What type of study is this?

September 10, 2025Scientific ReportsOpen Access

Land use classification using multi-year Sentinel-2 images with deep learning ensemble network

View Full Paper

Ask AI

Bookmark

Achieving 98.21% accuracy, IRUNet enhances land use classification for better urban planning and environmental monitoring.
The model achieved a Dice similarity coefficient of 88.96%, outperforming traditional approaches like UNet and Attention-UNet.
The method employs multi-scale feature fusion and Test-Time Augmentation to improve prediction robustness and accuracy.
This framework enables effective multi-year land use classification, addressing gaps in existing methods.

Discussion

No takes yet. Share an insight, caveat, or question.

Implication

This research shows enhanced land use classification accuracy using IRUNet in multi-year Sentinel-2 imagery, indicating improved urban planning capabilities.

Cite This Study

Jagannathan et al. (2025) studied this question.

synapsesocial.com/papers/68c1bd3254b1d3bfb60ee4f6 https://doi.org/10.1038/s41598-025-12512-7

View Full Paper

Ask AI

Bookmark

Implication

This research shows enhanced land use classification accuracy using IRUNet in multi-year Sentinel-2 imagery, indicating improved urban planning capabilities.

Land use classification using multi-year Sentinel-2 images with deep learning ensemble network

Key Points

Discussion

Implication

Cite This Study

Land use classification using multi-year Sentinel-2 images with deep learning ensemble network

Key Points

Discussion

Implication

Cite This Study

Also Consider

Also Consider