DeepSalt: Bridging Laboratory and Satellite Spectra through Domain Adaptation and Knowledge Distillation for Large-Scale Soil Salinity Estimation

TL;DR

DeepSalt is a novel deep learning framework that combines domain adaptation and knowledge distillation to accurately estimate soil salinity at large scales by bridging laboratory and satellite spectral data.

Contribution

It introduces the Spectral Adaptation Unit and a knowledge distillation strategy to transfer spectral insights from lab to satellite data, enabling scalable soil salinity estimation.

Findings

DeepSalt outperforms baseline methods without domain adaptation.

The approach generalizes well to unseen regions.

It significantly reduces the need for ground sampling.

Abstract

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.