• Prediction of Sentinel-2 multi-band imagery with attention BiLSTM for continuous earth surface monitoring [0.0]
  This study proposes a framework based on an attention Bidirectional Long Short-Term Memory (BiLSTM) network for predicting multiband images. Our model can forecast target images on user-defined dates, including future dates and periods characterized by persistent cloud cover.
  arXiv  Detail & Related papers  (2024-06-30T21:07:11Z)
• Cloud gap-filling with deep learning for improved grassland monitoring [2.9272689981427407]
  We propose an innovative deep learning method that integrates cloud-free optical (Sentinel-2) observations and weather-independent (Sentinel-1) radar data.<n>Our approach employs a hybrid architecture combining CNNs and Recurrent Neural Networks (RNNs) to generate continuous NDVI time series.<n>We demonstrate the significance of observation continuity by assessing the impact of the generated NDVI time series on the downstream task of mowing event detection.
  arXiv  Detail & Related papers  (2024-03-14T16:41:26Z)
• VN-Net: Vision-Numerical Fusion Graph Convolutional Network for Sparse Spatio-Temporal Meteorological Forecasting [12.737085738169164]
  VN-Net is the first attempt to introduce GCN method to utilize multi-modal data for better handling sparse-temporal meteorological forecasting. VN-Net outperforms state-of-the-art by a significant margin on mean absolute error (MAE) and root mean square error (RMSE) for temperature, relative humidity, and forecasting.
  arXiv  Detail & Related papers  (2024-01-26T12:41:57Z)
• Graph Spatiotemporal Process for Multivariate Time Series Anomaly Detection with Missing Values [67.76168547245237]
  We introduce a novel framework called GST-Pro, which utilizes a graphtemporal process and anomaly scorer to detect anomalies. Our experimental results show that the GST-Pro method can effectively detect anomalies in time series data and outperforms state-of-the-art methods.
  arXiv  Detail & Related papers  (2024-01-11T10:10:16Z)
• TempSAL -- Uncovering Temporal Information for Deep Saliency Prediction [64.63645677568384]
  We introduce a novel saliency prediction model that learns to output saliency maps in sequential time intervals. Our approach locally modulates the saliency predictions by combining the learned temporal maps. Our code will be publicly available on GitHub.
  arXiv  Detail & Related papers  (2023-01-05T22:10:16Z)
• Meteorological Satellite Images Prediction Based on Deep Multi-scales Extrapolation Fusion [5.125401106179782]
  It is important to make accurate predictions for meteorological satellite images, especially the nowcasting prediction up to 2 hours ahead. Here we present a deep multiscales fusion method, to address the challenge of the nowcasting prediction. Experiments based on the FY-4A meteorological satellite data show that the proposed method can generate realistic prediction images.
  arXiv  Detail & Related papers  (2022-09-19T16:00:17Z)
• SatMAE: Pre-training Transformers for Temporal and Multi-Spectral Satellite Imagery [74.82821342249039]
  We present SatMAE, a pre-training framework for temporal or multi-spectral satellite imagery based on Masked Autoencoder (MAE) To leverage temporal information, we include a temporal embedding along with independently masking image patches across time.
  arXiv  Detail & Related papers  (2022-07-17T01:35:29Z)
• Predicting Landsat Reflectance with Deep Generative Fusion [2.867517731896504]
  Public satellite missions are commonly bound to a trade-off between spatial and temporal resolution. This hinders their potential to assist vegetation monitoring or humanitarian actions. We probe the potential of deep generative models to produce high-resolution optical imagery by fusing products with different spatial and temporal characteristics.
  arXiv  Detail & Related papers  (2020-11-09T21:06:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.