Spatial resolution enhancement is a pre-requisite for integrating unmanned aerial vehicle (UAV) datasets with the data from other sources. However, the mobility of UAV platforms, along with radiometric and atmospheric distortions, makes the task difficult. In this paper, various convolutional neural network (CNN) architectures are explored for resolving the issues related to sub-pixel classification and super-resolution of drone-derived datasets. The main contributions of this work are: 1) network-inversion based architectures for super-resolution and sub-pixel mapping of drone-derived images taking into account their spectral-spatial characteristics and the distortions prevalent in them 2) a feature-guided transformation for regularizing the inversion problem 3) loss functions for improving the spectral fidelity and inter-label compatibility of coarser to finer-scale mapping 4) use of multi-size kernel units for avoiding over-fitting. The proposed approach is the first of its kind in using neural network inversion for super-resolution and sub-pixel mapping. Experiments indicate that the proposed super-resolution approach gives better results in comparison with the sparse-code based approaches which generally result in corrupted dictionaries and sparse codes for multispectral aerial images. Also, the proposed use of neural network inversion, for projecting spatial affinities to sub-pixel maps, facilitates the consideration of coarser-scale texture and color information in modeling the finer-scale spatial-correlation. The simultaneous consideration of spectral bands, as proposed in this study, gives better super-resolution results when compared to the individual band enhancements. The proposed use of different data-augmentation strategies, for emulating the distortions, improves the generalization capability of the framework. Sensitivity of the proposed super-resolution and sub-pixel mapping frameworks with regard to the network parameters is thoroughly analyzed. The experiments over various standard datasets as well as those collected from known locations indicate that the proposed frameworks perform better when compared to the prominent published approaches. © 2018 Elsevier Ltd

There is an increasing interest in using hyperspectral data for phenotyping and crop management while overcoming the challenge of changing atmospheric conditions. The Piccolo dual field-of-view system collects up- and downwelling radiation nearly simultaneously with one spectrometer. Such systems offer great promise for crop monitoring under highly variable atmospheric conditions. Here, the system’s utility from a tractor-mounted boom was demonstrated for a case study of estimating soybean plant populations in early vegetative stages. The Piccolo system is described and its performance under changing sky conditions are assessed for two replicates of the same experiment. Plant population assessment was estimated by partial least squares regression (PLSR) resulting in stable estimations by models calibrated and validated under sunny and cloudy or cloudy and sunny conditions, respectively. We conclude that the Piccolo system is effective for data collection under variable atmospheric conditions, and we show its feasibility of operation for precision agriculture research and potential commercial applications. © 2019, MDPI AG. All rights reserved.

Leaves of the spiny winter annual Silybum marianum express white patches (variegation) that can cover significant surface areas, the outcome of air spaces formed between the epidermis and the green chlorenchyma. We asked: (1) what characterizes the white patches in S. marianum and what differs them from green patches? (2) Do white patches differ from green patches in photosynthetic efficiency under lower temperatures? We predicted that the air spaces in white patches have physiological benefits, elevating photosynthetic rates under low temperatures. To test our hypotheses we used both a variegated wild type and entirely green mutants. We grew the plants under moderate temperatures (20°C/10°C d/n) and compared them to plants grown under lower temperatures (15°C/5°C d/n). The developed plants were exposed to different temperatures for 1 h and their photosynthetic activity was measured. In addition, we compared in green vs. white patches, the reflectance spectra, patch structure, chlorophyll and dehydrin content, stomatal structure, plant growth, and leaf temperature. White patches were not significantly different from green patches in their biochemistry and photosynthesis. However, under lower temperatures, variegated wild-type leaves were significantly warmer than all-green mutants – possible explanations for that are discussed These findings support our hypothesis, that white variegation of S. marianum leaves has a physiological role, elevating leaf temperature during cold winter days. © 2019 Shelef, Summerfield, Lev-Yadun, Villamarin-Cortez, Sadeh, Herrmann and Rachmilevitch.

Pre-visual detection of crop disease is critical for food security. Field-based spectroscopic remote sensing offers a method to enable timely detection, but still requires appropriate instrumentation and testing. Soybean plants were spectrally measured throughout a growing season to assess the capacity of leaf and canopy level spectral measurements to detect non-visual foliage symptoms induced by Fusarium virguliforme (Fv, which causes sudden death syndrome). Canopy reflectance measurements were made using the Piccolo Doppio dual field-of-view, two-spectrometer (400 to 1630 nm) system on a tractor. Leaf level measurements were obtained, in different plots, using a handheld spectrometer (400 to 2500 nm). Partial least squares discriminant analysis (PLSDA) was applied to the spectroscopic data to discriminate between Fv-inoculated and control plants. Canopy and leaf spectral data allowed identification of Fv infection, prior to visual symptoms, with classification accuracy of 88% and 91% for calibration, 79% and 87% for cross-validation, and 82% and 92% for validation, respectively. Differences in wavelengths important to prediction by canopy vs. leaf data confirm that there are different bases for accurate predictions among methods. Partial least square regression (PLSR) was used on a late-stage canopy level data to predict soybean seed yield, with calibration, cross-validation and validation R2 values 0.71, 0.59 and 0.62 (p < 0.01), respectively, and validation root mean square error of 0.31 t·ha−1. Spectral data from the tractor mounted system are thus sensitive to the expression of Fv root infection at canopy scale prior to canopy symptoms, suggesting such systems may be effective for precision agricultural research and management.

Abstract Land use changes are one of the most important factors causing environmental transformations and species diversity alterations. The aim of the current study was to develop a geoinformatics-based framework to quantify alpha and beta diversity indices in two sites in Israel with different land uses, i.e., an agricultural system of fruit orchards, an afforestation system of planted groves, and an unmanaged system of groves. The framework comprises four scaling steps: (1) classification of a tree species distribution (SD) map using imaging spectroscopy (IS) at a pixel size of 1 m; (2) estimation of local species richness by calculating the alpha diversity index for 30-m grid cells; (3) calculation of beta diversity for different land use categories and sub-categories at different sizes; and (4) calculation of the beta diversity difference between the two sites. The SD was classified based on a hyperspectral image with 448 bands within the 380–2500 nm spectral range and a spatial resolution of 1 m. Twenty-three tree species were classified with high overall accuracy values of 82.57% and 86.93% for the two sites. Significantly high values of the alpha index characterize the unmanaged land use, and the lowest values were calculated for the agricultural land use. In addition, high values of alpha indices were found at the borders between the polygons related to the “edge-effect” phenomenon, whereas low alpha indices were found in areas with high invasion species rates. The beta index value, calculated for 58 polygons, was significantly lower in the agricultural land use. The suggested framework of this study succeeded in quantifying land use effects on tree species distribution, evenness, and richness. IS and spatial statistics techniques offer an opportunity to study woody plant species variation with a multiscale approach that is useful for managing land use, especially under increasing environmental changes.

The two-spotted spider mite (Tetranychus urticae Koch; TSSM) feeds on the under-surface of leaves, piercing the chloroplast-containing cells and affecting pigments as well as leaf structure. This damage could be spectrally detectable in the visible and near-infrared spectral regions. The aim was to spectrally explore the ability to assess TSSM damage levels in greenhouse-grown pepper (Capsicum annuum) and bean (Phaseolus vulgaris) leaves. Several vegetation indices (VIs) provided the ability to classify early TSSM damage using a one-way analysis of variance. Hyperspectral (400–1000 nm) and multispectral (five common bands) data were analysed and cross-validated independently by partial least squares-discriminant analysis models. These analyses resulted in 100% and 95% success in identifying early damage with hyperspectral data reflected from pepper and bean leaves, respectively, and in 92% with multispectral data reflected from pepper leaves. Although the TSSM activity occurred on the underside of leaves their damage can be spectrally detected by reflected data from the upper side. Early TSSM damage identification to greenhouse pepper and bean leaves, that their sole damage was by TSSM, can be obtained by VIs, hyperspectral data, and multispectral data. This study shows that by using sub leaf spatial resolution early damage by TSSM can be spectrally detected. It can be potentially applied for greenhouses as well as fields as an early detection method for TSSM management.