A technique is presented for detecting vegetation crop nutrient stress from hyperspectral data. Experiments are conducted on peach trees. It is shown that nutrient deficiencies that caused stress could an be detected reliably on hyperspectral spectra. During an extensive field campaign, foliar and crown reflectance has been measured with a portable field spectroradiometer. Airborne hyperspectral imagery is acquired over the orchard with the AHS hyperspectral sensor. The multi-level approach (leaf level and top of canopy) enabled the assessment of vegetation indices and their relationship with pigment concentration at both leaf and canopy levels, showing the potential and limitations of hyperspectral remote sensing on the different levels. Stress on the peach orchard is was treated with iron chelates to recover from iron chlorosis conditions. Blocks of trees treated with iron chelates created a dynamic range of chlorophyll concentration as measured in leaves. A relationship is obtained between the measured spectra and estimated biochemical parameters via inversion of a linked directional homogeneous canopy reflectance model (ACRM) and the PROSPECT leaf model. Numerical model inversion was conducted by minimizing the difference between the measured reflectance samples and modeled values. An improved optimization method is presented. Results are compared with a simple linear regression analysis, linking chlorophyll to the reflectance measured at the leaf level and Top of Canopy (TOC). Optimal band regions and bandwidths are analyzed.
Early detection of biotic and abiotic stresses and subsequent steering of agricultural systems using hyperspectral sensors potentially could contribute to the pro-active treatment of production-limiting factors. Venturia inaequalis (apple scab) is an important biotic factor that can reduce yield in apple orchards. Previous hyperspectral research focused on (i) determining if Venturia inaequalis leaf infections could be differentiated from healthy leaves and (ii) investigating at which developmental stage Venturia inaequalis infection could be detected. Logistical regression and partial least squares discriminant analysis were used to select the hyperspectral bands that best define differences among treatments. It was clear that hyperspectral data provide the contiguous, high spectral resolution data that are needed to detect subtle changes in reflectance values between healthy and stressed vegetation. The research was extended to include tree-based modeling as an alternative classification method. Results suggested that good predictability could be achieved when classifying infected plants based on this supervised classification technique. It was concluded that the spectral domain around 1600 nm was best suited to discriminate between infected and non-infected leaves immediately after infection, while the visible spectral region became more important at a well-developed infection stage. Research was focused on young leaves, because of the decreased incidence of infection in older leaves, the so-called 'ontogenic resistance'. Additional research was performed to gain a better understanding of the processes occurring during the first days after leaf unfolding and to evaluate the natural spectral variability among leaves. An undisturbed 20-day growth profile was examined to assess variations in the reflectance spectra due to physiological changes at the different growth stages of the leaves. Results suggested that an accurate distinction could be made between different leaf developmental stages using the 570 nm, 1940 nm, and 1460 nm wavelengths, and the red edge inflection point. Based on these results and the outcome of some existing chlorophyll indices, it was concluded that the chlorophyll content in leaves increased remarkably during the first 20 days after unfolding.
This paper studies the detection of vegetation stress in orchards via remote sensing. During previous research, it was shown that stress can be detected reliably on hyperspectral reflectances of the fresh leaves, using a generic wavelet based hyperspectral classification. In this work, we demonstrate the capability to detect stress from airborne/spaceborne hyperspectral sensors by upscaling the leaf reflectances to top of atmosphere (TOA) radiances. Several data sets are generated, measuring the foliar reflectance with a portable field spectroradiometer, covering different time periods, fruit variants and stress types. We concentrated on the Jonagold and Golden Delicious apple trees, induced with mildew and nitrogen deficiency. First, a directional homogeneous canopy reflectance model (ACRM) is applied on these data sets for simulating top of canopy (TOC) spectra. Then, the TOC level is further upscaled to TOA, using the atmospheric radiative transfer model MODTRAN4. To simulate hyperspectral imagery acquired with real airborne/spaceborne sensors, the spectrum is further filtered and subsampled to the available resolution. Using these simulated upscaled TOC and TOA spectra in classification, we will demonstrate that there is still a differentiation possible between stresses and non-stressed trees. Furthermore, results show it is possible to train a classifier with simulated TOA data, to make a classification of real hyperspectral imagery over the orchard.