Salvato in:
Dettagli Bibliografici
Autori principali: Dey, Rupasree, Matin, Abdul, Lewark, Everett, Faruk, Tanjim Bin, Bachinin, Andrei, Leuthold, Sam, Cotrufo, M. Francesca, Pallickara, Shrideep, Pallickara, Sangmi Lee
Natura: Preprint
Pubblicazione: 2025
Soggetti:
Accesso online:https://arxiv.org/abs/2510.23124
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866911234505310208
author Dey, Rupasree
Matin, Abdul
Lewark, Everett
Faruk, Tanjim Bin
Bachinin, Andrei
Leuthold, Sam
Cotrufo, M. Francesca
Pallickara, Shrideep
Pallickara, Sangmi Lee
author_facet Dey, Rupasree
Matin, Abdul
Lewark, Everett
Faruk, Tanjim Bin
Bachinin, Andrei
Leuthold, Sam
Cotrufo, M. Francesca
Pallickara, Shrideep
Pallickara, Sangmi Lee
contents Soil salinization poses a significant threat to both ecosystems and agriculture because it limits plants' ability to absorb water and, in doing so, reduces crop productivity. This phenomenon alters the soil's spectral properties, creating a measurable relationship between salinity and light reflectance that enables remote monitoring. While laboratory spectroscopy provides precise measurements, its reliance on in-situ sampling limits scalability to regional or global levels. Conversely, hyperspectral satellite imagery enables wide-area observation but lacks the fine-grained interpretability of laboratory instruments. To bridge this gap, we introduce DeepSalt, a deep-learning-based spectral transfer framework that leverages knowledge distillation and a novel Spectral Adaptation Unit to transfer high-resolution spectral insights from laboratory-based spectroscopy to satellite-based hyperspectral sensing. Our approach eliminates the need for extensive ground sampling while enabling accurate, large-scale salinity estimation, as demonstrated through comprehensive empirical benchmarks. DeepSalt achieves significant performance gains over methods without explicit domain adaptation, underscoring the impact of the proposed Spectral Adaptation Unit and the knowledge distillation strategy. The model also effectively generalized to unseen geographic regions, explaining a substantial portion of the salinity variance.
format Preprint
id arxiv_https___arxiv_org_abs_2510_23124
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle DeepSalt: Bridging Laboratory and Satellite Spectra through Domain Adaptation and Knowledge Distillation for Large-Scale Soil Salinity Estimation
Dey, Rupasree
Matin, Abdul
Lewark, Everett
Faruk, Tanjim Bin
Bachinin, Andrei
Leuthold, Sam
Cotrufo, M. Francesca
Pallickara, Shrideep
Pallickara, Sangmi Lee
Computer Vision and Pattern Recognition
Machine Learning
Soil salinization poses a significant threat to both ecosystems and agriculture because it limits plants' ability to absorb water and, in doing so, reduces crop productivity. This phenomenon alters the soil's spectral properties, creating a measurable relationship between salinity and light reflectance that enables remote monitoring. While laboratory spectroscopy provides precise measurements, its reliance on in-situ sampling limits scalability to regional or global levels. Conversely, hyperspectral satellite imagery enables wide-area observation but lacks the fine-grained interpretability of laboratory instruments. To bridge this gap, we introduce DeepSalt, a deep-learning-based spectral transfer framework that leverages knowledge distillation and a novel Spectral Adaptation Unit to transfer high-resolution spectral insights from laboratory-based spectroscopy to satellite-based hyperspectral sensing. Our approach eliminates the need for extensive ground sampling while enabling accurate, large-scale salinity estimation, as demonstrated through comprehensive empirical benchmarks. DeepSalt achieves significant performance gains over methods without explicit domain adaptation, underscoring the impact of the proposed Spectral Adaptation Unit and the knowledge distillation strategy. The model also effectively generalized to unseen geographic regions, explaining a substantial portion of the salinity variance.
title DeepSalt: Bridging Laboratory and Satellite Spectra through Domain Adaptation and Knowledge Distillation for Large-Scale Soil Salinity Estimation
topic Computer Vision and Pattern Recognition
Machine Learning
url https://arxiv.org/abs/2510.23124