Optimizing Fine-Tuning of Earth Foundation Models via Multidimensional Latin Hypercube Sampling for Small-Scale Burn Scar Identification

Identifying small-scale burn scars is critical for global carbon accounting, yet remains computationally challenging due to spectral complexity and ground truth scarcity in heterogeneous landscapes. Conventional deep learning models often fail to generalize in such environments, lacking both domain-...

Descripció completa

Dades bibliogràfiques

Autors principals:	Yuchen Du, Daniel Jacome, Jianghao Wang
Format:	Artigo
Idioma:	Inglês
Publicat:	MDPI AG 2026-04-01
Col·lecció:	Fire
Matèries:	burn scar segmentation Latin hypercube sampling earth foundation models Prithvi fine-tuning
Accés en línia:	https://www.mdpi.com/2571-6255/9/4/161
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!