# Detecting Urban Changes with Recurrent Neural Networks from Multitemporal Sentinel-2 Data

arXiv: https://arxiv.org/abs/1910.07778 · HTML: https://mlsanity.com/paper/1910.07778/

## Key facts

- Cited by 20 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 17 Oct 2019.

## Built on by (most cited first, 20 of 20)

- [RS-Mamba for Large Remote Sensing Image Dense Prediction](https://mlsanity.com/paper/2404.02668/) (2024)
- [Self-Supervised Material and Texture Representation Learning for Remote Sensing Tasks](https://mlsanity.com/paper/2112.01715/) (2021)
- [HANet: A Hierarchical Attention Network for Change Detection With Bitemporal Very-High-Resolution Remote Sensing Images](https://mlsanity.com/paper/2404.09178/) (2024)
- [FCCDN: Feature Constraint Network for VHR Image Change Detection](https://mlsanity.com/paper/2105.10860/) (2021)
- [Super-resolution-based Change Detection Network with Stacked Attention Module for Images with Different Resolutions](https://mlsanity.com/paper/2103.00188/) (2021)
- [Exchanging Dual Encoder-Decoder: A New Strategy for Change Detection with Semantic Guidance and Spatial Localization](https://mlsanity.com/paper/2311.11302/) (2023)
- [ELGC-Net: Efficient Local-Global Context Aggregation for Remote Sensing Change Detection](https://mlsanity.com/paper/2403.17909/) (2024)
- [Continuous Cross-resolution Remote Sensing Image Change Detection](https://mlsanity.com/paper/2305.14722/) (2023)
- [Continuous Urban Change Detection from Satellite Image Time Series with Temporal Feature Refinement and Multi-Task Integration](https://mlsanity.com/paper/2406.17458/) (2024)
- [ViewDelta: Scaling Scene Change Detection through Text-Conditioning](https://mlsanity.com/paper/2412.07612/) (2024)
- [SAM Guided Semantic and Motion Changed Region Mining for Remote Sensing Change Captioning](https://mlsanity.com/paper/2511.21420/) (2025)
- [Using Graph Neural Networks to Predict Local Culture](https://mlsanity.com/paper/2402.17905/) (2024)
- [Multi-temporal Calving Front Segmentation](https://mlsanity.com/paper/2512.11560/) (2025)
- [Deep learning approaches to Earth Observation change detection](https://mlsanity.com/paper/2107.06132/) (2021)
- [ML Updates for OpenStreetMap: Analysis of Research Gaps and Future Directions](https://mlsanity.com/paper/2407.03365/) (2024)
- [SChanger: Change Detection from a Semantic Change and Spatial Consistency Perspective](https://mlsanity.com/paper/2503.20734/) (2025)
- [Fusion of Satellite Images and Weather Data with Transformer Networks for Downy Mildew Disease Detection](https://mlsanity.com/paper/2209.02797/) (2022)
- [Combining recurrent and residual learning for deforestation monitoring using multitemporal SAR images](https://mlsanity.com/paper/2310.05697/) (2023)
- [UDHF2-Net: Uncertainty-diffusion-model-based High-Frequency TransFormer Network for Remotely Sensed Imagery Interpretation](https://mlsanity.com/paper/2406.16129/) (2024)
- [GRAD-Former: Gated Robust Attention-based Differential Transformer for Change Detection](https://mlsanity.com/paper/2603.01161/) (2026)

## Abstract (arXiv)

beginabstract The advent of multitemporal high resolution data, like the Copernicus Sentinel-2, has enhanced significantly the potential of monitoring the earth's surface and environmental dynamics. In this paper, we present a novel deep learning framework for urban change detection which combines state-of-the-art fully convolutional networks (similar to U-Net) for feature representation and powerful recurrent networks (such as LSTMs) for temporal modeling. We report our results on the recently publicly available bi-temporal Onera Satellite Change Detection (OSCD) Sentinel-2 dataset, enhancing the temporal information with additional images of the same region on different dates. Moreover, we evaluate the performance of the recurrent networks as well as the use of the additional dates on the unseen test-set using an ensemble cross-validation strategy. All the developed models during the validation phase have scored an overall accuracy of more than 95%, while the use of LSTMs and further temporal information, boost the F1 rate of the change class by an additional 1.5%.