Remote Sensing Image Processing

Camps‐Valls, Gustau; Tuia, Devis; Gmez-Chova, Luis; Jimnez, Sandra; Malo, J.

doi:10.1007/978-3-031-02247-0

Cited by 64 publications

(10 citation statements)

References 459 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…RTMs and advanced regression methods, such as GPs: simulated data generated by the RTM is used to train the statistical model which is finally applied on real spectral observations. In this way, hybrid methods ( Brede et al, 2020 ; Camps-Valls et al, 2011 ) use the advantages of both approaches: the underlying physics is regarded by the RTM and at the same time flexibility, scalability and computational speed is provided by the machine learning algorithms ( Camps-Valls et al, 2019 , 2016 ; Verrelst et al, 2015 ). Hybrid retrieval workflows are therefore very promising for vegetation properties mapping using imaging spectroscopy data and have been implemented in several operational processing chains, mainly in combination with neural networks ( Upreti et al, 2019 ; Verger et al, 2011 ).…”

Section: Introductionmentioning

confidence: 99%

Retrieval of aboveground crop nitrogen content with a hybrid machine learning method

Berger

Verrelst

Féret

et al. 2020

International Journal of Applied Earth Observation and Geoinfor

103

View full text Add to dashboard Cite

Hyperspectral acquisitions have proven to be the most informative Earth observation data source for the estimation of nitrogen (N) content, which is the main limiting nutrient for plant growth and thus agricultural production. In the past, empirical algorithms have been widely employed to retrieve information on this biochemical plant component from canopy reflectance. However, these approaches do not seek for a cause-effect relationship based on physical laws. Moreover, most studies solely relied on the correlation of chlorophyll content with nitrogen, and thus neglected the fact that most N is bound in proteins. Our study presents a hybrid retrieval method using a physically-based approach combined with machine learning regression to estimate crop N content. Within the workflow, the leaf optical properties model PROSPECT-PRO including the newly calibrated specific absorption coefficients (SAC) of proteins, was coupled with the canopy reflectance model 4SAIL to PROSAIL-PRO. The latter was then employed to generate a training database to be used for advanced probabilistic machine learning methods: a standard homoscedastic Gaussian process (GP) and a heteroscedastic GP regression that accounts for signal-to-noise relations. Both GP models have the property of providing confidence intervals for the estimates, which sets them apart from other machine learners. Moreover, a GP-based sequential backward band removal algorithm was employed to analyze the band-specific information content of PROSAIL-PRO simulated spectra for the estimation of aboveground N. Data from multiple hyperspectral field campaigns, carried out in the framework of the future satellite mission Environmental Mapping and Analysis Program (EnMAP), were exploited for validation. In these campaigns, corn and winter wheat spectra were acquired to simulate spectral EnMAP data. Moreover, destructive N measurements from leaves, stalks and fruits were collected separately to enable plant-organ-specific validation. The results showed that both GP models can provide accurate aboveground N simulations, with slightly better results of the heteroscedastic GP in terms of model testing and against in situ N measurements from leaves plus stalks, with root mean square error (RMSE) of 2.1 g/m². However, the inclusion of fruit N content for validation deteriorated the results, which can be explained by the inability of the radiation to penetrate the thick tissues of stalks, corn cobs and wheat ears. GP-based band analysis identified optimal spectral settings with ten bands mainly situated in the shortwave infrared (SWIR) spectral region. Use of well-known protein absorption bands from the literature showed comparative results. Finally, the heteroscedastic GP model was successfully applied on airborne hyperspectral data for N mapping. We conclude that GP algorithms, and in particular the heteroscedastic GP, should be implemented for global agricultural monitoring of aboveground N from future imaging spectroscopy data.

show abstract

Section: Introductionmentioning

confidence: 99%

Retrieval of aboveground crop nitrogen content with a hybrid machine learning method

Berger

Verrelst

Féret

et al. 2020

International Journal of Applied Earth Observation and Geoinfor

103

View full text Add to dashboard Cite

show abstract

“…This wealth of spectral information enables more accurate material identification compared to RGB imaging [2]. However, the observed reflectance is usually a mixture of the spectral signatures of the materials present in the scene due to the heterogeneity of the scene [3]. Consequently, there is a need for methods that can quantitatively decompose, or unmix, the captured spectral signature into its spectral components, also referred to as "endmembers," and their corresponding proportions within the mixture, referred to as "abundances" [4], [5].…”

Section: Introductionmentioning

confidence: 99%

“…1a, ideally models observed HSI signatures as a linear combination of endmembers' signatures weighted by their corresponding abundances [1]. However, when there are nonlinear effects such as multiple scattering, LMM is no longer applicable, because the signatures captured by sensors result from interactions with various materials at different levels/layers [3].…”

Section: Introductionmentioning

confidence: 99%

“…To address this nonlinearity, a nonlinear mixing model (NLMM) is proposed [3]. Two popular NLMMs are intimate mixture and multilayered mixture, illustrated in Fig.…”

Section: Introductionmentioning

confidence: 99%

“…Manuscript received April 19, 2021; revised August 16, 2021 are close to each other, while in multilayered mixture, interactions with different materials occur in different layers. Under both LMM and NLMM, the HSI blind unmixing problem involves two tasks [3]: (a) endmember estimation and (b) abundance estimation. Generally, endmember estimation methods are based on geometrical approaches, assuming that the data is embedded in a simplex whose vertices correspond to the endmembers.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Hyperspectral Blind Unmixing Using a Double Deep Image Prior

Zhou,

Rodrigues

2024

IEEE Trans. Neural Netw. Learning Syst.

View full text Add to dashboard Cite

With the rise of machine learning, hyperspectral image (HSI) unmixing problems have been tackled using learningbased methods. However, physically meaningful unmixing results are not guaranteed without proper guidance. In this work, we propose an unsupervised framework inspired by Deep-Image-Prior (DIP) that can be used for both linear and nonlinear blind unmixing models. The framework consists of three modules:(1) an Endmember estimation module using DIP (EDIP), (2) an Abundance estimation module using DIP (ADIP), and (3) a Mixing module (MM). EDIP and ADIP modules generate endmembers and abundances, respectively, while MM produces a reconstruction of the HSI observations based on the postulated unmixing model. We introduce a composite loss function that applies to both linear and nonlinear unmixing models to generate meaningful unmixing results. Additionally, we propose an adaptive loss weight strategy for better unmixing results in nonlinear mixing scenarios. The proposed methods outperform state-of-art unmixing algorithms in extensive experiments conducted on both synthetic and real datasets.

show abstract

Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression

Riese

Keller

2020

Advances in Computer Vision and Pattern Recognition

View full text Add to dashboard Cite

Remote Sensing Image Processing

Cited by 64 publications

References 459 publications

Retrieval of aboveground crop nitrogen content with a hybrid machine learning method

Retrieval of aboveground crop nitrogen content with a hybrid machine learning method

Hyperspectral Blind Unmixing Using a Double Deep Image Prior

Supervised, Semi-supervised, and Unsupervised Learning for Hyperspectral Regression

Contact Info

Product

Resources

About