Comparative analysis of atmospheric radiative transfer models using the Atmospheric Look-up table Generator (ALG) toolbox (version 2.0)

Gaussian processes retrieval of crop traits in Google Earth Engine based on Sentinel-2 top-of-atmosphere data

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.

Quantifying Fundamental Vegetation Traits over Europe Using the Sentinel-3 OLCI Catalogue in Google Earth Engine

Thanks to the emergence of cloud-computing platforms and the ability of machine learning methods to solve prediction problems efficiently, this work presents a workflow to automate spatiotemporal mapping of essential vegetation traits from Sentinel-3 (S3) imagery. The traits included leaf chlorophyll content (LCC), leaf area index (LAI), fraction of absorbed photosynthetically active radiation (FAPAR), and fractional vegetation cover (FVC), being fundamental for assessing photosynthetic activity on Earth. The workflow involved Gaussian process regression (GPR) algorithms trained on top-of-atmosphere (TOA) radiance simulations generated by the coupled canopy radiative transfer model (RTM) SCOPE and the atmospheric RTM 6SV. The retrieval models, named to S3-TOA-GPR-1.0, were directly implemented in Google Earth Engine (GEE) to enable the quantification of the traits from TOA data as acquired from the S3 Ocean and Land Colour Instrument (OLCI) sensor.Following good to high theoretical validation results with normalized root mean square error (NRMSE) ranging from 5% (FAPAR) to 19% (LAI), a three fold evaluation approach over diverse sites and land cover types was pursued: (1) temporal comparison against LAI and FAPAR products obtained from Moderate Resolution Imaging Spectroradiometer (MODIS) for the time window 2016-2020, (2) spatial difference mapping with Copernicus Global Land Service (CGLS) estimates, and (3) direct validation using interpolated in situ data from the VALERI network. For all three approaches, promising results were achieved. Selected sites demonstrated coherent seasonal patterns compared to LAI and FAPAR MODIS products, with differences between spatially averaged temporal patterns of only 6.59%. In respect of the spatial mapping comparison, estimates provided by the S3-TOA-GPR-1.0 models indicated highest consistency with FVC and FAPAR CGLS products. Moreover, the direct validation of our S3-TOA-GPR-1.0 models against VALERI estimates indicated with regard to jurisdictional claims in good retrieval performance for LAI, FAPAR and FVC. We conclude that our retrieval workflow of spatiotemporal S3 TOA data processing into GEE opens the path towards global monitoring of fundamental vegetation traits, accessible to the whole research community.

Refining Atmosphere Profiles for Aerial Target Detection Models

Atmospheric path radiance in the infrared is an extremely important quantity in calculating system performance in certain infrared detection systems. For infrared search and track (IRST) system performance calculations, the path radiance competes with the target for precious detector well electrons. In addition, the radiance differential between the target and the path radiance defines the signal level that must be detected. Long-range, high-performance, offensive IRST system design depends on accurate path radiance predictions. In addition, in new applications such as drone detection where a dim unresolved target is embedded into a path radiance background, sensor design and performance are highly dependent on atmospheric path radiance. Being able to predict the performance of these systems under particular weather conditions and locations has long been an important topic. MODTRAN has been a critical tool in the analysis of systems and prediction of electro-optical system performance. The authors have used MODTRAN over many years for an average system performance using the typical "pull-down" conditions in the software. This article considers the level of refinement required for a custom MODTRAN atmosphere profile to satisfactorily model an infrared camera's performance for a specific geographic location, date, and time. The average difference between a measured sky brightness temperature and a MODTRAN predicted value is less than 0.5 °C with sufficient atmosphere profile updates. The agreement between experimental results and MODTRAN predictions indicates the effectiveness of including updated atmospheric composition, radiosonde, and air quality data from readily available Internet sources to generate custom atmosphere profiles.

Laser Beam Atmospheric Propagation Modelling for Aerospace LIDAR Applications

Atmospheric effects have a significant impact on the performance of airborne and space laser systems. Traditional models used to predict propagation effects rely heavily on simplified assumptions of the atmospheric properties and their interactions with laser systems. In the engineering domain, these models need to be continually improved in order to develop tools that can predict laser beam propagation with high accuracy and for a wide range of practical applications such as LIDAR (light detection and ranging), free-space optical communications, remote sensing, etc. The underlying causes of laser beam attenuation in the atmosphere are examined in this paper, with a focus on the dominant linear effects: absorption, scattering, turbulence, and non-linear thermal effects such as blooming, kinetic cooling, and bleaching. These phenomena are quantitatively analyzed, highlighting the implications of the various assumptions made in current modeling approaches. Absorption and scattering, as the dominant causes of attenuation, are generally well captured in existing models and tools, but the impacts of non-linear phenomena are typically not well described as they tend to be application specific. Atmospheric radiative transfer codes, such as MODTRAN, ARTS, etc., and the associated spectral databases, such as HITRAN, are the existing tools that implement state-of-the-art models to quantify the total propagative effects on laser systems. These tools are widely used to analyze system performance, both for design and test/evaluation purposes. However, present day atmospheric radiative transfer codes make several assumptions that reduce accuracy in favor of faster processing. In this paper, the atmospheric radiative transfer models are reviewed highlighting the associated methodologies, assumptions, and limitations. Empirical models are found to offer a robust analysis of atmospheric propagation, which is particularly well-suited for design, development, test and evaluation (DDT&E) purposes. As such, empirical, semi-empirical, and ensemble methodologies are recommended to complement and augment the existing atmospheric radiative transfer codes. There is scope to evolve the numerical codes and empirical approaches to better suit aerospace applications, where fast analysis is required over a range of slant paths, incidence angles, altitudes, and atmospheric conditions, which are not exhaustively captured in current performance assessment methods.

Studying the Feasibility of Assimilating Sentinel-2 and PlanetScope Imagery into the SAFY Crop Model to Predict Within-Field Wheat Yield

Spatial information embedded in a crop model can improve yield prediction. Leaf area index (LAI) is a well-known crop variable often estimated from remote-sensing data and used as an input into crop models. In this study, we evaluated the assimilation of LAI derived from high-resolution (both spatial and temporal) satellite imagery into a mechanistic crop model, a simple algorithm for yield estimate (SAFY), to assess the within-field crop yield. We tested this approach on spring wheat grown in Israel. Empirical LAI models were derived from the biophysical processor for Sentinel-2 LAI and spectral vegetation indices from Sentinel-2 and PlanetScope images. The predicted grain yield obtained from the SAFY model was compared against the harvester’s yield map. LAI derived from PlanetScope and Sentinel-2 fused images achieved higher yield prediction (RMSE = 69 g/m2) accuracy than that of Sentinel-2 LAI (RMSE = 88 g/m2). Even though the spatial yield estimation was only moderately correlated to the ground truth (R2 = 0.45), this is consistent with current studies in this field, and the potential to capture within-field yield variations using high-resolution imagery has been demonstrated. Accordingly, this is the first application of PlanetScope and Sentinel-2 images conjointly used to obtain a high-density time series of LAI information to model within-field yield variability.

Systematic Assessment of MODTRAN Emulators for Atmospheric Correction

Atmospheric radiative transfer models (RTMs) simulate the light propagation in the Earth's atmosphere. With the evolution of RTMs, their increase in complexity makes them impractical in routine processing such as atmospheric correction. To overcome their computational burden, standard practice is to interpolate a multidimensional lookup table (LUT) of prestored simulations. However, accurate interpolation relies on large LUTs, which still implies large computation times for their generation and interpolation. In recent years, emulation has been proposed as an alternative to LUT interpolation. Emulation approximates the RTM outputs by a statistical regression model trained with a low number of RTM runs. However, a concern is whether the emulator reaches sufficient accuracy for atmospheric correction. Therefore, we have performed a systematic assessment of key aspects that impact the precision of emulating MODTRAN: 1) regression algorithm; 2) training database size; 3) dimensionality reduction (DR) method and a number of components; and 4) spectral resolution. The Gaussian processes regression (GPR) was found the most accurate emulator. The principal component analysis remains a robust DR method and nearly 20 components reach sufficient precision. Based on a database of 1000 samples covering a broad range of atmospheric conditions, GPR emulators can reconstruct the simulated spectral data with relative errors below 1% for the 95th percentile. These emulators reduce the processing time from days to minutes, preserving sufficient accuracy for atmospheric correction and providing model uncertainties and derivatives. We provide a set of guidelines and tools to design and generate accurate emulators for satellite data processing applications.

Top-of-Atmosphere Retrieval of Multiple Crop Traits Using Variational Heteroscedastic Gaussian Processes within a Hybrid Workflow

In support of cropland monitoring, operational Copernicus Sentinel-2 (S2) data became available globally and can be explored for the retrieval of important crop traits. Based on a hybrid workflow, retrieval models for six essential biochemical and biophysical crop traits were developed for both S2 bottom-of-atmosphere (BOA) L2A and S2 top-of-atmosphere (TOA) L1C data. A variational heteroscedastic Gaussian process regression (VHGPR) algorithm was trained with simulations generated by the combined leaf-canopy reflectance model PROSAILat the BOA scale and further combined with the Second Simulation of a Satellite Signal in the Solar Spectrum (6SV) atmosphere model at the TOA scale. Established VHGPR models were then applied to S2 L1C and L2A reflectance data for mapping: leaf chlorophyll content (C_ab), leaf water content (C_w), fractional vegetation coverage (FVC), leaf area index (LAI), and upscaled leaf biochemical compounds, i.e., LAI * C_ab (laiCab) and LAI * C_w (laiCw). Estimated variables were validated using in situ reference data collected during the Munich-North-Isar field campaigns within growing seasons of maize and winter wheat in the years 2017 and 2018. For leaf biochemicals, retrieval from BOA reflectance slightly outperformed results from TOA reflectance, e.g., obtaining a root mean squared error (RMSE) of 6.5 μg/cm² (BOA) vs. 8 μg/cm² (TOA) in the case of C_ab. For the majority of canopy-level variables, instead, estimation accuracy was higher when using TOA reflectance data, e.g., with an RMSE of 139 g/m² (BOA) vs. 113 g/m² (TOA) for laiCw. Derived maps were further compared against reference products obtained from the ESA Sentinel Application Platform (SNAP) Biophysical Processor. Altogether, the consistency between L1C and L2A retrievals confirmed that crop traits can potentially be estimated directly from TOA reflectance data. Successful mapping of canopy-level crop traits including information about prediction confidence suggests that the models can be transferred over spatial and temporal scales and, therefore, can contribute to decision-making processes for cropland management.

A Survey of Active Learning for Quantifying Vegetation Traits from Terrestrial Earth Observation Data

The current exponential increase of spatiotemporally explicit data streams from satellitebased Earth observation missions offers promising opportunities for global vegetation monitoring. Intelligent sampling through active learning (AL) heuristics provides a pathway for fast inference of essential vegetation variables by means of hybrid retrieval approaches, i.e., machine learning regression algorithms trained by radiative transfer model (RTM) simulations. In this study we summarize AL theory and perform a brief systematic literature survey about AL heuristics used in the context of Earth observation regression problems over terrestrial targets. Across all relevant studies it appeared that: (i) retrieval accuracy of AL-optimized training data sets outperformed models trained over large randomly sampled data sets, and (ii) Euclidean distance-based (EBD) diversity method tends to be the most efficient AL technique in terms of accuracy and computational demand. Additionally, a case study is presented based on experimental data employing both uncertainty and diversity AL criteria. Hereby, a a simulated training data base by the PROSAIL-PRO canopy RTM is used to demonstrate the benefit of AL techniques for the estimation of total leaf carotenoid content (C_xc) and leaf water content (C_w). Gaussian process regression (GPR) was incorporated to minimize and optimize the training data set with AL. Training the GPR algorithm on optimally AL-based sampled data sets led to improved variable retrievals compared to training on full data pools, which is further demonstrated on a mapping example. From these findings we can recommend the use of AL-based sub-sampling procedures to select the most informative samples out of large training data pools. This will not only optimize regression accuracy due to exclusion of redundant information, but also speed up processing time and reduce final model size of kernel-based machine learning regression algorithms, such as GPR. With this study we want to encourage further testing and implementation of AL sampling methods for hybrid retrieval workflows. AL can contribute to the solution of regression problems within the framework of operational vegetation monitoring using satellite imaging spectroscopy data, and may strongly facilitate data processing for cloud-computing platforms.

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

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.