Ill-posed Surface Emissivity Retrieval from Multi-Geometry Hyperspectral Images using a Hybrid Deep Neural Network

TL;DR

This paper introduces a hybrid neural network that automatically performs atmospheric correction on hyperspectral images from multiple geometries, accurately estimating atmospheric parameters and target emissivity without extra meteorological data, enabling real-time remote sensing applications.

Contribution

A novel geometry-dependent hybrid neural network for atmospheric correction that operates without additional meteorological data, improving accuracy and efficiency.

Findings

Achieved MAE under 0.02 for 29 materials in emissivity estimation.

Successfully characterized atmosphere and estimated emissivity spectra from multi-geometry hyperspectral data.

Enabled potential for real-time atmospheric correction in remote sensing.

Abstract

Atmospheric correction is a fundamental task in remote sensing because observations are taken either of the atmosphere or looking through the atmosphere. Atmospheric correction errors can significantly alter the spectral signature of the observations, and lead to invalid classifications or target detection. This is even more crucial when working with hyperspectral data, where a precise measurement of spectral properties is required. State-of-the-art physics-based atmospheric correction approaches require extensive prior knowledge about sensor characteristics, collection geometry, and environmental characteristics of the scene being collected. These approaches are computationally expensive, prone to inaccuracy due to lack of sufficient environmental and collection information, and often impossible for real-time applications. In this paper, a geometry-dependent hybrid neural network is proposed for automatic atmospheric correction using multi-scan hyperspectral data collected from different geometries. The proposed network can characterize the atmosphere without any additional meteorological data. A grid-search method is also proposed to solve the temperature emissivity separation problem. Results show that the proposed network has the capacity to accurately characterize the atmosphere and estimate target emissivity spectra with a Mean Absolute Error (MAE) under 0.02 for 29 different materials. This solution can lead to accurate atmospheric correction to improve target detection for real time applications.