No abstract

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.

No abstract

Decades after release of the first PROSPECT + SAIL (commonly called PROSAIL) versions, the model is still the most famous representative in the field of canopy reflectance modelling and has been widely used to obtain plant biochemical and structural variables, particularly in the agricultural context. The performance of the retrieval is usually assessed by quantifying the distance between the estimated and the in situ measured variables. While this has worked for hundreds of studies that obtained canopy density as a one-sided Leaf Area Index (LAI) or pigment content, little is known about the role of the canopy geometrical properties specified as the Average Leaf Inclination Angle (ALIA). In this study, we exploit an extensive field dataset, including narrow-band field spectra, leaf variables and canopy properties recorded in seven individual campaigns for winter wheat (4x) and silage maize (3x). PROSAIL outputs generally did not represent field spectra well, when in situ variables served as input for the model. A manual fitting of ALIA and leaf water (EWT) revealed significant deviations for both variables (RMSE = 14.5°, 0.020 cm) and an additional fitting of the brown leaf pigments (Cbrown) was necessary to obtain matching spectra at the near infrared (NIR) shoulder. Wheat spectra tend to be underestimated by the model until the emergence of inflorescence when PROSAIL begins to overestimate crop reflectance. This seasonal pattern could be attributed to an attenuated development of ALIAopt compared to in situ measured ALIA. Segmentation of nadir images of wheat was further used to separate spectral contributors into dark background, ears and leaves + stalks. It could be shown that the share of visible fruit ears from nadir view correlates positively with the deviations between field spectral measurement and PROSAIL spectral outputs (R² = 0.78 for aggregation by phenological stages), indicating that retrieval errors increase for ripening stages. An appropriate model parameterization is recommended to assure accurate retrievals of biophysical and biochemical products of interest. The interpretation of inverted ALIA as physical leaf inclinations is considered unfeasible and we argue in favour of treating it as a free calibration parameter.

The current exponential increase of spatiotemporally explicit data streams from satellite-based 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 (Cxc) and leaf water content (Cw). 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.