Deep learning-based prediction of plant height and crown area of vegetable crops using LiDAR point cloud.

Remote sensing has been increasingly used in precision agriculture. Buoyed by the developments in the miniaturization of sensors and platforms, contemporary remote sensing offers data at resolutions finer enough to respond to within-farm variations. LiDAR point cloud, offers features amenable to modelling structural parameters of crops. Early prediction of crop growth parameters helps farmers and other stakeholders dynamically manage farming activities. The objective of this work is the development and application of a deep learning framework to predict plant-level crop height and crown area at different growth stages for vegetable crops. LiDAR point clouds were acquired using a terrestrial laser scanner on five dates during the growth cycles of tomato, eggplant and cabbage on the experimental research farms of the University of Agricultural Sciences, Bengaluru, India. We implemented a hybrid deep learning framework combining distinct features of long-term short memory (LSTM) and Gated Recurrent Unit (GRU) for the predictions of plant height and crown area. The predictions are validated with reference ground truth measurements. These predictions were validated against ground truth measurements. The findings demonstrate that plant-level structural parameters can be predicted well ahead of crop growth stages with around 80% accuracy. Notably, the LSTM and the GRU models exhibited limitations in capturing variations in structural parameters. Conversely, the hybrid model offered significantly improved predictions, particularly for crown area, with error rates for height prediction ranging from 5 to 12%, with deviations exhibiting a more balanced distribution between overestimation and underestimation This approach effectively captured the inherent temporal growth pattern of the crops, highlighting the potential of deep learning for precision agriculture applications. However, the prediction quality is relatively low at the advanced growth stage, closer to the harvest. In contrast, the prediction quality is stable across the three different crops. The results indicate the presence of a robust relationship between the features of the LiDAR point cloud and the auto-feature map of the deep learning methods adapted for plant-level crop structural characterization. This approach effectively captured the inherent temporal growth pattern of the crops, highlighting the potential of deep learning for precision agriculture applications.

Major quantitative trait locus qLA3.1 is related to tomato leaf angle by regulating cell length at the petiole base.

KEY MESSAGE: qLA3.1, controlling leaf angle in tomato, was fine-mapped to an interval of 4.45 kb on chromosome A03, and one gene encoding auxin response factor was identified as a candidate gene. Leaf angle is a crucial trait in plant architecture that plays an important role in achieving optimal plant structure. However, there are limited reports on gene localization, cloning, and the function of plant architecture in horticultural crops, particularly regarding leaf angle. In this study, we selected 'Z3' with erect leaves and 'Heinz1706' with horizontal leaves as the phenotype and cytological observation. We combined bulked segregant analysis and fine genetic mapping to identify a candidate gene, known as, i.e., qLA3.1, which was related to tomato leaf angle. Through multiple analyses, we found that Solyc03g113410 was the most probably candidate for qLA3.1, which encoded the auxin response factor SlARF11 in tomato and was homologous to OsARF11 related to leaf angle in rice. We discovered that silencing SlARF11 resulted in upright leaves, while plants with over-expressed SlARF11 exhibited horizontal leaves. We also found that cultivars with erect leaves had a mutation from base G to base A. Moreover, quantitative analysis of plants treated with hormones indicated that SlARF11 might participate in cell elongation and the activation of genes related to auxin and brassinosteroid pathways. Transcriptome analysis further validated that SlARF11 may regulate leaf angle through hormone signaling pathways. These data support the idea that the auxin response factor SlARF11 may have an important function in tomato leaf petiole angles.

Idiosyncratic and dose-dependent epistasis drives variation in tomato fruit size.

Epistasis between genes is traditionally studied with mutations that eliminate protein activity, but most natural genetic variation is in cis-regulatory DNA and influences gene expression and function quantitatively. In this study, we used natural and engineered cis-regulatory alleles in a plant stem-cell circuit to systematically evaluate epistatic relationships controlling tomato fruit size. Combining a promoter allelic series with two other loci, we collected over 30,000 phenotypic data points from 46 genotypes to quantify how allele strength transforms epistasis. We revealed a saturating dose-dependent relationship but also allele-specific idiosyncratic interactions, including between alleles driving a step change in fruit size during domestication. Our approach and findings expose an underexplored dimension of epistasis, in which cis-regulatory allelic diversity within gene regulatory networks elicits nonlinear, unpredictable interactions that shape phenotypes.

Genetic basis of the lobedness degree in tomato fruit morphology.

Fruit shape is a key trait in tomato (Solanum lycopersicum L.). Since most studies focused on proximo-distal fruit morphology, we hypothesized that unknown QTLs for medio-lateral direction ones could be found analysing segregating populations where major shape genes are fixed. We examined the diversity of fruit morphology in medio-lateral direction; defined divergent traits in cultivars carrying identical genetic constitution at LC and FAS genes; and identified QTLs for lobedness degree (LD) by a QTL-seq approach. We found that LC and FAS genes were not enough to explain LD variability in a large tomato collection. Then, we derived F2 populations crossing cultivars divergent for LD where LC and FAS were fixed (Yellow Stuffer x Heinz 1439 [F2YSxH] and Voyage x Old Brooks [F2VxOB]). By QTL-seq we identified a QTL for LD on chromosome 8 in both F2, which was validated in F2YSxH by interval mapping accounting for ~ 17% of the variability. Other two QTLs located on chromosomes 6 and 11 with epistasis explained ~ 61% of the variability in the F2VxOB. In conclusion, three novel QTLs with major effect for LD (ld6, ld8, and ld11) were identified through the study of diversity and genetic segregation in intraspecific tomato crosses.

Pheno4D: A spatio-temporal dataset of maize and tomato plant point clouds for phenotyping and advanced plant analysis.

Understanding the growth and development of individual plants is of central importance in modern agriculture, crop breeding, and crop science. To this end, using 3D data for plant analysis has gained attention over the last years. High-resolution point clouds offer the potential to derive a variety of plant traits, such as plant height, biomass, as well as the number and size of relevant plant organs. Periodically scanning the plants even allows for performing spatio-temporal growth analysis. However, highly accurate 3D point clouds from plants recorded at different growth stages are rare, and acquiring this kind of data is costly. Besides, advanced plant analysis methods from machine learning require annotated training data and thus generate intense manual labor before being able to perform an analysis. To address these issues, we present with this dataset paper a multi-temporal dataset featuring high-resolution registered point clouds of maize and tomato plants, which we manually labeled for computer vision tasks, such as for instance segmentation and 3D reconstruction, providing approximately 260 million labeled 3D points. To highlight the usability of the data and to provide baselines for other researchers, we show a variety of applications ranging from point cloud segmentation to non-rigid registration and surface reconstruction. We believe that our dataset will help to develop new algorithms to advance the research for plant phenotyping, 3D reconstruction, non-rigid registration, and deep learning on raw point clouds. The dataset is freely accessible at https://www.ipb.uni-bonn.de/data/pheno4d/.

Effect of the Nanoparticle Exposures on the Tomato Bacterial Wilt Disease Control by Modulating the Rhizosphere Bacterial Community.

Ralstonia Solanacearum is one of the most infectious soil-borne bacterial plant pathogens, causing tomato bacterial wilt (TBW). Nanotechnology is an emerging area of research, particularly the application of nanoparticles (NPs) as nanopesticides to manage plant disease is gaining attention nowadays. However, the interaction between NPs and rhizosphere bacterial communities remains largely elusive. This study indicated that metal NPs (CuO, ZnO, and FeO) reduced the incidence of bacterial wilt to varying degrees and affected the composition and structure of the rhizosphere bacterial community. The results revealed that the application of metal oxide NPs can improve the morphological and physiological parameters of TBW infected tomato plants. Among all, CuONPs amendments significantly increase the Chao1 and Shannon index. In the early stage (the second week), it significantly reduces the relative abundance of pathogens. However, the relative abundance of beneficial Streptomyces bacteria increased significantly, negatively correlated with the relative abundance of pathogenic bacteria. In addition, the nano-treatment group will enrich some potential beneficial bacteria such as species from Sphingomonadaceae, Rhizobiaceae, etc. In general, our research provides evidence and strategies for preventing and controlling soil-borne disease tomato bacterial wilt with metal oxide NPs.

Bulk RNA-Seq analysis to dissect the regulation of stigma position in tomato.

KEY MESSAGE: Transcriptomic analysis of tomato genotypes contrasting for stigma position suggests that stigma insertion occurred by the disruption of a process that finds a parallel in Arabidopsis gynoecium development. Domestication of cultivated tomato (Solanum lycopersicum L.) included the transition from allogamy to autogamy that occurred through the loss of self-incompatibilty and the retraction of the stigma within the antheridial cone. Although the inserted stigma is an established phenotype in modern tomatoes, an exserted stigma is still present in several landraces or vintage varieties. Moreover, exsertion of the stigma is a frequent response to high temperature stress and, being a cause of reduced fertility, a trait of increasing importance. Few QTLs for stigma position have been described and only one of the underlying genes identified. To gain insights on genes involved in stigma position in tomato, a bulk RNA sequencing (RNA-Seq) approach was adopted, using two groups of contrasting genotypes. Phenotypic analysis confirmed the extent and the stability of stigma position in the selected genotypes, whereas they were highly heterogeneous for other reproductive and productive traits. The RNA-Seq analysis yielded 801 differentially expressed genes (DEGs), 566 up-regulated and 235 down-regulated in the genotypes with exserted stigma. Validation by quantitative PCR indicated a high reliability of the RNA-Seq data. Up-regulated DEGs were enriched for genes involved in the cell wall metabolism, lipid transport, auxin response and flavonoid biosynthesis. Down-regulated DEGs were enriched for genes involved in translation. Validation of selected genes on pistil tissue of the 26 single genotypes revealed that differences between bulks could both be due to a general trend of the bulk or to the behaviour of single genotypes. Novel candidate genes potentially involved in the control of stigma position in tomato are discussed.

Morphological and anatomical characteristics of exserted stigma sterility and the location and function of SlLst (Solanum lycopersicum Long styles) gene in tomato.

KEY MESSAGE: Anatomical changes in and hormone roles of the exserted stigma were investigated, and localization and functional analysis of SlLst for the exserted stigma were performed using SLAF-BSA-seq, parental resequencing and overexpression of SlLst in tomato. Tomato accession T431 produces stigmas under relatively high temperatures (> 27 °C, the average temperature in Harbin, China, in June-August), so pollen can rarely reach the stigma properly. This allows the percentage of male sterility exceed 95%, making the use of this accession practical for hybrid seed production. To investigate the mechanism underlying the exserted stigma male sterility, the morphological changes of, anatomical changes of, and comparative endogenous hormone (IAA, ABA, GA3, ZT, SA) changes in flowers during flower development of tomato accessions DL5 and T431 were measured. The location and function of genes controlling exserted stigma sterility were analyzed using super SLAF-BSA-seq, parental resequencing, comparative genomics and the overexpression of SlLst in tomato. The results showed that an increase in cell number mainly caused stigma exsertion. IAA played a major role, while ABA had an opposite effect on stigma exertion. Moreover, 26 candidate genes related to the exserted stigma were found, located on chromosome 12. The Solyc12g027610.1 (SlLst) gene was identified as the key candidate gene by functional analysis. A subcellular localization assay revealed that SlLst is targeted to the nucleus and cell membrane. Phenotypic analysis of SlLst-overexpressing tomato showed that SlLst plays a crucial role during stigma exsertion.

A plant parasite uses light cues to detect differences in host-plant proximity and architecture.

Sunlight filtered by green plant tissue becomes diminished in its ratio of red to far-red wavelengths (R:FR). Some parasitic plants exploit this change by growing towards regions of low R:FR to locate host plants. In principle, variation in R:FR can also convey ecologically relevant information about host proximity or architecture. Here, we demonstrate that the parasitic vine Cuscuta epilinum Weihe (Convolvulaceae) can distinguish fine-scale differences in R:FR associated with differences in the proximity and shape of potential host plants. We conducted dual-choice experiments by placing parasite seedlings between targets, including low R:FR fields manipulated via LED lighting and pairs of model plants exhibiting realistic R and FR reflectance but differing in proximity or shape. Seedlings consistently distinguished between low-R:FR fields of differing intensity. Furthermore, they exhibited preferences for nearer plant models versus identical models placed 4 cm further away and between same-sized models exhibiting shape differences. Our results indicate that parasites can discriminate minute differences in R:FR signatures corresponding to host factors (proximity and shape) that impact seedling survival. This keen sensory ability underpins the parasite's sophisticated foraging behaviour and highlights the broader importance of light cues in plant ecology.

Yellow-fruited phenotype is caused by 573 bp insertion at 5' UTR of YFT1 allele in yft1 mutant tomato.

The yft1 tomato mutant has a yellow-fruited phenotype controlled by a recessive gene of YFT1 allele, which has been shown by map-based cloning to be a homolog of ETHYLENE INSENSITIVE 2 (EIN2). Genetic lesion of YFT1 allele in yft1 is attributed to a 573 bp DNA fragment (IF573) insertion at 1,200 bp downstream of the transcription start site. Transcriptomic analysis revealed that YFT1 lesion resulted in 5,053 differentially expressed genes (DEGs) in yft1 pericarp compared with the M82 wild type cultivar. These were annotated as being involved in ethylene synthesis, chromoplast development, and carotenoid synthesis. The YFT1 lesion caused a reduction in its own transcript levels in yft1 and impaired ethylene emission and signal transduction, delayed chromoplast development and decreased carotenoid accumulation. The molecular mechanism underlying the downregulated YFT1 allele in yft1 was examined at both RNA and DNA levels. The IF573 event appeared to introduce two negative regulatory sequences located at -272 to -173 bp and -172 to -73 bp in the YFT1 allele promoter, causing alterative splicing due to introduction of aberrant splicing sites, and breaking upstream open reading frames (uORF) structure in the 5'-UTR. Those results a new provided insight into molecular regulation of color formation in tomato fruit.

Kinase Partner Protein Plays a Key Role in Controlling the Speed and Shape of Pollen Tube Growth in Tomato.

The rapid and responsive growth of a pollen tube requires delicate coordination of membrane receptor signaling, Rho-of-Plants (ROP) GTPase activity switching, and actin cytoskeleton assembly. The tomato (Solanum lycopersicum) kinase partner protein (KPP), is a ROP guanine nucleotide exchange factor (GEF) that activates ROP GTPases and interacts with the tomato pollen receptor kinases LePRK1 and LePRK2. It remains unclear how KPP relays signals from plasma membrane-localized LePRKs to ROP switches and other cellular machineries to modulate pollen tube growth. Here, we biochemically verified KPP's activity on ROP4 and showed that KPP RNA interference transgenic pollen tubes grew slower while KPP-overexpressing pollen tubes grew faster, suggesting that KPP functions as a rheostat for speed control in LePRK2-mediated pollen tube growth. The N terminus of KPP is required for self-inhibition of its ROPGEF activity, and expression of truncated KPP lacking the N terminus caused pollen tube tip enlargement. The C-terminus of KPP is required for its interaction with LePRK1 and LePRK2, and the expression of a truncated KPP lacking the C-terminus triggered pollen tube bifurcation. Furthermore, coexpression assays showed that self-associated KPP recruited actin-nucleating Actin-Related Protein2/3 (ARP2/3) complexes to the tip membrane. Interfering with ARP2/3 activity reduced the pollen tube abnormalities caused by overexpressing KPP fragments. In conclusion, KPP plays a key role in pollen tube speed and shape control by recruiting the branched actin nucleator ARP2/3 complex and an actin bundler to the membrane-localized receptors LePRK1 and LePRK2.

Transpiration from Tomato Fruit Occurs Primarily via Trichome-Associated Transcuticular Polar Pores.

Nonstomatal water loss by transpiration through the hydrophobic cuticle is ubiquitous in land plants, but the pathways along which this occurs have not been identified. Tomato (Solanum lycopersicum) provides an excellent system in which to study this phenomenon, as its fruit are astomatous and a major target for desiccation resistance to enhance shelf life. We screened a tomato core collection of 398 accessions from around the world and selected seven cultivars that collectively exhibited the lowest and highest degrees of transpirational water loss for a more detailed study. The transpirational differences between these lines reflected the permeances of their isolated cuticles, but this did not correlate with various measures of cuticle abundance or composition. Rather, we found that fruit cuticle permeance has a strong dependence on the abundance of microscopic polar pores. We further observed that these transcuticular pores are associated with trichomes and are exposed when the trichomes are dislodged, revealing a previously unreported link between fruit trichome density and transpirational water loss. During postharvest storage, limited self-sealing of the pores was detected for certain cultivars, in contrast with the stem scar, which healed relatively rapidly. The abundance of trichome-associated pores, together with their self-sealing capacity, presents a promising target for breeding or engineering efforts to reduce fruit transpirational water loss.

Microtubule-Mediated Wall Anisotropy Contributes to Leaf Blade Flattening.

Plant organs can adopt a wide range of shapes, resulting from highly directional cell growth and divisions. We focus here on leaves and leaf-like organs in Arabidopsis and tomato, characterized by the formation of thin, flat laminae. Combining experimental approaches with 3D mechanical modeling, we provide evidence that leaf shape depends on cortical microtubule mediated cellulose deposition along the main predicted stress orientations, in particular, along the adaxial-abaxial axis in internal cell walls. This behavior can be explained by a mechanical feedback and has the potential to sustain and even amplify a preexisting degree of flatness, which in turn depends on genes involved in the control of organ polarity and leaf margin formation.

Detection of Quantitative Trait Loci (QTL) Associated with the Fruit Morphology of Tomato.

Tomato (Solanum lycopersicum L.) is the second most-consumed vegetable in the world. The market value and culinary purpose of tomato are often determined by fruit size and shape, which makes the genetic improvement of these traits a priority for tomato breeders. The main objective of the study was to detect quantitative trait loci (QTL) associated with the tomato fruit shape and size. The use of elite breeding materials in the genetic mapping studies will facilitate the detection of genetic loci of direct relevance to breeders. We performed QTL analysis in an intra-specific population of tomato developed from a cross between two elite breeding lines NC 30P × NC-22L-1(2008) consisting of 110 recombinant inbred lines (RIL). The precision software Tomato Analyzer (TA) was used to measure fruit morphology attributes associated with fruit shape and size traits. The RIL population was genotyped with the SolCAP 7720 SNP array. We identified novel QTL controlling elongated fruit shape on chromosome 10, explaining up to 24% of the phenotypic variance. This information will be useful in improving tomato fruit morphology traits.

UF, a WOX gene, regulates a novel phenotype of un-fused flower in tomato.

Flower formation is a basic condition for fruit set in all flowering plants. The normal stamen of tomato flower fused together to form a yellow cylinder surrounding the carpels. In this study, we identified an un-fused flower (uf) tomato mutant that is defective in petal, carpal and stamen fusion and lateral outgrowth. After RNA-seq-based BSA (BSR), the candidate region location was identified in the long arm of chromosome 3. Using map-based cloning with InDel and CAPS markers, the UF candidate gene was mapped in a 104 kb region. In this region, a WOX (WUSCHEL-related homeobox) transcription factor SlWOX1 was considered as a candidate of UF as there is a 72bp deletion in its second exon in uf mutant. The mutations of SlWOX1 generated by CRISPR/CAS9 approach under wild-type background reproduced the phenotypes of uf mutant, indicating that the SlWOX1 gene is indeed UF. Interestingly, expression analysis of organ lateral polarity determinant genes showed that abaxial genes (SlYABBY5 and SlARF4) and adaxial genes (AS and HD-ZIPIII) were significantly down-regulated in the uf mutant, which is different to that in Arabidopsis and petunia. In conclusion, this work revealed a novel function of SlWOX1 in the regulation of flower development in tomato.

An endophytic Talaromyces omanensis enhances reproductive, physiological and anatomical characteristics of drought-stressed tomato.

The effects of a newly discovered endophytic fungus, Talaromyces omanensis, on the drought tolerance of tomato is presented in this study. The fungus was obtained from a desert plant Rhazya stricta in Oman. Drought stress was induced by a 15% solution of Polyethylene glycol-6000 (PEG-6000). Several parameters were measured including pollen sterility, pollen tube length, growth, flowering, and yield characteristics, the biochemical analysis of the leaves and fruits, as well as other physiological and anatomical parameters. The results showed that T. omanensis provided multiple advantages to tomato grown under drought stress, including improved reproductive characteristics, chlorophyll fluorescence, and some anatomical characteristics such as increased phloem and cortex width and a reduction of pith autolysis that leads to hollow stem. In addition, T. omanensis significantly increased drought-stress related characteristics such as shoot dry weight, root length, the number of flowers, and fruit weight. A significantly higher concentration of gibberellic acid (GA3) was found in tomato plants treated by T. omanensis, which may enhance their drought tolerance. These results suggest that T. omanensis is a potential biological anti-stress stimulator for important horticultural crops such as tomatoes. This study is the first to report the beneficial effects of T. omanensis in alleviating drought stress in tomatoes.

Monitoring Plant Status and Fertilization Strategy through Multispectral Images.

A crop monitoring system was developed for the supervision of organic fertilization status on tomato plants at early stages. An automatic and nondestructive approach was used to analyze tomato plants with different levels of water-soluble organic fertilizer (3 + 5 NK) and vermicompost. The evaluation system was composed by a multispectral camera with five lenses: green (550 nm), red (660 nm), red edge (735 nm), near infrared (790 nm), RGB, and a computational image processing system. The water-soluble fertilizer was applied weekly in four different treatments: (T0: 0 mL, T1: 6.25 mL, T2: 12.5 mL and T3: 25 mL) and the vermicomposting was added in Weeks 1 and 5. The trial was conducted in a greenhouse and 192 images were taken with each lens. A plant segmentation algorithm was developed and several vegetation indices were calculated. On top of calculating indices, multiple morphological features were obtained through image processing techniques. The morphological features were revealed to be more feasible to distinguish between the control and the organic fertilized plants than the vegetation indices. The system was developed in order to be assembled in a precision organic fertilization robotic platform.

Machine Learning Approaches to Improve Three Basic Plant Phenotyping Tasks Using Three-Dimensional Point Clouds.

Developing automated methods to efficiently process large volumes of point cloud data remains a challenge for three-dimensional (3D) plant phenotyping applications. Here, we describe the development of machine learning methods to tackle three primary challenges in plant phenotyping: lamina/stem classification, lamina counting, and stem skeletonization. For classification, we assessed and validated the accuracy of our methods on a dataset of 54 3D shoot architectures, representing multiple growth conditions and developmental time points for two Solanaceous species, tomato (Solanum lycopersicum cv 75 m82D) and Nicotiana benthamiana Using deep learning, we classified lamina versus stems with 97.8% accuracy. Critically, we also demonstrated the robustness of our method to growth conditions and species that have not been trained on, which is important in practical applications but is often untested. For lamina counting, we developed an enhanced region-growing algorithm to reduce oversegmentation; this method achieved 86.6% accuracy, outperforming prior methods developed for this problem. Finally, for stem skeletonization, we developed an enhanced tip detection technique, which ran an order of magnitude faster and generated more precise skeleton architectures than prior methods. Overall, our improvements enable higher throughput and accurate extraction of phenotypic properties from 3D point cloud data.

CO2 and nitrogen interaction alters root anatomy, morphology, nitrogen partitioning and photosynthetic acclimation of tomato plants.

MAIN CONCLUSION: Nitrogen and CO2 supply interactively regulate whole plant nitrogen partitioning and root anatomical and morphological development in tomato plants. Nitrogen (N) and carbon (C) are the key elements in plant growth and constitute the majority of plant dry matter. Growing at CO2 enrichment has the potential to stimulate the growth of C3 plants, however, growth is often limited by N availability. Thus, the interactive effects of CO2 under different N fertilization rates can affect growth, acclimation to elevated CO2, and yield. However, the majority of research in this field has focused on shoot traits, while neglecting plants' hidden half-the roots. We hypothesize that elevated CO2 and low N effects on transpiration will interactively affect root vascular development and plant N partitioning. Here we studied the effects of elevated CO2 and N concentrations on greenhouse-grown tomato plants, a C3 crop. Our main objective was to determine in what manner the N fertilization rate and elevated CO2 affected root development and nitrogen partitioning among plant organs. Our results indicate that N interacting with the CO2 level affects the development of the root system in terms of the length, anatomy, and partitioning of the N concentration between the roots and shoot. Both CO2 and N concentrations were found to affect xylem size in an opposite manner, elevated CO2 found to repressed, whereas ample N stimulated xylem development. We found that under limiting N and eCO2, the N% increase in the root, while it decreased in the shoot. Under eCO2, the root system size increased with a coordinated decrease in root xylem area. We suggest that tomato root response to elevated CO2 depends on N fertilization rates, and that a decrease in xylem size is a possible underlying response that limits nitrogen allocation from the root into the shoot. Additionally, the greater abundance of root amino acids suggests increased root nitrogen metabolism at eCO2 conditions with ample N.