Estimating soil moisture content under grassland with hyperspectral data using radiative transfer modelling and machine learning.

The monitoring of soil moisture content (SMC) at very high spatial resolution (<10m) using unmanned aerial systems (UAS) is of high interest for precision agriculture and the validation of large scale SMC products. Data-driven approaches are the most common method to retrieve SMC with UAS-borne data at water limited sites over non-disturbed agricultural crops. A major disadvantage of data-driven algorithms is the limited transferability in space and time and the need of a high number of ground reference samples. Physically-based approaches are less dependent on the amount of samples and are transferable in space and time. This study explores the potential of (1) a hybrid method targeting the soil brightness factor of the PROSAIL model using a variational heteroscedastic Gaussian Processes regression (VHGPR) algorithm, and (2) a data-driven method employing VHGPR for the retrieval of SMC over three grassland sites based on UAS-borne VIS-NIR (399-1001 nm) hyperspectral data. The sites were managed by mowing (Fendt), grazing (Grosses Bruch) and irrigation (Marquardt). With these distinct local pre-conditions we aimed to identify factors that favor and limit the retrieval of SMC. The hybrid approach presented encouraging results in Marquardt (RMSE = 1.5 Vol_%, R2 = 0.2). At the permanent grassland sites (Fendt, Grosses Bruch) the thatch layer jeopardized the application of the hybrid model. We identified the complex canopy structure of grassland as the main factor impacting the hybrid SMC retrieval. The data-driven approach showed high accuracy for Fendt (R2 = 0.84, RMSE = 8.66) and Marquardt (R2 = 0.4, RMSE = 10.52). All data-driven models build on the LAI-SMC relationship. However, this relationship was hampered by mowing (Fendt), leading to a lack of transferability in time. The alteration of plant traits by grazing prevents finding a relationship with SMC in Grosses Bruch. In Marquardt, we identified the timelag between changes in SMC and plant response as the main reason of decrease in model accuracy. Yet, the model performance is accurate in undisturbed and water-limited areas (Marquardt). The analysis points to challenges that need to be tackled in future research and opens the discussion for the development of robust models to retrieve high resolution SMC from UAS-borne remote sensing observations.

Retrieval of Crop Variables from Proximal Multispectral UAV Image Data Using PROSAIL in Maize Canopy.

Mapping crop variables at different growth stages is crucial to inform farmers and plant breeders about the crop status. For mapping purposes, inversion of canopy radiative transfer models (RTMs) is a viable alternative to parametric and non-parametric regression models, which often lack transferability in time and space. Due to the physical nature of RTMs, inversion outputs can be delivered in sound physical units that reflect the underlying processes in the canopy. In this study, we explored the capabilities of the coupled leaf-canopy RTM PROSAIL applied to high-spatial-resolution (0.015 m) multispectral unmanned aerial vehicle (UAV) data to retrieve the leaf chlorophyll content (LCC), leaf area index (LAI) and canopy chlorophyll content (CCC) of sweet and silage maize throughout one growing season. Two different retrieval methods were tested: (i) applying the RTM inversion scheme to mean reflectance data derived from single breeding plots (mean reflectance approach) and (ii) applying the same inversion scheme to an orthomosaic to separately retrieve the target variables for each pixel of the breeding plots (pixel-based approach). For LCC retrieval, soil and shaded pixels were removed by applying simple vegetation index thresholding. Retrieval of LCC from UAV data yielded promising results compared to ground measurements (sweet maize RMSE = 4.92 µg/cm2, silage maize RMSE = 3.74 µg/cm2) when using the mean reflectance approach. LAI retrieval was more challenging due to the blending of sunlit and shaded pixels present in the UAV data, but worked well at the early developmental stages (sweet maize RMSE = 0.70m2/m2, silage RMSE = 0.61m2/m2 across all dates). CCC retrieval significantly benefited from the pixel-based approach compared to the mean reflectance approach (RMSEs decreased from 45.6 to 33.1 µg/m2). We argue that high-resolution UAV imagery is well suited for LCC retrieval, as shadows and background soil can be precisely removed, leaving only green plant pixels for the analysis. As for retrieving LAI, it proved to be challenging for two distinct varieties of maize that were characterized by contrasting canopy geometry.

Radiative transfer model inversion using high-resolution hyperspectral airborne imagery - Retrieving maize LAI to access biomass and grain yield.

Mapping crop within-field yield variability provide an essential piece of information for precision agriculture applications. Leaf Area Index (LAI) is an important parameter that describes maize growth, vegetation structure, light absorption and subsequently maize biomass and grain yield (GY). The main goal for this study was to estimate maize biomass and GY through LAI retrieved from hyperspectral aerial images using a PROSAIL model inversion and compare its performance with biomass and GY estimations through simple vegetation index approaches. This study was conducted in two separate maize fields of 12 and 20 ha located in north-west Mexico. Both fields were cultivated with the same hybrid. One field was irrigated by a linear pivot and the other by a furrow irrigation system. Ground LAI data were collected at different crop growth stages followed by maize biomass and GY at the harvesting time. Through a weekly/biweekly airborne flight campaign, a total of 19 mosaics were acquired between both fields with a micro-hyperspectral Vis-NIR imaging sensor ranging from 400 to 850 nanometres (nm) at different crop growth stages. The PROSAIL model was calibrated and validated for retrieving maize LAI by simulating maize canopy spectral reflectance based on crop-specific parameters. The model was used to retrieve LAI from both fields and to subsequently estimate maize biomass and GY. Additionally, different vegetation indices were calculated from the aerial images to also estimate maize yield and compare the indices with PROSAIL based estimations. The PROSAIL validation to retrieve LAI from hyperspectral imagery showed a R2 value of 0.5 against ground LAI with RMSE of 0.8 m2/m2. Maize biomass and GY estimation based on NDRE showed the highest accuracies, followed by retrieved LAI, GNDVI and NDVI with R2 value of 0.81, 0.73, 0.73 and 0.65 for biomass, and 0.83, 0.69, 0.73 and 0.62 for GY estimation, respectively. Furthermore, the late vegetative growth stage at V16 was found to be the best stage for maize yield prediction for all studied indices.

Integrating a crop growth model and radiative transfer model to improve estimation of crop traits based on deep learning.

A major challenge for the estimation of crop traits (biophysical variables) from canopy reflectance is the creation of a high-quality training dataset. To address this problem, this research investigated a conceptual framework by integrating a crop growth model with a radiative transfer model to introduce biological constraints in a synthetic training dataset. In addition to the comparison of two datasets without and with biological constraints, we also investigated the effects of observation geometry, retrieval method, and wavelength range on estimation accuracy of four crop traits (leaf area index, leaf chlorophyll content, leaf dry matter, and leaf water content) of wheat. The theoretical analysis demonstrated potential advantages of adding biological constraints in synthetic training datasets as well as the capability of deep learning. Additionally, the predictive models were validated on real unmanned aerial vehicle-based multispectral images collected from wheat plots contrasting in canopy structure. The predictive model trained over a synthetic dataset with biological constraints enabled the prediction of leaf water content from using wavelengths in the visible to near infrared range based on the correlations between crop traits. Our findings presented the potential of the proposed conceptual framework in simultaneously retrieving multiple crop traits from canopy reflectance for applications in precision agriculture and plant breeding.

A model for phenotyping crop fractional vegetation cover using imagery from unmanned aerial vehicles.

Fractional vegetation cover (FVC) is the key trait of interest for characterizing crop growth status in crop breeding and precision management. Accurate quantification of FVC among different breeding lines, cultivars, and growth environments is challenging, especially because of the large spatiotemporal variability in complex field conditions. This study presents an ensemble modeling strategy for phenotyping crop FVC from unmanned aerial vehicle (UAV)-based multispectral images by coupling the PROSAIL model with a gap probability model (PROSAIL-GP). Seven field experiments for four main crops were conducted, and canopy images were acquired using a UAV platform equipped with RGB and multispectral cameras. The PROSAIL-GP model successfully retrieved FVC in oilseed rape (Brassica napus L.) with coefficient of determination, root mean square error (RMSE), and relative RMSE (rRMSE) of 0.79, 0.09, and 18%, respectively. The robustness of the proposed method was further examined in rice (Oryza sativa L.), wheat (Triticum aestivum L.), and cotton (Gossypium hirsutum L.), and a high accuracy of FVC retrieval was obtained, with rRMSEs of 12%, 6%, and 6%, respectively. Our findings suggest that the proposed method can efficiently retrieve crop FVC from UAV images at a high spatiotemporal domain, which should be a promising tool for precision crop breeding.

Analyzing the Effects of Hyperspectral ZhuHai-1 Band Combinations on LAI Estimation Based on the PROSAIL Model.

Leaf area index (LAI) is a key biophysical variable to characterize vegetation canopy. Accurate and quantitative LAI estimation is significant for monitoring vegetation growth status. ZhuHai-1 (ZH-1), which is a commercial remote sensing micro-nano satellite, provides a possibility for quantitative detection of vegetation with high spatial and spectral resolution. However, the band characteristics of ZH-1 are closely related to the accuracy of vegetation monitoring. In this study, a simulation dataset containing 32 bands of ZH-1 was generated by using the PROSAIL model, which was used to analyze the performance of 32 bands for LAI estimation by using the hybrid inversion method. Meanwhile, the effect of different band combinations on LAI estimation was discussed based on sensitivity analysis and the correlation between bands. Then, the optimal band combination from ZH-1 hyperspectral satellite data for LAI estimation was obtained. LAI estimation was performed based on the selected optimal band combination of ZH-1 satellite images in Xiantao city, Hubei province, and compared with the Sentinel-2 normalized difference vegetation index (NDVI) values and LAI product. The results demonstrated that the obtained LAI map based on the optimal band combination of ZH-1 was generally consistent with the overall distribution of Sentinel-2 NDVI and the LAI product, but had a moderate correlation with Sentinel-2 LAI (R = 0.60), which may not favorably indicate the validity of indirect validation. However, the method of this study on the analysis of hyperspectral data bands has application potential to provide a reference for selecting appropriate bands of hyperspectral satellite data to estimate LAI and improve the application of hyperspectral data such as ZH-1 in vegetation monitoring.

Assessing Non-Photosynthetic Cropland Biomass from Spaceborne Hyperspectral Imagery.

Non-photosynthetic vegetation (NPV) biomass has been identified as a priority variable for upcoming spaceborne imaging spectroscopy missions, calling for a quantitative estimation of lignocellulosic plant material as opposed to the sole indication of surface coverage. Therefore, we propose a hybrid model for the retrieval of non-photosynthetic cropland biomass. The workflow included coupling the leaf optical model PROSPECT-PRO with the canopy reflectance model 4SAIL, which allowed us to simulate NPV biomass from carbon-based constituents (CBC) and leaf area index (LAI). PROSAIL-PRO provided a training database for a Gaussian process regression (GPR) algorithm, simulating a wide range of non-photosynthetic vegetation states. Active learning was employed to reduce and optimize the training data set. In addition, we applied spectral dimensionality reduction to condense essential information of non-photosynthetic signals. The resulting NPV-GPR model was successfully validated against soybean field data with normalized root mean square error (nRMSE) of 13.4% and a coefficient of determination (R2) of 0.85. To demonstrate mapping capability, the NPV-GPR model was tested on a PRISMA hyperspectral image acquired over agricultural areas in the North of Munich, Germany. Reliable estimates were mainly achieved over senescent vegetation areas as suggested by model uncertainties. The proposed workflow is the first step towards the quantification of non-photosynthetic cropland biomass as a next-generation product from near-term operational missions, such as CHIME.

Estimation of Multi-Species Leaf Area Index Based on Chinese GF-1 Satellite Data Using Look-Up Table and Gaussian Process Regression Methods.

Leaf area index (LAI) is an important biophysical parameter, which can be effectively applied in the estimation of vegetation growth status. At present, amounts of studies just focused on the LAI estimation of a single plant type, while plant types are usually mixed rather than single distribution. In this study, the suitability of GF-1 data for multi-species LAI estimation was evaluated by using Gaussian process regression (GPR), and a look-up table (LUT) combined with a PROSAIL radiative transfer model. Then, the performance of the LUT and GPR for multi-species LAI estimation was analyzed in term of 15 different band combinations and 10 published vegetation indices (VIs). Lastly, the effect of the different band combinations and published VIs on the accuracy of LAI estimation was discussed. The results indicated that GF-1 data exhibited a good potential for multi-species LAI retrieval. Then, GPR exhibited better performance than that of LUT for multi-species LAI estimation. What is more, modified soil adjusted vegetation index (MSAVI) was selected based on the GPR algorithm for multi-species LAI estimation with a lower root mean squared error (RMSE = 0.6448 m2/m2) compared to other band combinations and VIs. Then, this study can provide guidance for multi-species LAI estimation.

Assimilating spatiotemporal MODIS LAI data with a particle filter algorithm for improving carbon cycle simulations for bamboo forest ecosystems.

Bamboo forests are an important part of the forest ecosystem, which has strong carbon sequestration potential and plays an important role in the global carbon cycle. As a key parameter for simulating the carbon cycle using forest ecosystem models, the quality of leaf area index (LAI) data has a direct influence on the accuracy of modelling results. Here, we used the particle filter (PF) algorithm and PROSAIL model to assimilate MODIS LAI products, which were then used to drive a boreal ecosystem productivity simulator model to simulate the bamboo forest carbon cycle. The results showed that the relationship between the assimilated and observed LAI values was very significant, with an R2 of 0.95 and an RMSE of 0.28, greatly improving the precision of MODIS LAI products. The R2 values for the gross primary productivity (GPP), net ecosystem exchange (NEE), and total ecosystem respiration (TER) simulated by the assimilated LAI values and observed carbon fluxes were 0.65, 0.45 and 0.70, respectively, and the RMSE values were 1.10 g C m-2 day-1, 1.00 g C m-2 day-1 and 0.35 g C m-2 day-1, respectively. Compared with the results of the carbon cycle simulated by non-assimilated LAI, the R2 values of the GPP, NEE and TER values that were simulated by assimilated LAI increased by 27.5%, 45.2% and 6.1%, and the RMSE values decreased by 29.9%, 23.7% and 22.2%, respectively. Therefore, coupling the PF and PROSAIL models can greatly improve the simulation precision for the large-scale bamboo forest carbon cycle. This study laid the foundation for simulating the carbon cycle over a large-scale bamboo forest based on low-resolution data in the future.

Quantifying the Robustness of Vegetation Indices through Global Sensitivity Analysis of Homogeneous and Forest Leaf-Canopy Radiative Transfer Models.

Vegetation indices (VIs) are widely used in optical remote sensing to estimate biophysical variables of vegetated surfaces. With the advent of spectroscopy technology, spectral bands can be combined in numerous ways to extract the desired information. This resulted in a plethora of proposed indices, designed for a diversity of applications and research purposes. However, it is not always clear whether they are sensitive to the variable of interest while at the same time, responding insensitive to confounding factors. Hence, to be able to quantify the robustness of VIs, a systematic evaluation is needed, thereby introducing a widest possible variety of biochemical and structural heterogeneity. Such exercise can be achieved with coupled leaf and canopy radiative transfer models (RTMs), whereby input variables can virtually simulate any vegetation scenario. With the intention of evaluating multiple VIs in an efficient way, this led us to the development of a global sensitivity analysis (GSA) toolbox dedicated to the analysis of VIs on their sensitivity towards RTM input variables. We identified VIs that are designed to be sensitive towards leaf chlorophyll content (LCC), leaf water content (LWC) and leaf area index (LAI) for common sensors of terrestrial Earth observation satellites: Landsat 8, MODIS, Sentinel-2, Sentinel-3 and the upcoming imaging spectrometer mission EnMAP. The coupled RTMs PROSAIL and PROINFORM were used for simulations of homogeneous and forest canopies respectively. GSA total sensitivity results suggest that LCC-sensitive indices respond most robust: for the great majority of scenarios, chlorophyll a + b content (Cab) drives between 75% and 82% of the indices' variability. LWC-sensitive indices were most affected by confounding variables such as Cab and LAI, although the equivalent water thickness (Cw) can drive between 25% and 50% of the indices' variability. Conversely, the majority of LAI-sensitive indices are not only sensitive to LAI but rather to a mixture of structural and biochemical variables.

Global Sensitivity Analysis of Leaf-Canopy-Atmosphere RTMs: Implications for Biophysical Variables Retrieval from Top-of-Atmosphere Radiance Data.

Knowledge of key variables driving the top of the atmosphere (TOA) radiance over a vegetated surface is an important step to derive biophysical variables from TOA radiance data, e.g., as observed by an optical satellite. Coupled leaf-canopy-atmosphere Radiative Transfer Models (RTMs) allow linking vegetation variables directly to the at-sensor TOA radiance measured. Global Sensitivity Analysis (GSA) of RTMs enables the computation of the total contribution of each input variable to the output variance. We determined the impacts of the leaf-canopy-atmosphere variables into TOA radiance using the GSA to gain insights into retrievable variables. The leaf and canopy RTM PROSAIL was coupled with the atmospheric RTM MODTRAN5. Because of MODTRAN's computational burden and GSA's demand for many simulations, we first developed a surrogate statistical learning model, i.e., an emulator, that allows approximating RTM outputs through a machine learning algorithm with low computation time. A Gaussian process regression (GPR) emulator was used to reproduce lookup tables of TOA radiance as a function of 12 input variables with relative errors of 2.4%. GSA total sensitivity results quantified the driving variables of emulated TOA radiance along the 400-2500 nm spectral range at 15 cm-1 (between 0.3-9 nm); overall, the vegetation variables play a more dominant role than atmospheric variables. This suggests the possibility to retrieve biophysical variables directly from at-sensor TOA radiance data. Particularly promising are leaf chlorophyll content, leaf water thickness and leaf area index, as these variables are the most important drivers in governing TOA radiance outside the water absorption regions. A software framework was developed to facilitate the development of retrieval models from at-sensor TOA radiance data. As a proof of concept, maps of these biophysical variables have been generated for both TOA (L1C) and bottom-of-atmosphere (L2A) Sentinel-2 data by means of a hybrid retrieval scheme, i.e., training GPR retrieval algorithms using the RTM simulations. Obtained maps from L1C vs L2A data are consistent, suggesting that vegetation properties can be directly retrieved from TOA radiance data given a cloud-free sky, thus without the need of an atmospheric correction.

Retrieval of Winter Wheat Leaf Area Index from Chinese GF-1 Satellite Data Using the PROSAIL Model.

Leaf area index (LAI) is one of the key biophysical parameters in crop structure. The accurate quantitative estimation of crop LAI is essential to verify crop growth and health. The PROSAIL radiative transfer model (RTM) is one of the most established methods for estimating crop LAI. In this study, a look-up table (LUT) based on the PROSAIL RTM was first used to estimate winter wheat LAI from GF-1 data, which accounted for some available prior knowledge relating to the distribution of winter wheat characteristics. Next, the effects of 15 LAI-LUT strategies with reflectance bands and 10 LAI-LUT strategies with vegetation indexes on the accuracy of the winter wheat LAI retrieval with different phenological stages were evaluated against in situ LAI measurements. The results showed that the LUT strategies of LAI-GNDVI were optimal and had the highest accuracy with a root mean squared error (RMSE) value of 0.34, and a coefficient of determination (R²) of 0.61 during the elongation stages, and the LUT strategies of LAI-Green were optimal with a RMSE of 0.74, and R² of 0.20 during the grain-filling stages. The results demonstrated that the PROSAIL RTM had great potential in winter wheat LAI inversion with GF-1 satellite data and the performance could be improved by selecting the appropriate LUT inversion strategies in different growth periods.

[Tasseled cap triangle (TCT)-leaf area index (LAI)model of rice fields based on PROSAIL model and its application]. / 基于PROSAIL模型的水稻田缨帽三角-å¶é¢ç§¯æŒ‡æ•°æ¨¡åž‹åŠå ¶åº”ç”¨.

The tasseled cap triangle (TCT)-leaf area index (LAI) isoline is a model that reflects the distribution of LAI isoline in the spectral space constituted by reflectance of red and near-infrared (NIR) bands, and the LAI retrieval model developed on the basis of this is more accurate than the commonly used statistical relationship models. This study used ground-based measurements of the rice field, validated the applicability of PROSAIL model in simulating canopy reflectance of rice field, and calibrated the input parameters of the model. The ranges of values of PROSAIL input parameters for simulating rice canopy reflectance were determined. Based on this, the TCT-LAI isoline model of rice field was established, and a look-up table (LUT) required in remote sensing retrieval of LAI was developed. Then, the LUT was used for Landsat 8 and WorldView 3 data to retrieve LAI of rice field, respectively. The results showed that the LAI retrieved using the LUT developed from TCT-LAI isoline model had a good linear relationship with the measured LAI R2=0.76, RMSE=0.47. Compared with the LAI retrieved from Landsat 8, LAI values retrieved from WorldView 3 va-ried with wider range, and data distribution was more scattered. Resampling the Landsat 8 and WorldView 3 reflectance data to 1 km to retrieve LAI, the result of MODIS LAI product was significantly underestimated compared to that of retrieved LAI.