Variability and Uncertainty Challenges in Scaling Imaging Spectroscopy Retrievals and Validations from Leaves Up to Vegetation Canopies

Malenovský, Zbyněk; Homolová, Lucie; Lukeš, Petr; Buddenbaum, Henning; Verrelst, Jochem; Alonso, Luis; Schaepman, Michael E.; Lauret, Nicolas; Gastellu-Etchegorry, Jean-Philippe

doi:10.1007/s10712-019-09534-y

Cited by 38 publications

(29 citation statements)

References 127 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Tree canopies are likely to be well distinguished if functional information on morphology and physiology at species level is available (Torabzadeh et al, 2019). In recent years, the use of remote sensing has enabled great advances in both functional as well as scaling-based approaches (Gamon et al, 2019;Malenovský et al, 2019). In forests where species groups are well characterized and occur in clumps, species distributions can be fairly readily mapped using satellite-derived data (Chastain and Townsend, 2007).…”

Section: Direct Detection and Sampling Of Species And Their Traitsmentioning

confidence: 99%

Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models

Randin

Ashcroft

Bolliger

et al. 2020

Remote Sensing of Environment

183

142

View full text Add to dashboard Cite

General rights Copyright and moral rights for the publications made accessible in the public portal are retained by the authors and/or other copyright owners and it is a condition of accessing publications that users recognise and abide by the legal requirements associated with these rights. • Users may download and print one copy of any publication from the public portal for the purpose of private study or research. • You may not further distribute the material or use it for any profit-making activity or commercial gain • You may freely distribute the URL identifying the publication in the public portal ? Take down policy If you believe that this document breaches copyright please contact us providing details, and we will remove access to the work immediately and investigate your claim.

show abstract

Section: Direct Detection and Sampling Of Species And Their Traitsmentioning

confidence: 99%

Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models

Randin

Ashcroft

Bolliger

et al. 2020

Remote Sensing of Environment

183

142

View full text Add to dashboard Cite

show abstract

“…Essentially, quantification of surface biophysical variables from spectral data always relies on a model, enabling the interpretation of spectral observations and their translation into a surface biophysical variable. Methodologically, these retrieval models can be classified into the following four categories: (1) parametric regression, e.g., spectral indices combined with a fitting function, (2) non-parametric regression, e.g., machine learning regression algorithms (ML-RAs), (3) physically-based, i.e., inverting radiative transfer models (RTMs), and (4) hybrid methods. See [3,4] for a comprehensive review of these methods and mapping applications.…”

Section: Introductionmentioning

confidence: 99%

“…This means that solutions have to be developed to enable integrating GPR into the GEE environment. All in all, the ambition to plug in GPR into the GEE platform for the generation of vegetation products from S2 satellite data in a flawless cloud-based approach brings us to the following main objectives: (1) to adapt the GPR algorithm for multispectral data so it is scalable into GEE environment; (2) to optimize and import a GPR model for LAI G estimation in GEE; (3) to process S2 multispectral data into LAI G in GEE; (4) to tackle the gap-filling of discontinuous LAI G time series by extending the GPR modeling to the time domain; and (5) exemplify the processing power of the developed framework with a few comprehensive case studies.…”

Section: Introductionmentioning

confidence: 99%

Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine

et al. 2021

Self Cite

View full text Add to dashboard Cite

For the last decade, Gaussian process regression (GPR) proved to be a competitive machine learning regression algorithm for Earth observation applications, with attractive unique properties such as band relevance ranking and uncertainty estimates. More recently, GPR also proved to be a proficient time series processor to fill up gaps in optical imagery, typically due to cloud cover. This makes GPR perfectly suited for large-scale spatiotemporal processing of satellite imageries into cloud-free products of biophysical variables. With the advent of the Google Earth Engine (GEE) cloud platform, new opportunities emerged to process local-to-planetary scale satellite data using advanced machine learning techniques and convert them into gap-filled vegetation properties products. However, GPR is not yet part of the GEE ecosystem. To circumvent this limitation, this work proposes a general adaptation of GPR formulation to parallel processing framework and its integration into GEE. To demonstrate the functioning and utility of the developed workflow, a GPR model predicting green leaf area index (LAIG) from Sentinel-2 imagery was imported. Although by running this GPR model into GEE any corner of the world can be mapped into LAIG at a resolution of 20 m, here we show some demonstration cases over western Europe with zoom-ins over Spain. Thanks to the computational power of GEE, the mapping takes place on-the-fly. Additionally, a GPR-based gap filling strategy based on pre-optimized kernel hyperparameters is also put forward for the generation of multi-orbit cloud-free LAIG maps with an unprecedented level of detail, and the extraction of regularly-sampled LAIG time series at a pixel level. The ability to plugin a locally-trained GPR model into the GEE framework and its instant processing opens up a new paradigm of remote sensing image processing.

show abstract

“…How and what we detect with remote sensing, including the "best" sampling strategy, can depend on the specific question or hypothesis to be tested, the observer's disciplinary background, the technology at hand, and the realism of the scaling model with respect to the relevant physiological and biophysical processes. Challenges in scaling imaging spectroscopy observations from leaves to vegetation canopies, including topics of natural variability and measurement uncertainty, are further described by Malenovský et al (2019) (this issue).…”

Section: The Concept Of Scalementioning

confidence: 99%

Assessing Vegetation Function with Imaging Spectroscopy

et al. 2019

View full text Add to dashboard Cite

Healthy vegetation function supports diverse biological communities and ecosystem processes, and provides crops, forest products, forage, and countless other benefits. Vegetation function can be assessed by examining dynamic processes and by evaluating plant traits, which themselves are dynamic. Using both trait-based and process-based approaches, spectroscopy can assess vegetation function at multiple scales using a variety of sensors and platforms ranging from proximal to airborne and satellite measurements. Since spectroscopic data are defined by the instruments and platforms available, along with their corresponding spatial, temporal and spectral scales, and since these scales may not always match those of the function of interest, consideration of scale is a necessary focus. For a full understanding of vegetation processes, combined (multi-scale) sampling methods using empirical and theoretical approaches are required, along with improved informatics.

show abstract

Variability and Uncertainty Challenges in Scaling Imaging Spectroscopy Retrievals and Validations from Leaves Up to Vegetation Canopies

Cited by 38 publications

References 127 publications

Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models

Monitoring biodiversity in the Anthropocene using remote sensing in species distribution models

Green LAI Mapping and Cloud Gap-Filling Using Gaussian Process Regression in Google Earth Engine

Assessing Vegetation Function with Imaging Spectroscopy

Contact Info

Product

Resources

About