Lightweight Deep Learning Approaches for Lithological Mapping in Vegetated Terrains of the Vălioara Valley, Romania

Mapping lithology in areas with dense vegetation remains a major challenge for remote sensing, as plant cover tends to obscure the spectral signatures of underlying rock formations. This study tackles that issue by comparing the performance of three custom-built lightweight deep learning models in t...

Full description

Bibliographic Details

Published in:	ISPRS International Journal of Geo-Information
Main Authors:	Valentin Árvai, Gáspár Albert
Format:	Article
Language:	English
Published:	MDPI AG 2025-09-01
Subjects:	lithological mapping remote sensing deep learning vision transformer pixel-based image analysis Sentinel-2
Online Access:	https://www.mdpi.com/2220-9964/14/9/350