Cloud Removal from Satellite Imagery using a Lightweight Gated Attention U-Net.
4 affiliations
- 1School of Technology Management and Engineering (STME), SVKM's NMIMS Deemed to be University, Indore, MP, 453112, India.
- 2School of Computer Science Engineering & Applications, D Y Patil International University (DYPIU), Akurdi, Pune, MH, India.
- 3Symbiosis Institute of Technology, Pune, Symbiosis International (Deemed University), Pune, MH, 412115, India.
- 4School of Artificial Intelligence, Sai University, Chennai, TN, 603104, India.
Abstract
Cloud cover in optical satellite images reduces their usefulness for many applications such as land use analysis, vegetation monitoring, and disaster assessment. Traditional methods like cloud masking and image compositing often fail to recover fine spatial details, especially in heavily occluded regions. Recent deep learning approaches, mainly based on U-Net architectures, have shown good performance for cloud removal. However, many of these models struggle to focus on cloud-affected regions while also keeping the computation efficient. This work presents a lightweight Gated Attention U-Net model for satellite image cloud removal. The model is built on a Modified U-Net backbone and uses gating-based attention in the skip connections to highlight important spatial features in cloud-covered areas. Instead of proposing a new attention design, this study systematically evaluates three attention settings, namely No Attention, Light Attention, and Full Gated Attention, under the same training and assessment conditions. This allows a fair analysis of reconstruction accuracy, stability, and computational efficiency. Experiments on the Remote Sensing Image Cloud Removal (RICE1) dataset show that the attention-based configurations achieve stable reconstruction performance across three random seeds. The Full Gated Attention configuration achieves a mean Peak Signal-to-Noise Ratio (PSNR) of 34.76 ± 0.51 dB, while the Light Attention configuration provides the highest mean PSNR (35.21 ± 0.13 dB) and lowest Mean Absolute Error (MAE) (0.0167 ± 0.0004) among the attention variants. Additional assessment on the RICE2 dataset using the same Gated Attention U-Net configuration supports the robustness of the architecture across different cloud patterns and scene conditions. The attention-based configurations maintain low inference times, ranging from 0.0086 to 0.0104 seconds per image across the three-seed experiments. This makes it suitable for low-latency satellite image processing applications and deployment in resource-constrained environments. Overall, the results demonstrate that selective attention can provide a favorable balance between reconstruction quality and computational efficiency within the lightweight Modified U-Net framework.
Related
- OpsSatNet: A Lightweight Sensor-Aware Attention Network for Satellite Telemetry Anomaly Detection
- MANBO: Mamba-Based Lightweight Attention Network with Priority-Bridged Ordering for Point Cloud Processing
- RoadTopo-SAM:Topology-Aware Vectorized Road Network Extraction from High-Resolution Satellite Imagery of Open-Pit Mines
- Deep Learning on Satellite Imagery Reveals Landscape Drivers of Metabolic Syndrome
- Spatio-Temporal Analysis of Urban Expansion in Awka and its Environs, Nigeria Using Sentinel-2 Satellite Imagery and Google Earth Engine (2021 to 2026)
BibTeX
@article{mishra2026cloud,
title = {{Cloud Removal from Satellite Imagery using a Lightweight Gated Attention U-Net.}},
author = {Raj Gaurav Mishra and Anuj Kumar and Sangeeta Pant and Ketan Kotecha and Ajith Abraham},
journal = {MethodsX},
year = {2026},
month = oct,
doi = {10.1016/j.mex.2026.104229},
url = {https://europepmc.org/article/MED/42997841},
note = {CC BY-NC-ND},
}
RIS
TY - JOUR
TI - Cloud Removal from Satellite Imagery using a Lightweight Gated Attention U-Net.
AU - Raj Gaurav Mishra
AU - Anuj Kumar
AU - Sangeeta Pant
AU - Ketan Kotecha
AU - Ajith Abraham
PY - 2026
DA - 2026/10/23
JO - MethodsX
DO - 10.1016/j.mex.2026.104229
UR - https://europepmc.org/article/MED/42997841
AB - Cloud cover in optical satellite images reduces their usefulness for many applications such as land use analysis, vegetation monitoring, and disaster assessment. Traditional methods like cloud masking and image compositing often fail to recover fine spatial details, especially in heavily occluded regions. Recent deep learning approaches, mainly based on U-Net architectures, have shown good performance for cloud removal. However, many of these models struggle to focus on cloud-affected regions while also keeping the computation efficient. This work presents a lightweight Gated Attention U-Net model for satellite image cloud removal. The model is built on a Modified U-Net backbone and uses gating-based attention in the skip connections to highlight important spatial features in cloud-covered areas. Instead of proposing a new attention design, this study systematically evaluates three attention settings, namely No Attention, Light Attention, and Full Gated Attention, under the same training and assessment conditions. This allows a fair analysis of reconstruction accuracy, stability, and computational efficiency. Experiments on the Remote Sensing Image Cloud Removal (RICE1) dataset show that the attention-based configurations achieve stable reconstruction performance across three random seeds. The Full Gated Attention configuration achieves a mean Peak Signal-to-Noise Ratio (PSNR) of 34.76 ± 0.51 dB, while the Light Attention configuration provides the highest mean PSNR (35.21 ± 0.13 dB) and lowest Mean Absolute Error (MAE) (0.0167 ± 0.0004) among the attention variants. Additional assessment on the RICE2 dataset using the same Gated Attention U-Net configuration supports the robustness of the architecture across different cloud patterns and scene conditions. The attention-based configurations maintain low inference times, ranging from 0.0086 to 0.0104 seconds per image across the three-seed experiments. This makes it suitable for low-latency satellite image processing applications and deployment in resource-constrained environments. Overall, the results demonstrate that selective attention can provide a favorable balance between reconstruction quality and computational efficiency within the lightweight Modified U-Net framework.
SN - 2215-0161
ER -