Past and Future of Plant Stress Detection: An Overview From Remote Sensing to Positron Emission Tomography

Abstract

Plant stress detection is considered one of the most critical areas for the improvement of crop yield in the compelling worldwide scenario, dictated by both the climate change and the geopolitical consequences of the Covid-19 epidemics. A complicated interconnection of biotic and abiotic stressors affect plant growth, including water, salt, temperature, light exposure, nutrients availability, agrochemicals, air and soil pollutants, pests and diseases. In facing this extended panorama, the technology choice is manifold. On the one hand, quantitative methods, such as metabolomics, provide very sensitive indicators of most of the stressors, with the drawback of a disruptive approach, which prevents follow up and dynamical studies. On the other hand qualitative methods, such as fluorescence, thermography and VIS/NIR reflectance, provide a non-disruptive view of the action of the stressors in plants, even across large fields, with the drawback of a poor accuracy. When looking at the spatial scale, the effect of stress may imply modifications from DNA level (nanometers) up to cell (micrometers), full plant (millimeters to meters), and entire field (kilometers). While quantitative techniques are sensitive to the smallest scales, only qualitative approaches can be used for the larger ones. Emerging technologies from nuclear and medical physics, such as computed tomography, magnetic resonance imaging and positron emission tomography, are expected to bridge the gap of quantitative non-disruptive morphologic and functional measurements at larger scale. In this review we analyze the landscape of the different technologies nowadays available, showing the benefits of each approach in plant stress detection, with a particular focus on the gaps, which will be filled in the nearby future by the emerging nuclear physics approaches to agriculture.

Keywords: fluorescence imaging; metabolomics; plant imaging; plant positron emission tomography; plant stress; remote sensing; spectroscopy; thermal imaging.

Figure 1

A summary of the main techniques for plant stress detection. The stressors and the wavelength used for stress detection in each technique are also shown. Stress manifests itself over a wide length scale ranging from the microscopic cellular to the macroscopic plant and field level. Whole field sensing (VIS/NIR reflectance, Thermography, Fluorescence) is naturally attractive in the agricultural practice, but provides only a qualitative information. At plant level morphological imaging techniques (CT, MRI) provide quantitative high resolution detection of structural damages induced by the stress, but cannot provide any information on the functional basis of the physiological mechanisms of reactions to both biotic and abiotic stressors at cellular level. For this purpose, metabolomics is an essential tool to enhance the results obtained with morphologic imaging techniques, but it is sample disruptive and is not able to provide timely indications to support early interventions both in open-field and controlled conditions. PET is by far the only quantitative functional imaging technique, which provides a time-dynamic non-disruptive information of the modifications of functional mechanisms and transport flows in the vascular system in response to biotic and abiotic stress.

Figure 2

A typical healthy vegetation spectrum (350–2,500 nm); spectral reflectance signature refers to spinach leaves (author's personal and unpublished data). Measurements were taken using full-range hyperspectral ASD FieldSpec 4 Hi-Res (Analytical Spectral Devices Inc., Boulder, CO, USA) spectroradiometer equipped with a contact probe. Red-edge and water bands' absorption sections are highlighted in red and blue, respectively.

Figure 3

Example of CT of a leaf of Epipremnum Aureum. 3D view (A), transverse (B), and longitudinal (C) slices with visible midrib and veins, distribution of the CT values in the leaf expressed in Hounsfield units (D). Two regions can be identified from the analysis of the CT values: −550 <HU< −50 identifies the vascular system (E) and −800 <HU< −550 identifies the mesophyll (F).

Figure 4

Example of a physical model of a leaf of Epipremnum Aureum: simulation of a positron escape in GEANT4 (A), positron annihilation probability (B), and positron contamination probability (C).

Figure 5

Example of a [18]F-FDG PET of a leaf of Epipremnum Aureum: 3-dimensional view of the corrected tracer concentration 10 min (A), 70 min (B), 130 min (C), and 190 min (D) after the beginning of the scan. The average standard uptake value of the measured (empty markers) and corrected tracer distribution (filled markers) in the two ROIs identified in (A) are shown in (E) as a function of the acquisition time.