Towards crop traits estimation from hyperspectral data: evaluation of neural network models trained with real multi-site data or synthetic RTM simulations

Abstract

Hyperspectral images from newly launched (ASI-PRISMA and DLR-EnMAP) and future satellite (ESA-CHIME) are an opportunity, thanks to the high spectral resolution and full range continuity, to improve the retrieval of information about the crop parameters and status.The high dimensionality of hyperspectral data and the non-linear relationship between the crop biophysical parameters and their spectral signature make quantitative estimation of crop characteristics challenging, to address these problems we tested different configurations of neural networks (fully connected and convolutional).We tested the different architectures on two training dataset, one consists in ground data collected in three experiments, in different locations and seasons, the second one (hybrid) is composed by synthetic data generated using a radiative transfer model (PROSAIL-PRO).Preliminary results for LAI, CCC and CNC retrieval are encouraging in particular when ground data are exploited demonstrating of the potentiality of NN to fully exploit the information density of the hyperspectral data.

Code and data availability

The paper describes ground hyperspectral/biopar datasets and NN models but provides no public deposit, availability statement, or authors' URL for its data, code, or trained models. The only URL present (https://gitlab.com/jbferet/prosail) is the cited third-party PROSAIL RTM tool, not a paper-specific asset.

No evidence-backed public reproduction asset is currently recorded.