Hyperspectral imaging for chemicals identification: a human-inspired machine learning approach

Abstract

Data analysis has increasingly relied on machine learning in recent years. Since machines implement mathematical algorithms without knowing the physical nature of the problem, they may be accurate but lack the flexibility to move across different domains. This manuscript presents a machine-educating approach where a machine is equipped with a physical model, universal building blocks, and an unlabeled dataset from which it derives its decision criteria. Here, the concept of machine education is deployed to identify thin layers of organic materials using hyperspectral imaging (HSI). The measured spectra formed a nonlinear mixture of the unknown background materials and the target material spectra. The machine was educated to resolve this nonlinear mixing and identify the spectral signature of the target materials. The inputs for educating and testing the machine were a nonlinear mixing model, the spectra of the pure target materials (which are problem invariant), and the unlabeled HSI data. The educated machine is accurate, and its generalization capabilities outperform classical machines. When using the educated machine, the number of falsely identified samples is ~ 100 times lower than the classical machine. The probability for detection with the educated machine is 96% compared to 90% with the classical machine.

Field-Deployed Spectroscopy from 350 to 2500 nm: A Promising Technique for Early Identification of Powdery Mildew Disease (Erysiphe necator) in Vineyards

“…These techniques often combine near-infrared (NIR) and red reflectance to gather data, exploiting biophysical parameters detectable via sensors equipped on UAVs. Notably, in the context of detecting diseases and environmental safety, HSI has been extensively utilised [20,21]. Moreover, HSI is adept at reducing constants and linear functions, thereby refining the precision of remote sensing in measuring crop parameters [22].…”

Foreground Signature Extraction for an Intimate Mixing Model in Hyperspectral Image Classification

“…Other works have explored settings in which nonlinear effects, such as reflection and refraction, have a non-negligible effect on the spectral mixtures represented by each pixel. There are a wide range of potential nonlinear unmixing models [7], [8], and dedicated algorithms for cases where the measured signature is noisy [9]- [11].…”