Search

Background Spectral imaging is a key method for high throughput phenotyping that can be related to a large variety of biological parameters. The Normalised Difference Vegetation Index (NDVI), uses specific wavelengths to compare crop health and performance. Increasing the accessibility of spectral imaging systems through the development of small, low cost, and easy to use platforms will generalise its use for precision agriculture. We describe a method for using a dual camera system connected to a Raspberry Pi to produce NDVI imagery, referred to as NDVIpi. Spectral reference targets were used to calibrate images into values of reflectance, that are then used to calculated NDVI with improved accuracy compared with systems that use single references/standards. Results NDVIpi imagery showed strong performance against standard spectrometry, as an accurate measurement of leaf NDVI. The NDVIpi was also compared to a relatively more expensive commercial camera (Micasense RedEdge), with both cameras having a comparable performance in measuring NDVI. There were differences between the NDVI values of the NDVIpi and the RedEdge, which could be attributed to the measurement of different wavelengths for use in the NDVI calculation by each camera. Subsequently, the wavelengths used by the NDVIpi show greater sensitivity to changes in chlorophyll content than the RedEdge. Conclusion We present a methodology for a Raspberry Pi based NDVI imaging system that utilizes low cost, off-the-shelf components, and a robust multi-reference calibration protocols that provides accurate NDVI measurements. When compared with a commercial system, comparable NDVI values were obtained, despite the fact that our system was a fraction of the cost. Our results also highlight the importance of the choice of red wavelengths in the calculation of NDVI, which resulted in differences in sensitivity between camera systems.

Tomato is an important commercial product which is perishable by nature and highly susceptible to fungal incidence once it is harvested. Not all tomatoes are equally vulnerable to pathogenic fungi, and an early detection of the vulnerable ones can help in taking timely preventive actions, ranging from isolating tomato batches to adjusting storage conditions, but also in making right business decisions like dynamic pricing based on quality or better shelf life estimate. More importantly, early detection of vulnerable produce can help in taking timely actions to minimize potential post-harvest losses. This paper investigates Near-infrared (NIR) hyperspectral imaging (1000–1700 nm) and machine learning to build models to automatically predict the susceptibility of sepals of recently harvested tomatoes to future fungal infections. Hyperspectral images of newly harvested tomatoes (cultivar Brioso) from 5 different growers were acquired before the onset of any visible fungal infection. After imaging, the tomatoes were placed under controlled conditions suited for fungal germination and growth for a 4-day period, and then imaged using normal color cameras. All sepals in the color images were ranked for fungal severity using crowdsourcing, and the final severity of each sepal was fused using principal component analysis. A novel hyperspectral data processing pipeline is presented which was used to automatically segment the tomato sepals from spectral images with multiple tomatoes connected via a truss. The key modelling question addressed in this research is whether there is a correlation between the hyperspectral data captured at harvest and the fungal infection observed 4 days later. Using 10-fold and group k-fold cross-validation, XG-Boost and Random Forest based regression models were trained on the features derived from the hyperspectral data corresponding to each sepal in the training set and tested on hold out test set. The best model found a Pearson correlation of 0.837, showing that there is strong linear correlation between the NIR spectra and the future fungal severity of the sepal. The sepal specific predictions were aggregated to predict the susceptibility of individual tomatoes, and a correlation of 0.92 was found. Besides modelling, focus is also on model interpretation, particularly to understand which spectral features are most relevant to model prediction. Two approaches to model interpretation were explored, feature importance and SHAP (SHapley Additive exPlanations), resulting in similar conclusions that the NIR range between 1390–1420 nm contributes most to the model’s final decision.

LED lighting has emerged as alternative to the current HPS standard in greenhouse production. However little is known about the impact on fruit quality under the different light spectra. We grew a biparental tomato RIL population between September 2019 and January 2020 under two commercial greenhouse supplemental lighting conditions, i.e. HPS, and 95% red/ 5% blue- LED, of about 220 µmol m− 2 s− 1 at maximum canopy height for 16h per day. Differences in Brix and blossom-end rot (BER) between the two light conditions were observed and we studied the genetic influences on those traits, separating genetics located on chromosomes from genetics located in plastids. The Brix value was on average 11% lower under LED than under HPS supplemental lighting. A LED-light specific QTL for Brix was identified on chromosome 6. This QTL can be of interest for breeding for tomato varieties cultivated under LED supplemental lighting. A Brix-QTL on chromosome 2 was found for both light conditions. In our study fewer plants developed BER under LED supplemental lighting than under HPS. We identified a novel genetic locus on chromosome 11 for the incidence of BER that lead to a difference in about 20% of fruits with BER. This genetic component was independent of the light.

Background There is little information on the effect of nutrient solutions composition on Arabidopsis growth. Therefore, we compared growth performance of Arabidopsis thaliana (Col-0) grown on the most commonly used nutrient solutions in deep water culture: Hoagland and Arnon, Murashige and Skoog, Tocquin, Hermans, and Conn. In addition to these nutrient solution composition experiments, we established Arabidopsis growth response curves for nutrient solution concentration and salt stress (NaCl). Results Arabidopsis rosette fresh and dry weight showed an approximate linear decline with NaCl dose in deep water culture, i.e. 9% reduction relative to control per unit of electrical conductivity (EC in dS m−1, for scale comprehension 1 dS m−1 equals ~ 10 mM NaCl). The Tocquin, ½Hoagland and Conn nutrient solutions had equal and optimal growth performance. Optimal nutrient solution concentration for Tocquin and Hoagland was 0.8 to 0.9 dS m−1. Close to the EC of ½Hoagland (1.1 dS m−1), which is frequently used in Arabidopsis research. Conn solution showed optimal growth at much higher EC (2 dS m−1) indicating that it is a balanced nutrient solution that matches the needs of Arabidopsis. Full Murashige and Skoog solution (5.9 dS m−1) was lethal and diluted solutions (EC of 1.6 and 1.1 dS m−1) caused stress symptoms and severe growth retardation at later developmental stages. Conclusions Arabidopsis thaliana (Col-0) plants grown in deep water culture showed a sixfold growth difference when commonly used nutrient solutions were compared. Murashige and Skoog solution should not be used as nutrient solution in deep water culture. Conn, Tocquin and ½Hoagland are balanced nutrient solutions which result in optimal Arabidopsis growth in hydroponic systems.

High relative air humidity (RH >= 85 %) during leaf development disturbs stomatal functioning leading to excessive water loss in conditions of high evaporative demand, resulting in severe reduction in postharvest longevity. In roses, this effect depends on the genotype, opening the possibility for breeding cultivars with more responsive stomata. In this study, we aim at identifying genomic regions associated with the control of water loss following growth at high RH. The F1 generation (108 offspring) and the two parents (P540 and P867) of a tetraploid cut rose population grown at high (85 %) RH were phenotyped for stomatal control to water loss by assessing the relative water content after 4 h of leaflet desiccation (RWC_4 h). The RWC_4 h varied between 7 and 62 % across the 110 studied individuals, with parents P540 and P867 showing 51 and 20 % RWC_4 h, respectively. Based on these data, a quantitative trait locus (QTL) analysis was performed. The impact of the identified QTLs on postharvest longevity of ten selected offspring was further evaluated. Three QTLs were identified: two major [positioned on linkage group 5 of the integrated consensus map (ICM 5) of both parents and on ICM 2 of the parent P867] and one putative minor (mapped to ICM 6 of both parents), explaining 32 % of the variability in the RWC_4 h. Low RWC_4 h was found to be a good proxy for eliminating the offspring with short vase life. This study constitutes a first step toward identifying the most likely regions for genes of interest controlling stomatal functioning in high RH-grown plants.