English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Atmospheric correction is a fundamental task in remote sensing becauseobservations are taken either of the atmosphere or looking through theatmosphere. Atmospheric correction errors can significantly alter the spectralsignature of the observations, and lead to invalid classifications or targetdetection. 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 requireextensive prior knowledge about sensor characteristics, collection geometry,and environmental characteristics of the scene being collected. Theseapproaches are computationally expensive, prone to inaccuracy due to lack ofsufficient environmental and collection information, and often impossible forreal-time applications. In this paper, a geometry-dependent hybrid neuralnetwork is proposed for automatic atmospheric correction using multi-scanhyperspectral data collected from different geometries. The proposed networkcan characterize the atmosphere without any additional meteorological data. Agrid-search method is also proposed to solve the temperature emissivityseparation problem. Results show that the proposed network has the capacity toaccurately characterize the atmosphere and estimate target emissivity spectrawith a Mean Absolute Error (MAE) under 0.02 for 29 different materials. Thissolution can lead to accurate atmospheric correction to improve targetdetection for real time applications.

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