Sentinel-2 Masking CNNs Trained on Physics-Supervised Labels

Sentinel-2 Masking CNNs Trained on Physics-Supervised Labels

This article presents a method to improve pixel-level classification of Sentinel-2 imagery by integrating spectral index-based masking with deep learning approaches using 1-D, 2-D, and 3-D convolutional neural networks (CNN1D, CNN2D, and CNN3D). Rather than relying on manually labeled data, the prop...

Full description

Saved in:
Bibliographic Details
Main Authors: Efrain Padilla-Zepeda, Kevin Alonso, Raquel De Los Reyes, Deni Torres-Roman, Avi Putri Pertiwi, Tobias Storch
Format: Article
Language:English
Published: IEEE 2025-01-01
Series:IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Subjects:
Classification
deep learning
masking algorithm
multispectral
pixel-level
sentinel-2
Online Access:https://ieeexplore.ieee.org/document/11045065/
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://ieeexplore.ieee.org/document/11045065/

Similar Items