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-...

Celý popis

Podrobná bibliografie

Hlavní autoři:	Yuchen Du, Daniel Jacome, Jianghao Wang
Médium:	Artigo
Jazyk:	Inglês
Vydáno:	MDPI AG 2026-04-01
Edice:	Fire
Témata:	burn scar segmentation Latin hypercube sampling earth foundation models Prithvi fine-tuning
On-line přístup:	https://www.mdpi.com/2571-6255/9/4/161
Tagy:	Přidat tag Žádné tagy, Buďte první, kdo vytvoří štítek k tomuto záznamu!