Classification of tomato seedling chilling injury based on chlorophyll fluorescence imaging and DBO-BiLSTM.

Introduction: Tomatoes are sensitive to low temperatures during their growth process, and low temperatures are one of the main environmental limitations affecting plant growth and development in Northeast China. Chlorophyll fluorescence imaging technology is a powerful tool for evaluating the efficiency of plant photosynthesis, which can detect and reflect the effects that plants are subjected to during the low temperature stress stage, including early chilling injury. Methods: This article primarily utilizes the chlorophyll fluorescence image set of tomato seedlings, applying the dung beetle optimization (DBO) algorithm to enhance the deep learning bidirectional long short term memory (BiLSTM) model, thereby improving the accuracy of classification prediction for chilling injury in tomatoes. Firstly, the proportion of tomato chilling injury areas in chlorophyll fluorescence images was calculated using a threshold segmentation algorithm to classify tomato cold damage into four categories. Then, the features of each type of cold damage image were filtered using SRCC to extract the data with the highest correlation with cold damage. These data served as the training and testing sample set for the BiLSTM model. Finally, DBO algorithm was applied to enhance the deep learning BiLSTM model, and the DBO-BiLSTM model was proposed to improve the prediction performance of tomato seedling category labels. Results: The results showed that the DBO-BiLSTM model optimized by DBO achieved an accuracy, precision, recall, and F1 score with an average of over 95%. Discussion: Compared to the original BiLSTM model, these evaluation parameters improved by 9.09%, 7.02%, 9.16%, and 8.68%, respectively. When compared to the commonly used SVM classification model, the evaluation parameters showed an increase of 6.35%, 7.33%, 6.33%, and 6.5%, respectively. This study was expected to detect early chilling injury through chlorophyll fluorescence imaging, achieve automatic classification and labeling of cold damage data, and lay a research foundation for in-depth research on the cold damage resistance of plants themselves and exploring the application of deep learning classification methods in precision agriculture.

Revolutionizing tomato disease detection in complex environments.

In the current agricultural landscape, a significant portion of tomato plants suffer from leaf diseases, posing a major challenge to manual detection due to the task's extensive scope. Existing detection algorithms struggle to balance speed with accuracy, especially when identifying small-scale leaf diseases across diverse settings. Addressing this need, this study presents FCHF-DETR (Faster-Cascaded-attention-High-feature-fusion-Focaler Detection-Transformer), an innovative, high-precision, and lightweight detection algorithm based on RT-DETR-R18 (Real-Time-Detection-Transformer-ResNet18). The algorithm was developed using a carefully curated dataset of 3147 RGB images, showcasing tomato leaf diseases across a range of scenes and resolutions. FasterNet replaces ResNet18 in the algorithm's backbone network, aimed at reducing the model's size and improving memory efficiency. Additionally, replacing the conventional AIFI (Attention-based Intra-scale Feature Interaction) module with Cascaded Group Attention and the original CCFM (CNN-based Cross-scale Feature-fusion Module) module with HSFPN (High-Level Screening-feature Fusion Pyramid Networks) in the Efficient Hybrid Encoder significantly enhanced detection accuracy without greatly affecting efficiency. To tackle the challenge of identifying challenging samples, the Focaler-CIoU loss function was incorporated, refining the model's performance throughout the dataset. Empirical results show that FCHF-DETR achieved 96.4% Precision, 96.7% Recall, 89.1% mAP (Mean Average Precision) 50-95 and 97.2% mAP50 on the test set, with a reduction of 9.2G in FLOPs (floating point of operations) and 3.6M in parameters. These findings clearly demonstrate that the proposed method improves detection accuracy and reduces computational complexity, addressing the dual challenges of precision and efficiency in tomato leaf disease detection.

Evolution of gene networks underlying adaptation to drought stress in the wild tomato Solanum chilense.

Drought stress is a key limitation for plant growth and colonization of arid habitats. We study the evolution of gene expression response to drought stress in a wild tomato, Solanum chilense, naturally occurring in dry habitats in South America. We conduct a transcriptome analysis under standard and drought experimental conditions to identify drought-responsive gene networks and estimate the age of the involved genes. We identify two main regulatory networks corresponding to two typical drought-responsive strategies: cell cycle and fundamental metabolic processes. The metabolic network exhibits a more recent evolutionary origin and a more variable transcriptome response than the cell cycle network (with ancestral origin and higher conservation of the transcriptional response). We also integrate population genomics analyses to reveal positive selection signals acting at the genes of both networks, revealing that genes exhibiting selective sweeps of older age also exhibit greater connectivity in the networks. These findings suggest that adaptive changes first occur at core genes of drought response networks, driving significant network re-wiring, which likely underpins species divergence and further spread into drier habitats. Combining transcriptomics and population genomics approaches, we decipher the timing of gene network evolution for drought stress response in arid habitats.

Synthetic data at scale: a development model to efficiently leverage machine learning in agriculture.

The rise of artificial intelligence (AI) and in particular modern machine learning (ML) algorithms during the last decade has been met with great interest in the agricultural industry. While undisputedly powerful, their main drawback remains the need for sufficient and diverse training data. The collection of real datasets and their annotation are the main cost drivers of ML developments, and while promising results on synthetically generated training data have been shown, their generation is not without difficulties on their own. In this paper, we present a development model for the iterative, cost-efficient generation of synthetic training data. Its application is demonstrated by developing a low-cost early disease detector for tomato plants (Solanum lycopersicum) using synthetic training data. A neural classifier is trained by exclusively using synthetic images, whose generation process is iteratively refined to obtain optimal performance. In contrast to other approaches that rely on a human assessment of similarity between real and synthetic data, we instead introduce a structured, quantitative approach. Our evaluation shows superior generalization results when compared to using non-task-specific real training data and a higher cost efficiency of development compared to traditional synthetic training data. We believe that our approach will help to reduce the cost of synthetic data generation in future applications.

Influence of indole acetic acid and trehalose, with and without zinc oxide nanoparticles coated urea on tomato growth in nitrogen deficient soils.

Nitrogen deficiency in low organic matter soils significantly reduces crop yield and plant health. The effects of foliar applications of indole acetic acid (IAA), trehalose (TA), and nanoparticles-coated urea (NPCU) on the growth and physiological attributes of tomatoes in nitrogen-deficient soil are not well documented in the literature. This study aims to explore the influence of IAA, TA, and NPCU on tomato plants in nitrogen-deficient soil. Treatments included control, 2mM IAA, 0.1% TA, and 2mM IAA + 0.1% TA, applied with and without NPCU. Results showed that 2mM IAA + 0.1% TA with NPCU significantly improved shoot length (~ 30%), root length (~ 63%), plant fresh (~ 48%) and dry weight (~ 48%), number of leaves (~ 38%), and leaf area (~ 58%) compared to control (NPCU only). Additionally, significant improvements in chlorophyll content, total protein, and total soluble sugar, along with a decrease in antioxidant activity (POD, SOD, CAT, and APX), validated the effectiveness of 2mM IAA + 0.1% TA with NPCU. The combined application of 2mM IAA + 0.1% TA with NPCU can be recommended as an effective strategy to enhance tomato growth and yield in nitrogen-deficient soils. This approach can be integrated into current agricultural practices to improve crop resilience and productivity, especially in regions with poor soil fertility. To confirm the efficacy of 2mM IAA + 0.1% TA with NPCU in various crops and climatic conditions, additional field studies are required.

RNA-protein interactions reveals the pivotal role of lncRNA1840 in tomato fruit maturation.

Long non-coding RNAs (lncRNAs) play crucial roles in various biological processes in plants. However, the functional mechanism of lncRNAs in fruit ripening, particularly the transition from unripe to ripe stages, remains elusive. One such lncRNA1840, reported by our group, was found to have important role in tomato fruit ripening. In the present study, we gain insight into its functional role in fruit ripening. CRISPR-Cas9 mediated lncRNA1840 mutants caused the delayed tomato fruit ripening. Notably, loss function of lncRNA1840 did not directly impact ethylene signaling but rather delay ethylene synthesis. Transcriptomic analysis revealed differences in the expression of ripening related genes in lncRNA1840 mutants, suggesting that it is involved in gene regulation of fruit ripening. We used Chromatin Isolation by RNA Purification (ChIRP)-Seq to identify lncRNA1840 binding sites on chromatin. ChIRP-seq suggested that lncRNA1840 had occupancy on 40 genes, but none of them is differentially expressed genes in transcriptomic analysis, which indicated lncRNA1840 might indirectly modulate the gene expression. ChIRP-mass spectrometry analysis identified potential protein interactors of lncRNA1840, Pre-mRNA processing splicing factor 8, highlighting its involvement in post-transcriptional regulatory pathways. In summary, lncRNA1840 is key player in tomato plant growth and fruit ripening, with multifaceted roles in gene expression and regulatory networks.

Molecular characterization to study the genetic diversity of begomoviruses occurring in the major chilli growing areas of Tamil Nadu state of India.

Chilli leaf curl disease (ChiLCD), which is a significant problem in chilli cultivation, is caused by begomoviruses that are transmitted by the whitefly Bemisia tabaci. This disease leads to severe impacts on crop yields. To determine the incidence of begomovirus in the chilli crop, infected chilli leaf samples exhibiting symptoms such as curling, yellowing, reduced leaf size, and overall stunted growth were collected from various districts of Tamil Nadu, namely, Coimbatore, Dharmapuri, Kancheepuram, Karur, Salem, Krishnagiri, Thoothukudi, Thiruvallur, Tiruchirappalli, Virudhunagar, Tiruvannamalai, Tenkasi, and Vellore, during the years 2018-2022. To determine the complete genome sequence of the begomoviruses, the rolling circle amplification (RCA) method was used to clone and sequence the begomovirus genomes from the chilli samples collected from various districts of Tamil Nadu. Here we characterized 17 DNA A genome sequences and 12 betasatellite sequences. BLAST results of the DNA A genome sequences revealed nucleotide identities ranging from 94.2 to 99.7% with five distinct begomovirus species of chilli, namely, chilli leaf curl Salem virus (HM007119), chilli leaf curl virus Bhavanisagar (NC_055130), chilli leaf curl Ahmedabad virus (MW795666), chilli leaf curl virus (NC_055131), and chilli leaf curl Sri Lanka virus (JN555600). BLAST results of the betasatellite sequences showed nucleotide identities of 96 to 98.8% with the tomato leaf curl Bangladesh betasatellite (MZ151286). In the present study, five distinct begomovirus species and one associated betasatellite were found to infect chilli crops in Tamil Nadu. This finding indicates a changing pattern of begomovirus occurrence in the different districts of Tamil Nadu. This study highlights the prevalence of chilli-infecting begomoviruses in the major chilli growing districts of Tamil Nadu, the identification of begomovirus species, and the significance of understanding and managing these viruses to safeguard chilli cultivation in the region.

The Epsin-like clathrin adaptor protein 4 SlECA4 improves tomato heat tolerance via clathrin-mediated endocytosis.

Clathrin-mediated endocytosis (CME) is one of the main pathways for plant cells to internalize the membrane proteins in response to changing environmental conditions. The Epsin-like Clathrin adaptor proteins (ECAs) play important roles in the assembly of clathrin coat; however, their involvement in plant response to heat stress remains unclear. Here we report that SlECA4 responded to heat stress, and the silencing and knockout of SlECA4 increased tomato sensitivity to heat stress, while the overexpression of SlECA4 enhanced tomato tolerance to heat stress. Meanwhile, the treatment with a CME inhibitor, ES9-17, reduced tomato heat tolerance. SlECA4 localized to the plasma membrane (PM), the trans-Golgi network/early endosomes (TGN/EE), and the prevacuolar compartment (PVC)/late endosomes. In SlECA4-KO line, both CME and recycling from the TGN/EE to the PM were inhibited. These data suggest that SlECA4 involved in CME. After heat treatment, more punctate structures of SlECA4:GFP accumualted in tobacco leaf epidermal cells by transient expression. Furthermore, compared to WT, the rate of CME was inhibited under heat stress in SlECA4-KO line. Taken together, the Epsin-like Clathrin adaptor protein SlECA4 plays a positive role in tomato tolerance to heat stress via the CME pathway.

Enhancing tomato (Solanum lycopersicum) yield and nutrition quality through hydroponic cultivation with treated wastewater.

Utilizing treated wastewater for crop cultivation is essential in regions with scarce freshwater resources for irrigation. This study evaluated the growth, fruit yield, nutritional and phytochemical quality of tomato fruits cultivated using a treated wastewater-based hydroponics system developed for the Trans Himalaya, India. Tomatoes grown with treated wastewater exhibited better growth, yield, nutritional content, phytochemical properties, and antioxidant activities than those grown in soil. Specifically, the lycopene and ß carotene were significantly (p < 0.05) higher in tomato fruits cultivated in treated wastewater (0.05 ± 0.00 and 0.09 ± 0.00 mg/g) than soil (0.02 ± 0.00 and 0.01 ± 0.00 mg/g). Also, significantly (p < 0.05) higher carbohydrate and protein contents (55.91 ± 1.19 and 21.34 ± 0.31 mg/g, respectively) were obtained under-treated wastewater than soil (39.48 ± 0.07 and 18.52 ± 0.10 mg/g). Similar trends were also obtained in phytochemicals and mineral analysis. However, morphological, proximate, and phytochemical characteristics of tomatoes in nutrient and wastewater-based hydroponics were comparable. Treated wastewater offers eco-friendly benefits for quality crop production.

Genomic insights and biocontrol potential of ten bacterial strains from the tomato core microbiome.

Introduction: Despite their adverse environmental effects, modern agriculture relies heavily on agrochemicals to manage diseases and pests and enhance plant growth and productivity. Some of these functions could instead be fulfilled by endophytes from the plant microbiota, which have diverse activities beneficial for plant growth and health. Methods: We therefore used a microbiome-guided top-down approach to select ten bacterial strains from different taxa in the core microbiome of tomato plants in the production chain for evaluation as potential bioinoculants. High-quality genomes for each strain were obtained using Oxford Nanopore long-read and Illumina short-read sequencing, enabling the dissection of their genetic makeup to identify phyto-beneficial traits. Results: Bacterial strains included both taxa commonly used as biofertilizers and biocontrol agents (i.e. Pseudomonas and Bacillus) as well as the less studied genera Leclercia, Chryseobacterium, Glutamicibacter, and Paenarthorbacter. When inoculated in the tomato rhizosphere, these strains promoted plant growth and reduced the severity of Fusarium Crown and Root Rot and Bacterial Spot infections. Genome analysis yielded a comprehensive inventory of genes from each strain related to processes including colonization, biofertilization, phytohormones, and plant signaling. Traits directly relevant to fertilization including phosphate solubilization and acquisition of nitrogen and iron were also identified. Moreover, the strains carried several functional genes putatively involved in abiotic stress alleviation and biotic stress management, traits that indirectly foster plant health and growth. Discussion: This study employs a top-down approach to identify new plant growth-promoting rhizobacteria (PGPRs), offering an alternative to the conventional bottom-up strategy. This method goes beyond the traditional screening of the strains and thus can expand the range of potential bioinoculants available for market application, paving the way to the use of new still underexplored genera.

Multi-Omics Exploration of ABA Involvement in Identifying Unique Molecular Markers for Single and Combined Stresses in tomato plants.

Over the past decade, our research group has found that plant responses to combined abiotic stresses are unique and cannot be inferred from studying plants exposed to individual stresses. Understanding how adaptative plant mechanisms integrate from stress perception to biochemical and physiological adjustments is a major challenge in abiotic stress signaling studies. Considering abscisic acid (ABA) as a key regulator in plant abiotic stress responses, in our study, ABA-deficient plants (flc) exposed to single or combined salinity and heat stresses were evaluated and different -omics analyses were conducted. Significant changes in biomass, photosynthesis, ions, transcripts, and metabolites occurred in mutant plants under single or combined stresses. Exogenous ABA application in flc mutants did not fully recover plant phenotypes or metabolic levels but induced cellular reprogramming with changes in specific markers. Multi-omics analysis aimed to identify ABA-dependent, ABA-independent, or stress-dependent markers in plant responses to single or combined stresses. We demonstrated that studying different -omics as a whole led to the identification of specific markers for each stress condition that were not detectable when each -omic was studied individually. This resource article provides an important and novel reference for scientists working in the field of plant abiotic stress. Future exploration of the transcriptomic, ionomic and metabolomic data presented in this study could lead to the identification of new pathways and genes associated with ABA signaling processes. These findings may be utilized to enhance crop resilience to heat waves, salinity, and their combination, contributing to addressing food security challenges in a climate change scenario.

Reduced fertilization supplemented with Bacillus safensis RGM 2450 and Bacillus siamensis RGM 2529 promotes tomato production in a sustainable way.

The rising demand for vegetables has driven the adoption of greenhouse cultivation to guarantee high yields and quality of fresh produce year-round. Consequently, this elevates the demand for fertilizers, whose costs are progressively escalating. Bacillus safensis RGM 2450 and Bacillus siamensis RGM 2529 are plant growth-promoting rhizobacteria (PGPR). The combination of these strains exhibited synergistic activity in stimulating the growth and seedling hydration of tomatoes. In this study, the effects of inoculation with a RGM 2450 plus RGM 2529 formulation were evaluated under 66% and 100% fertilization programs in tomato crops under greenhouse conditions. Fertilization programs (66% and 100%) with or without commercial biostimulants were used as control treatments. In this assay, the NPK percentage in the plant tissue, tomato average weight, tomato average weight per harvest, tomato diameter, and changes in the colonization, structure, and diversity of the bacterial rhizosphere were measured. The 100% and 66% fertilization programs supplemented with the RGM 2529 plus RGM 2450 formulation increased the average weight of tomatoes per harvest without statistical difference between them, but with the other treatments. The 66% fertilization with RGM 2450 plus RGM 2529 increased between 1.5 and 2.0 times the average weight of tomatoes per harvest compared to the 66% and 100% fertilizations with and without commercial biostimulant treatments, respectively. This study represents the first report demonstrating that the application of a formulation based on a mixture of B. siamensis and B. safensis in a fertilization program reduced by 33% is equivalent in productivity to a conventional fertilization program for tomato cultivation, achieving an increase in potential plant growth-promoting rizobacteria of the genus Flavobacterium. Therefore, the adoption of a combination of these bacterial strains within the framework of a 66% inorganic fertilization program is a sustainable approach to achieving greater tomato production and reducing the environmental risks associated with the use of inorganic fertilization.

Nectarine core-derived magnetite biochar for ultrasound-assisted preconcentration of polycyclic aromatic hydrocarbons (PAHs) in tomato paste: A cost-effective and sustainable approach.

A novel ultrasound-assisted magnetic solid-phase extraction coupled with gas chromatography-mass spectrometry (US-MSPE-GC/MS) was developed to detect trace amounts of polycyclic aromatic hydrocarbons (PAHs) in tomato paste, using a magnetic biochar adsorbent derived from nectarine cores. The highest extraction recovery was attained under 10 mg adsorbent mass, 30 min extraction time, 9 % (w/v) sodium chloride, and elution with 200 µL of dichloromethane. Under optimum conditions, the method demonstrated excellent linearity (R2 > 0.992) across a wide concentration range (0.01-100 ng g-1) with high sensitivity (LODs: 0.028-0.053 ng g-1, LOQs: 0.094-0.176 ng g-1) and good repeatability (RSDs <5.96 %). The application of the US-MSPE-GC/MS method was tested on four brands of real tomato paste and no PAHs were detected in unspiked samples, indicating no background contamination. This method showed high relative recoveries 88.03-98.52 %) and good reproducibility (<9.19 %.) at two concentration levels, confirming its effectiveness for PAH analysis in real samples.

Manure-biochar compost mitigates the soil salinity stress in tomato plants by modulating the osmoregulatory mechanism, photosynthetic pigments, and ionic homeostasis.

One of the main abiotic stresses that affect plant development and lower agricultural productivity globally is salt in the soil. Organic amendments, such as compost and biochar can mitigate the opposing effects of soil salinity (SS) stress. The purpose of this experiment was to look at how tomato growth and yield on salty soil were affected by mineral fertilization and manure-biochar compost (MBC). Furthermore, the study looked at how biochar (organic amendments) work to help tomato plants that are stressed by salt and also a mechanism by which biochar addresses the salt stress on tomato plants. Tomato yield and vegetative growth were negatively impacted by untreated saline soil, indicating that tomatoes are salt-sensitive. MBC with mineral fertilization increased vegetative growth, biomass yield, fruit yield, chlorophyll, and nutrient contents, Na/K ratio of salt-stressed tomato plants signifies the ameliorating effects on tomato plant growth and yield, under salt stress. Furthermore, the application of MBC with mineral fertilizer decreased H2O2, but increased leaf relative water content (RWC), leaf proline, total soluble sugar, and ascorbic acid content and improved leaf membrane damage, in comparison with untreated plants, in response to salt stress. Among the composting substances, T7 [poultry manure-biochar composting (PBC) (1:2) @ 3 t/ha + soil-based test fertilizer (SBTF)] dose exhibited better-improving effects on salt stress and had maintained an order of T7 > T9 > T8 > T6 in total biomass and fruit yield of tomato. These results suggested that MBC might mitigate the antagonistic effects of salt stress on plant growth and yield of tomatoes by improving osmotic adjustment, antioxidant capacity, nutrient accumulation, protecting photosynthetic pigments, and reducing ROS production and leaf damage in tomato plant leaves.

Discovery of steroidal alkaloid metabolites and their accumulation in pigs after short-term tomato consumption.

Studies suggest steroidal alkaloids contribute to the health properties of tomato-rich diets. Untargeted studies have detected tomato steroidal alkaloid metabolites in plasma, tissues, and urine, but concentrations remain unknown. Here we utilize UHPLC-MS/MS to characterize 31 steroidal alkaloid metabolites representing 10 unique masses, and a validated UHPLC-MS method to quantify them in blood plasma. In a two-week parallel-arm study, piglets (n = 20) were fed diets containing 10 % tomato powder or a macronutrient-matched control. Concentrations averaged to 107.7 nmol/L plasma, comprising of phase I (66 %) and phase II (4.5 %) metabolites. Primary phase I metabolites were hydroxylated isomers. MS/MS fragments (m/z 253, 271, 289) in conjunction with analysis of diet profile provided higher confidence when identifying hydroxylated metabolites. These results are the first to report quantitative levels of steroidal alkaloid metabolites in plasma, contributing to an understanding of physiologically relevant concentrations. This data is useful for contextualizing research on the health benefits of tomatoes.

Effects of phosphorus-solubilizing bacteria and biochar application on phosphorus availability and tomato growth under phosphorus stress.

BACKGROUND: Phosphorus-solubilizing bacteria (PSB) are vital in converting insoluble phosphorus into a soluble form that plants can readily absorb and utilize in soil. While previous studies have mainly focused on the extracellular secretion of microorganisms, few have explored the intricate intracellular metabolic processes involved in PSB-mediated phosphorus solubilization. RESULTS: Here, we uncovered that Ca3(PO4)2 could serve as a source of insoluble phosphorus for the PSB, Pseudomonas sp. NK2. High-performance liquid chromatography (HPLC) results indicated higher levels of organic acids released from insoluble phosphorus compared to a soluble phosphorus source (KH2PO4), with acetic acid released exclusively under insoluble phosphorus condition. Moreover, non-target metabolomics was employed to delve into the intracellular metabolic profile. It unveiled that insoluble phosphorus significantly enhanced the tricarboxylic acid cycle, glycolysis, glyoxylic acid metabolism, and other pathways, leading to the production of acetic acid, gluconic acid, oxalic acid, and citric acid for insoluble phosphorus solubilization. In our quest to identify suitable biochar carriers, we assessed seven types of biochar through the conjoint analysis of NBRIP medium culture and application to soil for 30 days, with cotton straw-immobilized NK2 emerging as the most potent phosphorus content provider. Lastly, NK2 after cotton straw immobilization demonstrated the ability to enhance biomass, plant height, and root development of Solanum lycopersicum L. cv. Micro Tom. CONCLUSIONS: Pseudomonas sp. NK2 with cotton straw biochar could enhance phosphorus availability and tomato growth. These findings bear significant implications for the practical application of phosphorus-solubilizing bacteria in agricultural production and the promotion of environmentally sustainable farming practices.

Multi-stage tomato fruit recognition method based on improved YOLOv8.

Introduction: In the field of facility agriculture, the accurate identification of tomatoes at multiple stages has become a significant area of research. However, accurately identifying and localizing tomatoes in complex environments is a formidable challenge. Complex working conditions can impair the performance of conventional detection techniques, underscoring the necessity for more robust methods. Methods: To address this issue, we propose a novel model of YOLOv8-EA for the localization and identification of tomato fruit. The model incorporates a number of significant enhancements. Firstly, the EfficientViT network replaces the original YOLOv8 backbone network, which has the effect of reducing the number of model parameters and improving the capability of the network to extract features. Secondly, some of the convolutions were integrated into the C2f module to create the C2f-Faster module, which facilitates the inference process of the model. Third, the bounding box loss function was modified to SIoU, thereby accelerating model convergence and enhancing detection accuracy. Lastly, the Auxiliary Detection Head (Aux-Head) module was incorporated to augment the network's learning capacity. Result: The accuracy, recall, and average precision of the YOLOv8-EA model on the self-constructed dataset were 91.4%, 88.7%, and 93.9%, respectively, with a detection speed of 163.33 frames/s. In comparison to the baseline YOLOv8n network, the model weight was increased by 2.07 MB, and the accuracy, recall, and average precision were enhanced by 10.9, 11.7, and 7.2 percentage points, respectively. The accuracy, recall, and average precision increased by 10.9, 11.7, and 7.2 percentage points, respectively, while the detection speed increased by 42.1%. The detection precision for unripe, semi-ripe, and ripe tomatoes was 97.1%, 91%, and 93.7%, respectively. On the public dataset, the accuracy, recall, and average precision of YOLOv8-EA are 91%, 89.2%, and 95.1%, respectively, and the detection speed is 1.8 ms, which is 4, 4.21, and 3.9 percentage points higher than the baseline YOLOv8n network. This represents an 18.2% improvement in detection speed, which demonstrates good generalization ability. Discussion: The reliability of YOLOv8-EA in identifying and locating multi-stage tomato fruits in complex environments demonstrates its efficacy in this regard and provides a technical foundation for the development of intelligent tomato picking devices.

Life cycle assessment of tomato biomass residue anaerobic digestion preceded by ethanol-based organosolv and choline chloride-based deep eutectic solvent.

Anaerobic digestion (AD) of lignocellulosic wastes (LW) has garnered substantial interest because of its notable energy and nutrient recovery, along with its potential for reducing greenhouse gas emissions. However, the LW is resistant to degradation, and its hydrolysis typically requires harsh conditions, hence the need for a pretreatment. Conducting a life cycle assessment (LCA) to evaluate the pretreatment of LW is an effective way to assess the environmental impacts associated with various pretreatment methods. This work evaluates and compares three scenarios for handling lignified tomato green waste (TGW), generated in the Greater of Agadir in Morocco, in terms of their environmental impacts and energy demand, using the LCA approach, performed with OpenLCA software. To achieve this aim, the impact of these scenarios on 11 indicators is studied. The analyzed management options include a base case scenario S0 where TGW undergoes a direct anaerobic digestion (AD), organosolv pretreatment of TGW followed by AD of the free-lignin fraction (S1), and choline chloride-based deep eutectic solvent (DES) delignification followed by AD of the free-lignin fraction (S2). The data used for the analysis comes from the Tamelast landfill, laboratory tests, literature, CML-IA baseline and Monte Carlo simulation calculations. The results obtained showed that the introduction of pretreatments in S1 and S2 mitigates significantly the environmental impact in different categories compared to S0. Scenario S2, with its enhanced recovery processes, shows the highest positive environmental contributions, despite its reliance on additional external electricity. S1 and S0 both respect energy circularity. Through this study, it has been demonstrated that chemical pretreatment of LW is energy, water and solvent-intensive and requires a large investment. It opens up perspectives for further works on pretreatment using natural DES technology, its development and its applications in the delignification of ligneous biomass on an industrial scale.