Laurent Tits

The Potential and Limitations of a Clustering Approach for the Improved Efficiency of Multiple Endmember Spectral Mixture Analysis in Plant Production System Monitoring

Due to the subpixel contribution of background soils and shadows, hyperspectral image interpretation in agricultural management is often constrained. In this paper, the potential of multiple endmember spectral mixture analysis (MESMA) to simultaneously extract the subpixel cover fraction and pure spectral signature of the crop component from a mixed hyperspectral signal is evaluated. Radiative transfer models are used to build lookup tables (LUTs) for both the crop and the soil component, but the extensiveness of the LUTs will decrease the efficiency and operational implementation of MESMA. A clustering procedure is therefore presented, allowing a more efficient use of the LUTs in the MESMA model. The performance of MESMA, using clustered and nonclustered LUTs, to extract the cover fraction and the spectral signature of plant canopies was evaluated using 200 simulated mixtures generated from in situ measured hyperspectral data of soil and citrus canopies. Clustering of the LUT resulted in a more efficient and accurate estimation of the pure subpixel vegetation signal ( rmse = 0.097 stabilizing at 40 iterations) compared to a nonclustered LUT (rmse = 0.11 stabilizing at 200 iterations). The subpixel cover fraction estimations, on the other hand, stabilize for both methods around 100 iterations, with an rmse of 0.15 for both approaches. The clustering of the LUT will thus increase both the efficiency and the accuracy of MESMA for estimating the spectral signature of crops while, on average, maintaining the accuracy for the cover fraction estimates. This will enable a more accurate extraction of plant production parameters, which opens up new opportunities regarding precision farming.

Unmixing-Based Fusion of Hyperspatial and Hyperspectral Airborne Imagery for Early Detection of Vegetation Stress

Many applications require a timely acquisition of high spatial and spectral resolution remote sensing data. This is often not achievable since spaceborne remote sensing instruments face a tradeoff between spatial and spectral resolution, while airborne sensors mounted on a manned aircraft are too expensive to acquire a high temporal resolution. This gap between information needs and data availability inspires research on using Remotely Piloted Aircraft Systems (RPAS) to capture the desired high spectral and spatial information, furthermore providing temporal flexibility. Present hyperspectral imagers on board lightweight RPAS are still rare, due to the operational complexity, sensor weight, and instability. This paper looks into the use of a hyperspectral-hyperspatial fusion technique for an improved biophysical parameter retrieval and physiological assessment in agricultural crops. First, a biophysical parameter extraction study is performed on a simulated citrus orchard. Subsequently, the unmixing-based fusion is applied on a real test case in commercial citrus orchards with discontinuous canopies, in which a more efficient and accurate estimation of water stress is achieved by fusing thermal hyperspatial and hyperspectral (APEX) imagery. Narrowband reflectance indices that have proven their effectiveness as previsual indicators of water stress, such as the Photochemical Reflectance Index (PRI), show a significant increase in tree water-stress detection when applied on the fused dataset compared to the original hyperspectral APEX dataset (R2 = 0.62, p <;0.001 vs. R2 = 0.21, p > 0.1). Maximal R2 values of 0.93 and 0.86 are obtained by a linear relationship between the vegetation index and the resp., water and chlorophyll, parameter content maps.

Spectral Unmixing of Forest Crown Components at Close Range, Airborne and Simulated Sentinel-2 and EnMAP Spectral Imaging Scale

Forest biochemical and biophysical variables and their spatial and temporal distribution are essential inputs to process-orientated ecosystem models. To provide this information, imaging spectroscopy appears to be a promising tool. In this context, the present study investigates the potential of spectral unmixing to derive sub-pixel crown component fractions in a temperate deciduous forest ecosystem. However, the high proportion of foliage in this complex vegetation structure leads to the problem of saturation effects, when applying broadband vegetation indices. This study illustrates that multiple endmember spectral mixture analysis (MESMA) can contribute to overcoming this challenge. Reference

Quantifying Nonlinear Spectral Mixing in Vegetated Areas: Computer Simulation Model Validation and First Results

Our understanding of nonlinear mixing events in vegetated areas is currently hampered by a pertinent lack of well-validated datasets. Most quantification and modeling efforts are, therefore, based on the theoretical assumptions or indirect empirical observations. Here, we performed a quantitative and qualitative evaluation of the accuracy of nonlinear mixing effects as modeled by a fully calibrated virtual orchard model (based on physically based ray-tracer software). For validation, we had available data from an in situ experiment. This experiment comprised in situ measured mixed pixel reflectance spectra, pixel-specific endmember spectra, and subpixel cover fraction distributions, all collected in the same orchard for which the virtual model was calibrated. We took advantage of this unique-coupled dataset to demonstrate that both the nature and the intensity of the nonlinear mixing events observed in the in situ data are realistically modeled by the ray-tracing software. This is an important observation because this implies that our virtual model now provides a solid tool for the detailed study of nonlinear mixing in vegetated areas which could facilitate as such the design, calibration, and validation of different nonlinear mixing modeling approaches. Initial results revealed that the nonlinear mixing is dependent on fractional distribution, soil moisture conditions, and endmember definitions. We could further demonstrate that the bilinear spectral mixture model nicely described nonlinear mixing events but at the same time overestimated reflectances in spectral regions with moderate-to-low nonlinear mixing behavior.

A Comparison of Nonlinear Mixing Models for Vegetated Areas Using Simulated and Real Hyperspectral Data

Spectral unmixing (SU) is a crucial processing step when analyzing hyperspectral data. In such analysis, most of the work in the literature relies on the widely acknowledged linear mixing model to describe the observed pixels. Unfortunately, this model has been shown to be of limited interest for specific scenes, in particular when acquired over vegetated areas. Consequently, in the past few years, several nonlinear mixing models have been introduced to take nonlinear effects into account while performing SU. These models have been proposed empirically, however, without any thorough validation. In this paper, the authors take advantage of two sets of real and physical-based simulated data to validate the accuracy of various nonlinear models in vegetated areas. These physics-based models, and their corresponding unmixing algorithms, are evaluated with respect to their ability of fitting the measured spectra and providing an accurate estimation of the abundance coefficients, considered as the spatial distribution of the materials in each pixel.

A Dynamic Unmixing Framework for Plant Production System Monitoring

Hyperspectral remote sensing or imaging spectroscopy is an emerging technology in plant production monitoring and management. The continuous reflectance spectra allow for the intensive monitoring of biophysical and biochemical tree characteristics during growth, through for instance the use of vegetation indices. Yet, since most of the pixels in hyperspectral images are mixed, the evaluation of the actual vegetation state on the ground directly from the measured spectra is degraded by the presence of other endmembers, such as soil. Spectral unmixing, then, becomes a necessary processing step to improve the interpretation of vegetation indices. In this sense, an active research direction is based on the use of large collections of pure spectra, called spectral libraries or dictionaries, which model a wide variety of possible states of the endmembers of interest on the ground, i.e., vegetation and soil. Under the linear mixing model (LMM), the observed spectra are assumed to be linear combinations of spectra from the available dictionary. Combinatorial techniques (e.g., MESMA) and sparse regression algorithms (e.g., SUnSAL) are widely used to tackle the unmixing problem in this case. However, both combinatorial and sparse techniques benefit from appropriate library reduction strategies. In this paper, we develop a new efficient method for library reduction (or dictionary pruning), which exploits the fact that hyperspectral data generally lives in a lower-dimensional subspace. Specifically, we present a slight modification of the MUSIC-CSR algorithm, a two-step method which aims first at pruning the dictionary and second at infering high-quality reconstruction of the vegetation spectra on the ground (this application being called signal unmixing in remote sensing), using the pruned dictionary as input to available unmixing methods. Our goal is two-fold: 1) to obtain high-accuracy unmixing output using sparse unmixing, with low-execution time; and 2) to improve MESMA performances in terms of accuracy. Our experiments, which have been conducted in a multi-temporal case study, show that the method achieves these two goals and proposes sparse unmixing as a reliable and robust alternative to the combinatorial methods in plant production monitoring applications. We further demonstrate that the proposed methodology of combining a library pruning approach with spectral unmixing provides a solid framework for the year-round monitoring of plant production systems.

Stem water potential monitoring in pear orchards through Worldview 2 multispectral imagery

Remote sensing can provide good alternatives for traditional in situ water status measurements in orchard crops, such as stem water potential (Ψstem). However, the heterogeneity of these cropping systems causes significant differences with regards to remote sensing products within one orchard and between orchards. In this study, robust spectral indicators of Ψstem were sought after, independent of sensor viewing geometry, orchard architecture and management. To this end, Ψstem was monitored throughout three consecutive growing seasons in (deficit) irrigated and rainfed pear orchards and related to spectral observations of leaves, canopies and WorldView-2 imagery. On a leaf and canopy level, high correlations were observed between the shortwave infrared reflectance and in situ measured Ψstem. Additionally, for canopy measurements, visible and near-infrared wavelengths (R530/R600, R530/R700 and R720/R800) showed significant correlations. Therefore, the Red-edge Normalized Difference Vegetation Index (ReNDVI) was applied on fully sunlit satellite imagery and found strongly related with Ψstem (R 2 = 0.47; RMSE = 0.36 MPa), undoubtedly showing the potential of WorldView-2 to monitor water stress in pear orchards. The relationship between ReNDVI and Ψstem was independent of management, irrigation setup, phenology and environmental conditions. In addition, results showed that this relation was also independent of off-nadir viewing angle and almost independent of viewing geometry, as the correlation decreased after the inclusion of fully shaded scenes.

First results of quantifying nonlinear mixing effects in heterogeneous forests: A modeling approach

Mixed satellite signals are traditionally modeled as linear combinations of the spectral signatures of its constituent components. Although nonlinearity has been shown to be significant for a variety of vegetation types, it is assumed to be negligible for most applications. We aim to assess the validity of the linear modeling assumption by making a quantitative analysis of the nature of multiple scattering effects in mixed forests. The effects of the spectral properties of the different species, structural differences and differences in tree height are evaluated. Virtual forest scenes and simulated hyperspectral satellite data were created through ray-tracing modeling using the Physically Based Ray-Tracer (PBRT) model. Results showed that both structure and the spectral properties influenced the nonlinear mixing behaviour, indicating that nonlinear unmixing models might be needed for forest cover mapping in heterogeneous forests.

Site-Specific Plant Condition Monitoring Through Hyperspectral Alternating Least Squares Unmixing

Alternating least squares (ALS) is a blind source separation method commonly used in chemometrics to simultaneously estimate the absorption spectrum and concentration of different components in a chemical sample. In this study, the transferability of ALS from chemometrics to agricultural remote sensing is evaluated. Due to the subpixel contribution of background components, spectral unmixing has become an indispensable processing step in the spectral analysis of agricultural areas. Yet, traditional unmixing techniques only allow estimating the subpixel cover distribution of different components, but fail to provide an estimate of pure spectral signature of the crop component. This info is, however, highly valuable, as this pure crop signature could be used to monitor the health status of trees. Here, we anticipate that ALS can provide a solution. ALS estimates both the concentration and the absorption spectra of different components in a chemical sample and this can easily be translated into estimating both the subpixel cover fraction and spectral signature of different components in a mixed image pixel. We tested the performance of ALS on binary synthetic mixtures of citrus canopy and soil spectra, as well as on a ray-tracing experiment of a virtual orchard. ALS indeed allowed to simultaneously estimate the subpixel cover distribution (RMSE=0.05), as well as the pure spectral signatures of different endmembers (RRMSE<;0.12), and considerably improved the extraction of biophysical parameters (Δ R2 up to 0.43). Thus, ALS provides a promising new image analysis tool for agricultural remote sensing.

Species-rich semi-natural grasslands have a higher resistance but a lower resilience than intensively managed agricultural grasslands in response to climate anomalies

The stable delivery of ecosystem services provided by grasslands is strongly dependent on the stability of grassland ecosystem functions such as biomass production. Biomass production is in turn strongly affected by the frequency and intensity of climate extremes. The aim of this study is to evaluate to what extent species-poor intensively managed agricultural grasslands can maintain their biomass productivity under climate anomalies, as compared to species-rich, semi-natural grasslands. Our hypothesis is that species richness stabilizes biomass production over time. Biomass production stability was assessed in response to drought and temperature anomalies using 14 years of the Normalized Difference Vegetation Index (NDVI), temperature and drought index time series. More specifically, vegetation resistance (i.e. the ability to withstand the climate anomaly) and resilience (i.e. the recovery rate) were derived using an auto-regressive model with external input variables (ARx). The stability metrics for both grasslands were subsequently compared. We found that semi-natural grasslands exhibited a higher resistance but lower resilience than agricultural grasslands in the Netherlands. Furthermore, the difference in stability between semi-natural and agricultural grasslands was dependent on the physical geography: the most significant differences in resistance were observed in coastal dunes and riverine areas, whereas the differences in resilience were the most significant in coastal dunes and fens. Synthesis and applications. We conclude that semi-natural grasslands show a higher resistance to drought and temperature anomalies compared to agricultural grasslands. These results underline the need to reassess the ways agricultural practices are performed. More specifically, increasing the plant species richness of agricultural grasslands and lowering their mowing and grazing frequency may contribute to buffer their biomass production stability against climate extremes.