Assessment of maize yield and phenology by drone-mounted superspectral camera
. Precision Agriculture 2019
. Publisher's VersionAbstract
The capability of unmanned aerial vehicle (UAV) spectral imagery to assess maize yield under full and deficit irrigation is demonstrated by a Tetracam MiniMCA12 11 bands camera. The MiniMCA12 was used to image an experimental field of 19 maize hybrids. Yield prediction models were explored for different maize development stages, with the best model found using maize plant development stage reproductive 2 (R2) for both maize grain yield and ear weight (respective R 2 values of 0.73 and 0.49, and root mean square error of validation (RMSEV) values of 2.07 and 3.41 metric tons per hectare using partial least squares regression (PLS-R) validation models). Models using vegetation indices for inputs rather than superspectral data showed similar R 2 but higher RMSEV values, and produced best results for the R4 development stage. In addition to being able to predict yield, spectral models were able to distinguish between different development stages and irrigation treatments. These abilities potentially allow for yield prediction of maize plants whose development stage and water status are unknown. © 2019, Springer Science+Business Media, LLC, part of Springer Nature.
Convolutional network architectures for super-resolution/sub-pixel mapping of drone-derived images
. Pattern Recognition 2019
, 431-446. Publisher's VersionAbstract
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
Investigating potato late blight physiological differences across potato cultivars with spectroscopy and machine learning
. Plant Science 2019
. Publisher's VersionAbstract
Understanding plant disease resistance is important in the integrated management of Phytophthora infestans, causal agent of potato late blight. Advanced field-based methods of disease detection that can identify infection before the onset of visual symptoms would improve management by greatly reducing disease potential and spread as well as improve both the financial and environmental sustainability of potato farms. In-vivo foliar spectroscopy offers the capacity to rapidly and non-destructively characterize plant physiological status, which can be used to detect the effects of necrotizing pathogens on plant condition prior to the appearance of visual symptoms. Here, we tested differences in spectral response of four potato cultivars, including two cultivars with a shared genotypic background except for a single copy of a resistance gene, to inoculation with Phytophthora infestans clonal lineage US-23 using three statistical approaches: random forest discrimination (RF), partial least squares discrimination analysis (PLS-DA), and normalized difference spectral index (NDSI). We find that cultivar, or plant genotype, has a significant impact on spectral reflectance of plants undergoing P. infestans infection. The spectral response of four potato cultivars to infection by Phytophthora infestans clonal lineage US-23 was highly variable, yet with important shared characteristics that facilitated discrimination. Early disease physiology was found to be variable across cultivars as well using non-destructively derived PLS-regression trait models. This work lays the foundation to better understand host-pathogen interactions across a variety of genotypic backgrounds, and establishes that host genotype has a significant impact on spectral reflectance, and hence on biochemical and physiological traits, of plants undergoing pathogen infection. © 2019 Elsevier B.V.
Spectral data collection by dual field-of-view system under changing atmospheric conditions—a case study of estimating early season soybean populations
. Sensors (Switzerland) 2019
. Publisher's VersionAbstract
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.
Thermal benefits from white variegation of silybum marianum leaves
. Frontiers in Plant Science 2019
. Publisher's VersionAbstract
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.