The unprecedented availability of optical satellite data in cloud-based computing platforms, such as Google Earth Engine (GEE), opens new possibilities to develop crop trait retrieval models from the local to the planetary scale. Hybrid retrieval models are of interest to run in these platforms as they combine the advantages of physically- based radiative transfer models (RTM) with the flexibility of machine learning regression algorithms. Previous research with GEE primarily relied on processing bottom-of-atmosphere (BOA) reflectance data, which requires atmospheric correction. In the present study, we implemented hybrid models directly into GEE for processing Sentinel-2 (S2) Level-1C (L1C) top-of-atmosphere (TOA) reflectance data into crop traits. To achieve this, a training dataset was generated using the leaf-canopy RTM PROSAIL in combination with the atmospheric model 6SV. Gaussian process regression (GPR) retrieval models were then established for eight essential crop traits namely leaf chlorophyll content, leaf water content, leaf dry matter content, fractional vegetation cover, leaf area index (LAI), and upscaled leaf variables (i.e., canopy chlorophyll content, canopy water content and canopy dry matter content). An important pre-requisite for implementation into GEE is that the models are sufficiently light in order to facilitate efficient and fast processing. Successful reduction of the training dataset by 78% was achieved using the active learning technique Euclidean distance-based diversity (EBD). With the EBD-GPR models, highly accurate validation results of LAI and upscaled leaf variables were obtained against in situ field data from the validation study site Munich-North-Isar (MNI), with normalized root mean square errors (NRMSE) from 6% to 13%. Using an independent validation dataset of similar crop types (Italian Grosseto test site), the retrieval models showed moderate to good performances for canopy-level variables, with NRMSE ranging from 14% to 50%, but failed for the leaf-level estimates. Obtained maps over the MNI site were further compared against Sentinel-2 Level 2 Prototype Processor (SL2P) vegetation estimates generated from the ESA Sentinels' Application Platform (SNAP) Biophysical Processor, proving high consistency of both retrievals ( R 2 from 0.80 to 0.94). Finally, thanks to the seamless GEE processing capability, the TOA-based mapping was applied over the entirety of Germany at 20 m spatial resolution including information about prediction uncertainty. The obtained maps provided confidence of the developed EBD-GPR retrieval models for integration in the GEE framework and national scale mapping from S2-L1C imagery. In summary, the proposed retrieval workflow demonstrates the possibility of routine processing of S2 TOA data into crop traits maps at any place on Earth as required for operational agricultural applications.
Why it matches plant phenotyping methods衛星データから作物形質を推定するGPR retrievalモデルと、GEE上での実装・検証ワークフローが研究の中心であり、植物形質フェノタイピング手法に該当する。
abstractwe implemented hybrid models directly into GEE for processing Sentinel-2 (S2) Level-1C (L1C) top-of-atmosphere (TOA) reflectance data into crop traits.
Reproduction assets found保存済みの本文根拠を更新済みルールで再検証し、公開資産1件を確認しました。Code · publicThe GEE codes to run the EBD-GPR models and display the vegetation maps of this study is hosted on the repository https://github.com/esjoal/GEE_GPR_mapping_vegetation .Open asset ↗esjoal/GEE_GPR_mapping_vegetationlines:222-231Code / dataset availability confirmedEurope PMC · checked 15 Sept 2026
-Solar-induced chlorophyll a Fluorescence (SIF), which is distributed over a relatively broad (~200 nm) spectral range, is a signal intricately connected to the efficiency of photosynthesis and is now observable from space. Variants of the Fraunhofer Line Depth/Discriminator (FLD) method are used as the basis of retrieval algorithms for estimating SIF from space. Although typically unobserved directly, recent advances in FLD-based algorithms now facilitate the prediction (by model inversion) of the canopy emitted fluorescence spectrum from the discrete-feature FLD retrievals.-Here we present first canopy scale measurements of chlorophyll a fluorescence spectra emitted from Scots pine at two times of year, and also from a lingonberry dominated understory. We used a high power multispectral Light Emitting Diode (LED) array to illuminate the respective canopies at night and measured under standardised conditions using a field spectrometer mounted in the nadir position above the canopy. We refer to the technique, which facilitates the in situ upscaling of a commonly measured leaf scale quantity to the canopy, as nocturnal LED-Induced chlorophyll a Fluorescence (LEDIF).-The shape of the LEDIF spectra was dependant on the colour of the excitation light and also on the dominant species. Because we measured pine at two different times of year we were also able to show an increase in the canopy scale apparent quantum yield of fluorescence which was consistent with leaf-level increase in fluorescence yield recorded with a monitoring PAM fluorometer.-The automation of the LEDIF technique could be used to estimate seasonal changes in canopy fluorescence spectra and yield from fixed or mobile platforms and provide a window into functional traits across species and architectures. LEDIF could also be used to evaluate FLD and inversion-based retrievals of canopy spectra, as well as different irradiance normalisation schemes typically applied to SIF data to account for the dependence of SIF on ambient light conditions.
Why it matches plant phenotyping methods植物キャノピーのクロロフィル蛍光スペクトルと見かけの量子収率を測定する新規LEDIF手法を開発・実証しており、植物の生理形質取得が研究の中心である。
abstractHere we present first canopy scale measurements of chlorophyll a fluorescence spectra emitted from Scots pine at two times of year, and also from a lingonberry dominated understory.
Reproduction assets foundThe paper's LEDIF fluorescence spectra and analysis code are not stated to be publicly available. The only qualifying public asset is the SMARTSMEAR database, from which the authors downloaded the site PAR and temperature measurements used in the study; it is a public, paper-relevant data source with an explicit URL,但它Dataset · publicAcross Space and Time (FAST2017) campaign, at
the Station for Measuring Atmosphere-Ecosystem Relations II
(SMEARII), Hyytiälä, Finland (61°51N, 24°17E). Site measurements of
above canopy photosynthetically active radiation (PAR) and in canopy
(16.8 m) temperature were downloaded from the publicly accessible
SMARTSMEAR database (https://avaa.tdata.fi/web/smart).2.2. Canopy spectral measurements
Canopy scale steady state chlorophyll a fluorescence spectra were
excited at night using a multispectral LED light source (BPP210 Beamz
Professional, distributed by Tronios BV, Twente, Netherlands) from a
scaffold tower at a height of approximately 0.5 m above a mature 15 m
tall Scots pine treeOpen asset ↗SMARTSMEARpdf-raw-page:2 lines:72-128Code / dataset availability confirmedEurope PMC · checked 10 Sept 2026
This paper introduces a modular processing chain to derive global high-resolution maps of leaf traits. In particular, we present global maps at 500 m resolution of specific leaf area, leaf dry matter content, leaf nitrogen and phosphorus content per dry mass, and leaf nitrogen/phosphorus ratio. The processing chain exploits machine learning techniques along with optical remote sensing data (MODIS/Landsat) and climate data for gap filling and up-scaling of in-situ measured leaf traits. The chain first uses random forests regression with surrogates to fill gaps in the database (> 45% of missing entries) and maximizes the global representativeness of the trait dataset. Plant species are then aggregated to Plant Functional Types (PFTs). Next, the spatial abundance of PFTs at MODIS resolution (500 m) is calculated using Landsat data (30 m). Based on these PFT abundances, representative trait values are calculated for MODIS pixels with nearby trait data. Finally, different regression algorithms are applied to globally predict trait estimates from these MODIS pixels using remote sensing and climate data. The methods were compared in terms of precision, robustness and efficiency. The best model (random forests regression) shows good precision (normalized RMSE≤ 20%) and goodness of fit (averaged Pearson's correlation R = 0.78) in any considered trait. Along with the estimated global maps of leaf traits, we provide associated uncertainty estimates derived from the regression models. The process chain is modular, and can easily accommodate new traits, data streams (traits databases and remote sensing data), and methods. The machine learning techniques applied allow attribution of information gain to data input and thus provide the opportunity to understand trait-environment relationships at the plant and ecosystem scales. The new data products – the gap-filled trait matrix, a global map of PFT abundance per MODIS gridcells and the high-resolution global leaf trait maps – are complementary to existing large-scale observations of the land surface and we therefore anticipate substantial contributions to advances in quantifying, understanding and prediction of the Earth system.
Why it matches plant phenotyping methodsリモートセンシング、気候データ、機械学習を統合して葉形質を推定する処理チェーンを開発・比較検証しており、植物形質取得が中心的である。
abstractThis paper introduces a modular processing chain to derive global high-resolution maps of leaf traits.
Reproduction assets foundThe paper's core phenotyping input is the public TRY plant trait database, from which the authors obtained in-situ leaf trait measurements (SLA, LDMC, LNC, LPC, LNPR) that they gap-filled and spatialized. No author analysis code, trained models, or data products with a public authors' URL are stated in the supplied.Dataset · publicOur methods first involve using a random forest with surrogates technique to gap fill the largest global plant trait database available (TRY, ( https://www.try-db.org// ))Open asset ↗TRY · TRYlines:106-109