Rapid and accurate detection of peanut pod appearance quality based on lightweight and improved YOLOv5_ SSE model
Introduction: With the escalating demands for agricultural product quality in modern agriculture, peanuts, as a crucial economic crop, have their pod appearance quality directly influencing market value and consumer acceptance. Traditionally, the visual inspection of peanut pod appearance quality relies heavily on manual labor, which is not only labor-intensive and inefficient but also susceptible to subjective judgments from inspectors, thereby compromising the consistency and accuracy of inspection outcomes. Consequently, the development of a rapid, accurate, and automated inspection system holds significant importance for enhancing production efficiency and quality control in the peanut industry. Methods: This study introduces the optimization and iteration of the YOLOv5s model, aiming to swiftly and precisely identify high-quality peanuts, peanuts with mechanical damage, moldy peanuts, and germinated peanuts. The CSPDarkNet53 network of the YOLOv5s model was substituted with the ShuffleNetv2 backbone network to reduce the model’s weight. Various attention mechanisms were explored for integration and substitution with the backbone network to enhance model performance. Furthermore, the substitution of various loss functions was investigated, with the Focal-EIoU loss function employed as the regression loss term for predicting bounding boxes, thereby improving inference accuracy. Results: Compared to the YOLOv5s network model, SSE-YOLOv5s boasts a mere 6.7% of the original model’s parameters, 7.8% of the computation, and an FPS rate 115. 1% higher. Its weight size is a mere 7.6% of the original model’s, while the detection accuracy and mean average precision (mAP) reach 98.3% and 99.3%, respectively, representing improvements of 1.6 and 0.7 percentage points over the original YOLOv5s model. Discussion: The results underscore the superiority of the SSE-YOLOv5s model, which achieves a maximum mAP of 99.3% with a minimal model size of 1. 1MB and a peak FPS of 192.3. This optimized network model excels in rapidly, efficiently, and accurately detecting the appearance quality of mixed multi-target peanut pods, making it suitable for deployment on embedded devices. This study provides an essential reference for multi-target appearance quality inspection of peanut pods.
https://doi.org/10.3389/fpls.2025.1494688
In-silico identification and characterization of O-methyltransferase gene family in peanut (Arachis hypogaea L.) reveals their putative roles in development and stress tolerance
Cultivated peanut (Arachis hypogaea) is a leading protein and oil-providing crop and food source in many countries. At the same time, it is affected by a number of biotic and abiotic stresses. O-methyltransferases (OMTs) play important roles in secondary metabolism, biotic and abiotic stress tolerance. However, the OMT genes have not been comprehensively analyzed in peanut. In this study, we performed a genome-wide investigation of A. hypogaea OMT genes (AhOMTs). Gene structure, motifs distribution, phylogenetic history, genome collinearity and duplication of AhOMTs were studied in detail. Promoter cis-elements, protein-protein interactions, and micro-RNAs targeting AhOMTs were also predicted. We also comprehensively studied their expression in different tissues and under different stresses. We identified 116 OMT genes in the genome of cultivated peanut. Phylogenetically, AhOMTs were divided into three groups. Tandem and segmental duplication events played a role in the evolution of AhOMTs, and purifying selection pressure drove the duplication process. AhOMT promoters were enriched in several key cis-elements involved in growth and development, hormones, light, and defense-related activities. Micro-RNAs from 12 different families targeted 35 AhOMTs. GO enrichment analysis indicated that AhOMTs are highly enriched in transferase and catalytic activities, cellular metabolic and biosynthesis processes. Transcriptome datasets revealed that AhOMTs possessed varying expression levels in different tissues and under hormones, water, and temperature stress. Expression profiling based on qRT-PCR results also supported the transcriptome results. This study provides the theoretical basis for further work on the biological roles of AhOMT genes for developmental and stress responses. https://doi.org/10.3389/fpls.2023.1145624
Physiological characterization of the wild almond Prunus arabica stem photosynthetic capability.
Leaves are the major plant tissue for transpiration and carbon fixation in deciduous trees. In harsh habitats, atmospheric CO2 assimilation via stem photosynthesis is common, providing extra carbon gain to cope with the detrimental conditions. We studied two almond species, the commercial Prunus dulcis cultivar "Um-el-Fahem" and the rare wild Prunus arabica. Our study revealed two distinctive strategies for carbon gain in these almond species. While, in P. dulcis, leaves possess the major photosynthetic surface area, in P. arabica, green stems perform this function, in particular during the winter after leaf drop. These two species' anatomical and physiological comparisons show that P. arabica carries unique features that support stem gas exchange and high-gross photosynthetic rates via stem photosynthetic capabilities (SPC). On the other hand, P. dulcis stems contribute low gross photosynthesis levels, as they are designed solely for reassimilation of CO2 from respiration, which is termed stem recycling photosynthesis (SRP). Results show that (a) P. arabica stems are covered with a high density of sunken stomata, in contrast to the stomata on P. dulcis stems, which disappear under a thick peridermal (bark) layer by their second year of development. (b) P. arabica stems contain significantly higher levels of chlorophyll compartmentalized to a mesophyll-like, chloroplast-rich, parenchyma layer, in contrast to rounded-shape cells of P. dulcis's stem parenchyma. (c) Pulse amplitude-modulated (PAM) fluorometry of P. arabica and P. dulcis stems revealed differences in the chlorophyll fluorescence and quenching parameters between the two species. (d) Gas exchange analysis showed that guard cells of P. arabica stems tightly regulate water loss under elevated temperatures while maintaining constant and high assimilation rates throughout the stem. Our data show that P. arabica uses a distinctive strategy for tree carbon gain via stem photosynthetic capability, which is regulated efficiently under harsh environmental conditions, such as elevated temperatures. These findings are highly important and can be used to develop new almond cultivars with agriculturally essential traits. https://doi.org/10.3389/fpls.2022.941504
Genome-Wide Analysis and Expression Profiles of Ethylene Signal Genes and Apetala2/Ethylene-Responsive Factors in Peanut (Arachis hypogaea L.).
Peanut is an important oil and economic crop widely cultivated in the world. It has special characteristics such as blooming on the ground but bearing fruits underground. During the peg penetrating into the ground, it is subjected to mechanical stress from the soil at the same time. It has been proved that mechanical stress affects plant growth and development by regulating the ethylene signaling-related genes. In this study, we identified some genes related to ethylene signal of peanut, including 10 ethylene sensors, two constitutive triple responses (CTRs), four ethylene insensitive 2 (EIN2s), four ethylene insensitive 3 (EIN3s), six EIN3-binding F-box proteins (EBFs), and 188 Apetala2/ethylene-responsive factors (AP2/ERFs). One hundred and eighty-eight AP2/ERFs were further divided into four subfamilies, 123 ERFs, 56 AP2s, 6 Related to ABI3/VP1 (RAVs), and three Soloists, of them one hundred and seventy AP2/ERF gene pairs were clustered into segmental duplication events in genome of Arachis hypogaea. A total of 134, 138, 97, and 150 AhAP2/ERF genes formed 210, 195, 166, and 525 orthologous gene pairs with Arachis duranensis, Arachis ipaensis, Arabidopsis thaliana, and Glycine max, respectively. Our transcriptome results showed that two EIN3s (Arahy.J729H0 and Arahy.S7XF8N) and one EBFs (Arahy.G4JMEM) were highly expressed when mechanical stress increased. Among the 188 AhAP2/ERF genes, there were 31 genes with the fragments per kilobase of exon model per million mapped fragments (FPKM) ≥ 100 at least one of the 15 samples of Tifrunner. Among them, three AhAP2/ERFs (Arahy.15RATX, Arahy.FAI7YU, and Arahy.452FBF) were specifically expressed in seeds and five AhAP2/ERFs (Arahy.HGAZ7D, Arahy.ZW7540, Arahy.4XS3FZ, Arahy.QGFJ76, and Arahy.AS0C7C) were highly expressed in the tissues, which responded mechanical stress, suggesting that they might sense mechanical stress. Mechanical stress simulation experiment showed that three AhAP2/ERFs (Arahy.QGFJ76, Arahy.AS0C7C, and Arahy.HGAZ7D) were sensitive to mechanical stress changes and they all had the conservative repressor motif (DLNXXP) in the C-terminus, indicated that they might transmit mechanical stress signals through transcriptional inhibition. This study reveals the regulatory landscape of ethylene signal-related genes in peanut, providing valuable information for the mining of target genes for further study. https://doi.org/10.3389/fpls.2022.828482
Agronomical and Physiological Behavior of Spanish Hazelnut Selection "Negret-N9" Grafted on Non-suckering Rootstocks
"Negret" is the most widely planted hazelnut cultivar in Northeastern Spain, where it is highly appreciated by the local kernel marked for its favorable nut traits. Its main disadvantages are the high suckers emission, causing large maintenance costs every year, and its medium-to-low vigor and susceptibility to iron chlorosis. In 2000, a trial to select new vigorous and non-suckering rootstocks for hazelnut was established at IRTA Mas Bové (Spain). The "Negret N-9" selection was grafted onto four clonal rootstocks ("Dundee" and "Newberg" two selections of open-pollinated Corylus colurna seedlings, the low suckering cultivar "Tonda Bianca" and the local selection "IRTA MB-69") and compared to the self-rooted "Negret N-9" as a control. The trial was designed as a randomized complete block with 10 replications and one tree per plot (10 trees per treatment). Plant vigor, suckers emission, yield, and nut and kernel traits have been evaluated over 10 years (2003-2012). During the 2006 to 2010 growing seasons, the qualitative traits of kernels, such as kernel skin color, oil content, and fatty acid profiles, were added to the characterization. Physiological data, such as steam water potential, stomatal conductance, and leaf chlorophyll content, were also evaluated during the 2015 growing season. The results showed that clonal rootstocks had a strong influence on vigor and yield of "Negret N-9." The "Dundee," "Newberg," and "IRTA MB-69" rootstocks showed the highest vegetative growth and the lower suckers emission. The yield was highest in trees grafted on "Dundee" rootstock. In terms of the qualitative traits of kernel which are important to the hazelnut industry, rootstocks increased the oil stability and induced a brown light color in the kernel pellicle versus the brown dark color observed in nuts collected from self-rooted "Negret N-9." The fatty acids profile was also influenced by the grafting combination. Finally, physiological traits indicated a higher overall performances for "Dundee" rootstock, which was generally found to be the best rootstock for "Negret N-9" in the experimental environment. https://doi.org/10.3389/fpls.2021.813902
Establishing a Reference Baseline for Midday Stem Water Potential in Olive and Its Use for Plant-Based Irrigation Management.
Midday stem water potential (SWP) is rapidly becoming adopted as a standard tool for plant-based irrigation management in many woody perennial crops. A reference or "baseline" SWP has been used in some crops (almond, prune, grape, and walnut) to account for the climatic influence of air vapor pressure deficit (VPD) on SWP under non-limiting soil moisture conditions. The baseline can be determined empirically for field trees maintained under such non-limiting conditions, but such conditions are difficult to achieve for an entire season. We present the results of an alternative survey-based approach, using a large set of SWP and VPD data collected over multiple years, from irrigation experiments in olive orchards located in multiple countries [Spain, United States (California), Italy, and Argentina]. The relation of SWP to midday VPD across the entire data set was consistent with an upper limit SWP which declined with VPD, with the upper limit being similar to that found in Prunus. A best fit linear regression estimate for this upper limit (baseline) was found by selecting the maximum R 2 and minimum probability for various upper fractions of the SWP/VPD relation. In addition to being surprisingly similar to the Prunus baseline, the olive baseline was also similar (within 0.1 MPa) to a recently published mechanistic olive soil-plant-atmosphere-continuum (SPAC) model for "super high density" orchard systems. Despite similarities in the baseline, the overall physiological range of SWP exhibited by olive extends to about -8 MPa, compared to about -4 MPa for economically producing almond. This may indicate that, despite species differences in physiological responses to low water availability (drought), there may be convergent adaptations/acclimations across species to high levels of water availability. Similar to its use in other crops, the olive baseline will enable more accurate and reproducible plant-based irrigation management for both full and deficit irrigation practices, and we present tentative SWP guidelines for this purpose. https://doi.org/10.3389/fpls.2021.791711
Mapping the Genetic Regions Responsible for Key Phenology-Related Traits in the European Hazelnut.
An increasing interest in the cultivation of (European) hazelnut (Corylus avellana) is driving a demand to breed cultivars adapted to non-conventional environments, particularly in the context of incipient climate change. Given that plant phenology is so strongly determined by genotype, a rational approach to support these breeding efforts will be to identify quantitative trait loci (QTLs) and the genes underlying the basis for adaptation. The present study was designed to map QTLs for phenology-related traits, such as the timing of both male and female flowering, dichogamy, and the period required for nuts to reach maturity. The analysis took advantage of an existing linkage map developed from a population of F1 progeny bred from the cross "Tonda Gentile delle Langhe" × "Merveille de Bollwiller," consisting in 11 LG. A total of 42 QTL-harboring regions were identified. Overall, 71 QTLs were detected, 49 on the TGdL map and 22 on the MB map; among these, 21 were classified as major; 13 were detected in at least two of the seasons (stable-major QTL). In detail, 20 QTLs were identified as contributing to the time of male flowering, 15 to time of female flowering, 25 to dichogamy, and 11 to time of nut maturity. LG02 was found to harbor 16 QTLs, while 15 QTLs mapped to LG10 and 14 to LG03. Many of the QTLs were clustered with one another. The major cluster was located on TGdL_02 and consisted of mainly major QTLs governing all the analyzed traits. A search of the key genomic regions revealed 22 candidate genes underlying the set of traits being investigated. Many of them have been described in the literature as involved in processes related to flowering, control of dormancy, budburst, the switch from vegetative to reproductive growth, or the morphogenesis of flowers and seeds. https://doi.org/10.3389/fpls.2021.749394
Discovery of Single Nucleotide Polymorphisms for Resistance to Abnormal Vertical Growth in Macadamia
Abnormal vertical growth (AVG) syndrome is a serious threat to the Australian macadamia industry as it decreases the yield of nuts by as much as 70% per annum. A lack of information on the cause of AVG has hindered the development of an effective disease management strategy. Discovery of genetic markers associated with disease resistance can be used as tool for rapid selection of elite cultivars, hence helps in efficient disease management. Differences in field susceptibility of macadamia cultivars provide an opportunity for discovery of genetic markers that are associated with host resistance. REML mixed model analysis was performed to estimate the AVG rating of 51 cultivars from multiple origins using phenotypic data from 359 trees planted in four sites. Most of the Hawaiian cultivars were found as susceptible, while selections from the Australian macadamia industry breeding program were predominantly resistant. All the cultivars were genotyped for 13,221 DArTseq-based single nucleotide polymorphism (SNP) markers. A bulked sample analysis was performed using 20 genotypes each at the extremes of AVG phenotypic ratings. Ten SNP markers were predicted to be associated with AVG resistance and two arbitrarily selected SNP markers were validated using PCR and Sanger sequencing. Our findings suggest that AVG resistance in the commercial cultivars may be derived from the genomic introgression of Macadamia tetraphylla through interspecific hybridization. The results may support marker-assisted selection for macadamia germplasm with AVG resistance. https://doi.org/10.3389/fpls.2021.756815
Chromosome-Level Genome Assembly and HazelOmics Database Construction Provides Insights Into Unsaturated Fatty Acid Synthesis and Cold Resistance in Hazelnut (Corylus heterophylla)
Corylus heterophylla (2n = 22) is the most widely distributed, unique, and economically important nut species in China. Chromosome-level genomes of C. avellana, C. heterophylla, and C. mandshurica have been published in 2021, but a satisfactory hazelnut genome database is absent. Northeast China is the main distribution and cultivation area of C. heterophylla, and the mechanism underlying the adaptation of C. heterophylla to extremely low temperature in this area remains unclear. Using single-molecule real-time sequencing and the chromosomal conformational capture (Hi-C) assisted genome assembly strategy, we obtained a high-quality chromosome-scale genome sequence of C. heterophylla, with a total length of 343 Mb and scaffold N50 of 32.88 Mb. A total of 94.72% of the test genes from the assembled genome could be aligned to the Embryophyta_odb9 database. In total, 22,319 protein-coding genes were predicted, and 21,056 (94.34%) were annotated in the assembled genome. A HazelOmics online database (HOD) containing the assembled genome, gene-coding sequences, protein sequences, and various types of annotation information was constructed. This database has a user-friendly and straightforward interface. In total, 439 contracted genes and 3,810 expanded genes were identified through genome evolution analysis, and 17 expanded genes were significantly enriched in the unsaturated fatty acid biosynthesis pathway (ko01040). Transcriptome analysis results showed that FAD (Cor0058010.1), SAD (Cor0141290.1), and KAT (Cor0122500.1) with high expression abundance were upregulated at the ovule maturity stage. We deduced that the expansion of these genes may promote high unsaturated fatty acid content in the kernels and improve the adaptability of C. heterophylla to the cold climate of Northeast China. The reference genome and database will be beneficial for future molecular breeding and gene function studies in this nut species, as well as for evolutionary research on species of the order Fagales. https://doi.org/10.3389/fpls.2021.766548
Susceptibility of Some Corylus avellana L. Cultivars to Xanthomonas arboricola pv. corylina.
Bacterial blight of hazelnut (Corylus avellana L.) is caused by Xanthomonas arboricola pv. corylina (Xac). In the past, bacterial blight has been a key disease impacting the Oregon hazelnut industry where 99% of the United States hazelnut crop is grown. The disease is re-emerging in young orchards, as acreage of newly released hazelnut cultivars rapidly increases. This increase in hazelnut acreage is accompanied by renewed interest in developing control strategies for bacterial blight. Information on susceptibility of hazelnut cultivars to Xac is limited, partially due to lack of verified methods to quantify hazelnut cultivar response to artificial inoculation. In this research, Xac inoculation protocols were adapted to two hazelnut growing environments to evaluate cultivar susceptibility: in vitro tissue culture under sterile and controlled conditions, and in vivo potted tree conditions. Five hazelnut cultivars were evaluated using the in vitro inoculation protocol and seven hazelnut cultivars were evaluated using the in vivo inoculation protocol. Under in vitro conditions, there were severe bacterial blight symptoms on each cultivar consistent with those seen in the field, but no significant differences in the susceptibility of the newly released cultivars were observed compared to known Xac-susceptible cultivar ("Barcelona"). Under in vivo conditions, the proportion of necrotic buds were significantly higher in "Jefferson" and "Dorris" compared to all of the other tested cultivars, including "Barcelona." The symptom progression seen in vivo mirrored the timing and symptom progression of bacterial blight reported from field observations. The in vitro conditions significantly reduced the amount of time required to measure the inoculation efficiency compared to the in vivo environment and allowed for greater replication. Further studies on the effects of Xac can use the results of these experiments to establish a dose-response model for bacterial blight, a wider range of germplasm can be tested under in vitro conditions, and management strategies that can be evaluated on large populations of new cultivars using the in vivo methods. https://doi.org/10.3389/fpls.2021.800339