FACT: FRESHID - MACHINE LEARNING FOR THE MOLECULAR EVALUATION OF FRESH PRODUCE QUALITY

• Sponsoring Institution: National Institute of Food and Agriculture
• Project Status: COMPLETE
• Funding Source: AFRI COMPETITIVE GRANT
• Reporting Frequency: Annual
• Accession No.: 1026048
• Grant No.: 2021-67021-34484
• Cumulative Award Amt.: $499,730.00
• Proposal No.: 2020-08839
• Project Start Date: Mar 15, 2021
• Project End Date: Mar 14, 2025
• Grant Year: 2021
• Program Code: [A1541]- Food and Agriculture Cyberinformatics and Tools

Recipient Organization
UNIVERSITY OF FLORIDA
G022 MCCARTY HALL
GAINESVILLE,FL 32611

Performing Department
Horticulture Sciences

Non Technical Summary
Fresh fruits and vegetables are an important component of the human diet, but their quality often deteriorates before reaching consumers due to ongoing biochemical processes and compositional changes.Freshness is an important and fleeting state, and its progressive loss after harvest cannot be easily evaluated. Until now this race against time has been almost entirely subjective, mostly based on external visual criteria. To the consumer, freshness is synonymous with proximity to the harvest time and retention of nutritional value.The current lack of objective indices for definingfreshnessof fruits or vegetables limits our capacity to control product quality and leads to food waste. In the proposed work,we will combine machine learning technologies and multi-omics tools to understand post-harvest senescence and microbial spoilage of fresh produce and then develop a simple imaging approach (FreshID) to evaluate fruit and vegetable quality, particularly nutritional and texture-related attributes such as maturity, storage ability, and firmness.This proposed comprehensive research program will identify the genes, proteins and compounds that can serve asfreshness-indicators and will then use these indicators todevelop of an algorithm to accurately estimate the freshness and/or produce spoilage.The outcomes of this proposed research will provide mechanisms for early detection of poor-quality produce and, by leveraging these mechanisms throughout the food production pipeline, understand how food waste can be reduced. Additionally, the FreshID toolbox of molecular markers associated with plant senescence can be used duringbreedingfor pre-harvest traits that could delay postharvest senescence. The goals of the proposed research are advances in both basic research and applied plant science that will impactfood security and human health. The developed tool would allow a new level of post-harvest logistics, supporting availability of high-quality, nutritious, and fresh produce.

Animal Health Component

50%

Research Effort Categories

Basic

40%

Applied

50%

Developmental

10%

Classification

Knowledge Area (KA)	Subject of Investigation (SOI)	Field of Science (FOS)	Percent
201	2499	1040	50%
402	1430	2020	50%

Knowledge Area
201 - Plant Genome, Genetics, and Genetic Mechanisms; 402 - Engineering Systems and Equipment;

Subject Of Investigation
1430 - Greens and leafy vegetables; 2499 - Plant research, general;

Field Of Science
1040 - Molecular biology; 2020 - Engineering;

Keywords

fresh

machine learning

microbial

produce

indicators

Goals / Objectives
Our specific objectives are:1) Discover invisible post-harvest changes that impending senescence and microbial spoilage in vegetables and fruits using imaging analysis;2) Identify genes, protein markers and chemical compounds that indicate freshness;3) Correlatehyperspectral imaging data with freshness indicators to develop an approach, FreshID.The FreshID approach has the potential to define afreshness signaturethat occurs prior to visible deterioration.A long-term goal of the proposed research is to aid development of an innovative FreshID device that can accurately estimate the freshness of produce. The value of such a device, an imager or lens offreshness signatureslies in the ability to accurately gauge produce freshness, independent of its original harvest condition or its microbial contamination status. In addition, the FreshID toolbox including these indicators and molecular markers associated with freshness can be used in the process of breeding for delaying post-harvest degradation and extending the shelf life of vegetables and fruits.

Project Methods
Hyperspectral imaging of broccoli senescence to indicate the freshness of vegetablesThe value of hyperspectral imaging stems from its promise of being able to identify and distinguish between different materials (or chemical compositions) at a sub-pixel level. This is often accomplished through spectral unmixing analysis (that is, estimating the materials found in a scene and each pixel's percentage associated with each material). However, standard spectral unmixing analysis fails to use all available information about a scene and is generally limited to simple mixing models that do not take into account known physical realities associated with hyperspectral imagery (such as variability and locally constrained materials). Furthermore, unmixing of hyperspectral data is an ill-posed inverse problem and multiple solutions exist. Many methods have been developed to estimate solutions by constraining the solution space using sparse assumptions, geometrical constraints, and other approaches. These methods do not constrain the problem using scene-specific information to guide analysis to the right answer but, instead, constrain it based on broad assumptions.In this work, we have extensive knowledge about the objects being images and this knowledge can be leveraged to improve hyperspectral analysis and unmixing. Information such as time since harvest, nutritional content, maturity and firmness can be used to constrain the model used for unmixing and analysis. Specifically, we will develop a hierarchical Bayesian model and associated parameter estimation algorithms forSemi-Supervised Partial Membership Latent Dirichlet Allocation(sPM-LDA) for hyperspectral unmixing. The proposed sPM-LDA approach will leverage ancillary information to guide analysis, account for spectral variability, allow for localized materials/chemical compositions, and incorporate spatial information.RNA-Seq:Total RNA in samples ground in liquid N2will be extracted using TRIzol and RNeasy Plant Mini Kits (QIAGEN) and used for construction of a sub-library for multiplexing. The RNA-Seq for broccoli will be performed at the Interdisciplinary Center for Biotechnology Research (ICBR) at the University of Florida. A Biomek FXP Laboratory Automation Workstation with TRobot, which performs every aspect of liquid handling, will be used for library creation and sequencing. The platform is capable of walk-away automation of the preparation and sequencing of 200 RNA-Seq libraries a week using TruSeq RNA sample prep and NextSeq 500 system (Illumina). This equipment supports 2x 150-bp sequencing. One high output run result in ~400 million reads of sequencing.Data analysis of RNA-Seq:Sequence reads will be mapped to available genomes forBrassicaoleraceaandBrassica rapa(http://plants.ensembl.org/Brassica_oleracea&http://plants.ensembl.org/Brassica_rapa).For RNA-Seq data analysis, the Galaxy platform at UF Research Computing will be used. Workflow for read alignment will begin with fastq groomer, fastq QC, and fastq trimmer, then HISAT2 (daehwankimlab.github.io/hisat2/).Parameters will be adjusted for read lengths (typically about 150 bp for NexSeq500), but default settings will otherwise be used. Resulting bam files from HISAT2 will be analyzed for expression levels using Cufflinks, Cuffcompare, and Cuffdiff (http://bowtie-bio.sourceforge.net/index.shtml; Trapnell et al. 2012,http://cufflinks.cbcb.umd.edu/). Data will be extracted using the CummeRbund module (http://compbio.mit.edu/cummeRbund) in R (http://www.r-project.org)or blast2go (http://www.blast2go.com).Protein extraction and sample preparation:Proteinswill be extracted and purified from ground broccoli floret samples using a modified phenol extraction, followed by ammonium acetate-methanol precipitation. Eluted peptides will be ionized by a nano-electrospray source that integrates the LC-MS system. We will use the standard protocols provided by the UF-ICBR. Protein concentration in all extracts will be determined using the RC/DC™ protein assay kit and interfering compounds will be compensated for using the manufacturer's protocol. Bovine serum albumin will be employed as a standard. Proteins will be labeled using the stable dimethyl isotopes.Metabolomicsanalysis:We will prepare samples provided by UF-ICBR facilities to make compound volatiles. GC-MS-based metabolomics profiling and data analysis will be conducted by the ICBR. Integrated omics data enable the discovery of novel factors regulating the senescence and signaling pathways in broccoli.

Progress 03/15/21 to 03/14/25

Outputs
Target Audience:The primary target audience for theFACT: FreshID - Machine Learning for the Molecular Evaluation of Fresh Produce Qualityproject includes: Plant Breeders and Postharvest Biologists- Researchers developing improved fruit and vegetable cultivars with enhanced quality and extended shelf life. The molecular and computational tools developed through this project provide valuable insights for integrating postharvest traits into breeding pipelines. Data Scientists and Computational Biologists- Professionals working at the interface of agriculture and artificial intelligence. The machine learning frameworks and predictive models generated through this project are designed to be adaptable and transferable to other crops and quality-related datasets. Extension Specialists and Food Supply Chain Stakeholders- Individuals involved in the handling, storage, distribution, and marketing of fresh produce. Our tools aim to support quality monitoring and decision-making during postharvest handling and storage. Undergraduate and Graduate Students- Trainees in horticultural sciences, data science, and agri-informatics who gain exposure to interdisciplinary research combining genomics, machine learning, and postharvest biology. Federal and State Agricultural Agencies and Policymakers- Stakeholders who guide investment in agricultural research and technology development. The outcomes of this project inform strategies for reducing food waste, increasing produce quality, and supporting sustainable agriculture. Changes/Problems: Shift from Field Trials to Controlled Environment Studies: Due to unpredictable weather patterns and logistical challenges in coordinating multiple field locations, we shifted some phenotyping and freshness evaluation trials to controlled environment chambers. This allowed for more standardized and reproducible imaging and biochemical analyses, though it limited direct application to field-grown produce during this phase. Data Integration and Model Refinement Challenges: Integration of large imaging datasets with biochemical and transcriptomic data required more time and bioinformatics resources than originally anticipated. To address this, we prioritized the development of pilot models for specific crops (e.g.lettuce) before expanding to additional commodities. We also established new collaborations with computational scientists to improve model interpretability and reduce data dimensionality. No Special or Additional Reporting Requirements: As of the reporting period, there were no additional or special reporting requirements outlined in the award's Terms and Conditions beyond standard progress and financial reports. These changes were made strategically to ensure the rigor and reproducibility of results and to maximize the long-term impact of theFreshIDapproach. What opportunities for training and professional development has the project provided?TheFreshIDproject has provided valuable interdisciplinary training and professional development opportunities for students and early-career researchers across plant sciences, data science, and postharvest biology: Graduate Student Training: Graduate students received hands-on training in hyperspectral imaging, machine learning, RNA-seq data analysis, and biochemical assays to quantify freshness-related markers. Students were mentored on manuscript writing, data visualization, and scientific communication. Several students presented their research at national conferences, enhancing their visibility and networking within the scientific community. Undergraduate Research Experience: Undergraduate students participated in lab rotations and summer research projects, contributing to image annotation, sample collection, and freshness scoring. These experiences helped foster interest in STEM careers and provided mentoring on research ethics, data management, and presentation skills. Workshops and Seminars: The project team organized interdisciplinary seminars and workshops focusing on AI applications in agriculture, postharvest quality assessment, and translational plant science. These sessions were open to students, faculty, and industry stakeholders and fostered cross-disciplinary learning. Collaborative and Cross-Institutional Engagement: The project enabled collaboration with bioinformatics and engineering experts, offering team members exposure to multi-disciplinary approaches. This helped enhance their skills in computational thinking, model development, and collaborative science. Proposal Writing and Grant Development: Junior team members and postdoctoral researchers were involved in the development of follow-up grant proposals, gaining experience in articulating research objectives, broader impacts, and team coordination. Through these opportunities, theFreshIDproject significantly contributed to workforce development in agricultural AI, postharvest biology, and data-driven plant research. How have the results been disseminated to communities of interest?Results from theFreshIDproject have been actively disseminated to various communities of interest, including academic researchers, industry stakeholders, and the broader agricultural community, through the following activities: Scientific Conferences and Symposia: Key findings were presented at national and international conferences, including the American Society for Horticultural Science (ASHS), the International Horticultural Congress (IHC), and the USDA AI in Agriculture Summit. These presentations reached researchers, educators, and extension professionals in horticulture, plant science, and data science. Peer-Reviewed Publications: Project results have been published in peer-reviewed journals, making them accessible to the academic community. Additional manuscripts are in preparation, covering the development of imaging-based freshness models and the identification of molecular freshness markers. Workshops and Extension Events: The research team delivered invited talks and organized educational workshops that introduced FreshID tools and findings to postharvest specialists, growers, and supply chain partners. These events encouraged knowledge transfer and stakeholder feedback. Outreach to Breeders and Industry Partners: The project team shared preliminary results and potential applications of the FreshID system with breeders and industry collaborators to explore integration into variety selection and storage decision-making processes. Student Presentations and Posters: Graduate and undergraduate students presented posters and oral presentations at local research symposiums and student competitions, broadening awareness among future scientists and practitioners. Digital Platforms and Collaborative Networks: A project website and digital materials were used to communicate progress and updates. Participation in cross-institutional networks such as the NIFA AI Research Coordination Network and FFAR's Fresh Produce Consortium has further extended reach and collaboration. These dissemination efforts have ensured that the knowledge generated throughFreshIDis accessible, actionable, and relevant to the communities best positioned to apply it. What do you plan to do during the next reporting period to accomplish the goals? Nothing Reported

Impacts
What was accomplished under these goals? During the project period, substantial progress was made across all major objectives of theFreshIDinitiative. Below are key accomplishments: Scientific Publications: Multiple manuscripts were prepared and submitted that detail our findings on the integration of hyperspectral imaging with biochemical and molecular freshness indicators. One peer-reviewed publication was accepted and published in a high-impact journal, focusing on the early detection of senescence-related traits using imaging and machine learning tools. Additional manuscripts are in preparation, particularly those addressing gene expression and compound profiling associated with freshness loss. Conference Presentations: Findings from the project were presented at several national and international conferences, including the American Society for Horticultural Science (ASHS) and the International Society for Horticultural Science (ISHS). A featured presentation on the FreshID concept and preliminary results was given at the USDA AI in Agriculture Summit, drawing attention from both research and industry audiences. Graduate and undergraduate researchers involved in the project presented posters and talks, increasing student engagement and training. Additional Grant Applications: Building on preliminary FreshID results, we submitted a competitive proposal to the USDA NIFA-SCRI program to scale the project for commercialization and breeder integration. A collaborative grant proposal was submitted to the NSF Smart and Connected Communities program, extending the FreshID framework to smart packaging and consumer engagement. New partnerships were formed with industry and academic collaborators, enabling the submission of a multi-institutional proposal to the Foundation for Food & Agriculture Research (FFAR) focused on predictive freshness and waste reduction tools. Overall, the FreshID project laid a strong foundation for the development of a molecular and imaging-based toolbox for postharvest freshness evaluation. These accomplishments have positioned the team for continued innovation in sensor-based produce quality assessment, plant breeding support, and postharvest loss reduction.

Publications

• Type: Peer Reviewed Journal Articles Status: Published Year Published: 2025 Citation: Metabolomic profiling of pulp from three passion fruit varieties: Implications for postharvest quality and nutritional value E Garcia, MRA Miranda, X Liu, A Sarkhosh, Y Wang, T Liu Postharvest Biology and Technology 229, 113689
• Type: Peer Reviewed Journal Articles Status: Published Year Published: 2025 Citation: Blueberry ripening mechanism: a systematic review of physiological and molecular evidence JM Zapien-Macias, T Liu, GH Nunez Horticulture Research, uhaf126
• Type: Peer Reviewed Journal Articles Status: Published Year Published: 2024 Citation: Morphological and genetic characterization of the muscadine fruit abscission zone AR Brinley, PJ Conner, F Yu, A Sarkhosh, T Liu Horticulture Research 11 (10), uhae227

Progress 03/15/23 to 03/14/24

Outputs
Target Audience:Many vegetables and fruit are sensitive to storage at lower temperatures and experience chilling injury that can result in internal disorder, leading to postharvestwaste and economic loss. Most tropical and subtropical fruit, such as avocado and mango, are sensitive to cold storage and can develop chilling injury with symptoms such as abnormal ripening, skin pitting, and darkening of the mesocarp. The severity of chilling injury symptoms is determined by various factors, including the cultivar, the storage temperature, and the length of cold exposure. The object of this study was to develop a method for estimation of internal chilling injury in avocado using hyperspectral imaging (HSI). Hyperspectral images of the avocado surface were obtained with a hyperspectral camera over the wavelength range of 400nm to 1000nm with 2nm resolution. Using estimated functions of multiple instances (eFUMI) and hyperspectral unmixing approaches, we identified the spectra that correlated with areas of internal injured. By quantifying injured areas and fruit firmness, we showed the association between the internal and the external changes as detected by HSI, which implied that HSI has the potential to be used to monitor internal disorder of avocado. HSI technology opens the possibility of non-destructive determination of chilling injury and other internal quality attributes in horticultural and food products. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?Three PhD students have been trained working on this project. Over 10 undergraduate and 2 high school students worked on this project in 2023. How have the results been disseminated to communities of interest?Our publications and conference proceedings and research presentations have drawn a lot of attension from scientists, stakeholders, and reporters. A couple of examples of medium report: UF/IFAS News: The title of the news report is'UF scientists plan to lengthen the shelf life of artichokes' The link to this report: https://blogs.ifas.ufl.edu/news/2024/03/05/uf-scientists-plan-to-lengthen-the-shelf-life-of-artichokes/ The Packer Magazine: https://www.thepacker.com/news/produce-crops/university-florida-researchers-look-extend-artichoke-shelf-life The Special Crop Grower magazine: Title of report: 'UF/IFAS Scientists Hope to Lengthen Shelf Life of Artichokes. https://specialtycropgrower.com/florida-uf-ifas-artichoke/ UF/IFAS News: The title of the news report is'UF scientists start to discover how to keep fruits and vegetables fresher before they arrive at the grocery store' The link to this report: https://blogs.ifas.ufl.edu/news/2023/09/07/uf-scientists-start-to-discover-how-to-keep-fruits-and-vegetables-fresher-before-they-arrive-at-the-grocery-store/ CBS4 news: Interview with CBS4 news on Dec 30, 2022,one of the local news stations in Gainesville. The reporter Massiel Leyva interviewed me about keeping produce fresh. https://mycbs4.com/news/local/expert-shares-tips-to-reduce-food-waste WCJB-TV20 news: The television channel was interested in covering this projectfor the station's What's Growing On segment. They have interviewed me. TV20 segment aired this project on May 13, 2021. The title of TV news is "What's Growing On: Scientists developing technology to read produce freshness signals." What do you plan to do during the next reporting period to accomplish the goals?We will continue publish research aricles and train graduate studnets and udnergraduate students towards the goals of this grant.

Impacts
What was accomplished under these goals? In the past year, we have 1. Discover invisible post-harvest changes that impending senescence in postharvest broccoli and avocado. 2.Identify genes, protein markers and chemical compounds that indicate freshness of postharvest broccoli. 3.Correlatehyperspectral imaging data with freshness indicators to develop an approach to characterize chilling injury in avocado fruit. We have published three peer-reviewed articles and two extension related peer-reviewed EDIS articles. We submit 6 abstract in international and nation conferences.

Publications

• Type: Journal Articles Status: Published Year Published: 2023 Citation: Xiaolei Guo, Chiwah Tseung, Alina Zare, Liu T. (2023) Hyperspectral Image Analysis for the Evaluation of Chilling Injury in Avocado Fruit during Cold Storage. Postharvest Biology and Technology. https://doi.org/10.1016/j.postharvbio.2023.112548
• Type: Journal Articles Status: Published Year Published: 2023 Citation: Utsab Ghimire, Eleni Pliakoni, Fahong Yu, Jeffrey K. Brecht, Liu T (2023) Identifying genes regulated during natural, on-plant senescence in broccoli (Brassica oleracea) in contrast to postharvest senescence. Postharvest Biology and Technology. 1206, 112535. https://doi.org/10.1016/j.postharvbio.2023.112535
• Type: Journal Articles Status: Published Year Published: 2023 Citation: Habibi F, Liu T, Muhammad S, Schaffer B, Sarkhosh A. (2023) Physiological, Biochemical, and Molecular Responses of Fruit Trees to Rootzone Hypoxia. Environmental Experimental Botany. 206, 105179. https://doi.org/10.1016/j.envexpbot.2022.105179
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Liu T, Ghimire U G, Pliakoni E, Agehara S., Brecht, J. (2023) Development of Innovative Tools for Understanding Postharvest Senescence in Ornamental Vegetables. The Postharvest Unlimited Conference. Wageningen, Netherlands.
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Liu T, Utsab GhimireG, Eleni Pliakoni, Jeffrey Brecht. (2023) Study the Mechanisms of Ethylene Action during Postharvest Senescence in Broccoli. XII International Symposium on the Plant Hormone Ethylene (Ethylene 2023). Toulouse, France.
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Brinley AG, Sarkhosh A., Conner P., Liu T. (2023) Genetic characterization of berry abscission zone in Muscadine. The American Society for Horticultural Science Conference Proceeding. Orlando, FL.
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Ghimire UG., Pilakoni E., Brecht J., Liu T. (2023) Senescence-Associated Genes (SAG) between natural and postharvest senescence. Functional characterization of The American Society for Horticultural Science Conference Proceeding. Orlando, FL.
• Type: Other Status: Published Year Published: 2023 Citation: Garcia EG, Sarkhosh A., Liu T. (2023) Proteomes of distinct tissues of Passiflora edulis fruit reveals key proteins and pathways during postharvest shelf life. Proceeding Florida State Horticulture Society.
• Type: Other Status: Published Year Published: 2023 Citation: Brinley AG, Sarkhosh A., Conner P., Liu T. (2023) Genetic characterization of berry abscission zone in Muscadine. Proceeding Florida State Horticulture Society.
• Type: Other Status: Published Year Published: 2023 Citation: Chase KG., Belisle C, Sargent S, Sandoya G, Huang C, Begcy K. Liu T. (2023) Examining preharvest genetic and morphological factors contributing to lettuce (Lactuca sativa L.) shelf life. Proceeding Florida State Horticulture Society.
• Type: Theses/Dissertations Status: Published Year Published: 2023 Citation: Chase KG. Characterization of senescence associated genes in Lactuca sativa with respect to shelf life.
• Type: Other Status: Published Year Published: 2023 Citation: Sharma S., Huo H., Vondracek KG., Liu T, and Lee S. (2023) Current Status of Research, Regulations, and Future Challenges for CRISPR Gene Editing in Crop Improvement. EDIS
• Type: Other Status: Published Year Published: 2023 Citation: Garcia E., Sarkhosh A., Liu T. The Emerging Industry in Passion Fruit in Florida.

Progress 03/15/22 to 03/14/23

Outputs
Target Audience:The targeted audiences included students,reesearchers, farmers, local growers, stake-holders.This study constitutes a proof-of-concept for a new, innovative approach to identify the true physiological age of fresh produce as a measure of freshness, quality, and remaining postharvest life that has thus far been out of reach. The project has contributed to the following project: a. USDAMulti-State project: NE1836: Improving Quality and Reducing Losses in Specialty Fruit and Vegetable Crops through Storage Technologies. Duration 10/01/2023 to 09/30/2028Duration 10/01/2023 to 09/30/2028 b.USDA Multi-State project: N-294: Improving Quality and Reducing Losses in Specialty Fruit and Vegetable Crops through Storage Technologies. Duration 10/01/2023 to 09/30/2028. c. It has drawn attention from local news, TV station, Padcast channel. The full list can be found at the Product section. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided? We have provided machine learning and genomics analysis training for graduate students and undergraduate students. Threegraduate students and more than seveundergraduate students have been recruited and conduct internships to this project. The PD has contributed and taughtFreshID projectrelated online course. How have the results been disseminated to communities of interest? The project has drawn considerable attention to communities including newspapers (Fresh Grower etc), TV station 20 (CBS4 news), news report (The Growing Produce, The Morning AgClips etc), Podcast. The entire list can be found in the 'Target Audience' sections. What do you plan to do during the next reporting period to accomplish the goals? We are going to submit tworesearch article and one review article related to this project in2023. The results of this project will be presented in local, national and international conference as well as extension related workshops for local growers, farmers and consumers. We will collaborate with industry personel to devlelop FreshID App and easy-accessibel device to measure freshness of vegetables and fruit.

Impacts
What was accomplished under these goals? Under these goals, what we have accomplished are listed below: 1. We have one manuscript using Fresh ID tools that has been revised and wait for the final decision. 2. We are working on three manscripts and two of them should be submitted within 1-2 months. 3. We also prepare one methodolgy and one review article on this project.

Publications

• Type: Journal Articles Status: Submitted Year Published: 2023 Citation: Xiaolei Guo, Alina Zare, and Liu T. (2023) Hyperspectral imaging analysis for the evaluation of chilling injury in postharvest avocado fruit. Postharvest Biology and Technology.
• Type: Journal Articles Status: Published Year Published: 2022 Citation: Yogesh Ahlawatf, Song Li, Eleni D. Pliakoni, Jeffrey Brecht, Liu T. (2022). Identification of senescence-associated genes in broccoli (Brassica oleracea) following harvest. Postharvest Biology and Technology. 183, 11729.
• Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Chase K., Belisle C, Sargent S, Sandoya G, Huang C, Begcy K. Liu T. (2022) Characterization of senescence associated genes in Lactuca sativa with respect to shelf life. Florida Society for Horticultural Science.
• Type: Conference Papers and Presentations Status: Published Year Published: 2022 Citation: Garcia E, Liu T. (2022) Establishing gene editing technology to generate seedless passion fruit. The American Society for Horticultural Science Meeting.
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Xiaolei Guo, Alina Zare, and Liu T. (2023) Deep Interactive Annotation to Support Hyperspectral Image Analysis.NAPPN (North American Plant Phenotyping Network).
• Type: Conference Papers and Presentations Status: Published Year Published: 2023 Citation: Liu, T., Guo X., Zare A. (2023). Imaging-based Machine Learning for Evaluating Freshness of Fruit and Vegetables. The PAG30 Plant & Animal Genome Meeting. San Diego, CA

Progress 03/15/21 to 03/14/22

Outputs
Target Audience:In this work, we identified candidate transcripts and related proteins that accurately reflect the physiological age or freshness during postharvest handling of broccoli (Brassica oleracea L.), other Brassica crops, and eventually additional unrelated species. The long-term goal of the proposed research is to aid development of an innovative tool to accurately estimate the freshness of produce. Such a tool would allow a new level of postharvest logistics, supporting availability of high-quality, nutritious, fresh produce. This pilot study constitutes a proof-of-concept for a new, innovative approach to identify the true physiological age of fresh produce as a measure of freshness, quality, and remaining postharvest life that has thus far been out of reach. This project has drawn considerable attentions. The major impacts includes: WCJB-TV20 news:The television channel was interested in covering this projectfor the station's What's Growing On segment. They have interviewed me. TV20 segment aired this project on May 13, 2021. The title of TV news is "What's Growing On: Scientists developing technology to read produce freshness signals." Here is the link:https://www.wcjb.com/2021/05/13/whats-growing-on-scientists-developing-technology-to-read-produce-freshness-signals/ Gainesville Sun newspaper:The title of this news report is 'Can't tell when fruits and veggies are going bad? UF researchers want to help'. The link to this report: https://www.gainesville.com/story/news/education/campus/2021/05/15/uf-ifas-and-engineering-scientists-study-food-decay-combat-waste/5071303001/ The Villages Daily Sun.The title of this news report is 'Florida trends: Preventing food waste and loss'. The link to this report: https://www.thevillagesdailysun.com/news/in_todays_daily_sun/florida-trends-preventing-food-waste-and-loss/article_7692238e-b142-11eb-a9c7-f382c7d5be2f.html Growing Produce: The title of the news report is 'How a Peek Inside Broccoli Genes Might Help Solve Food Waste Plight'. The link to this report: https://www.growingproduce.com/production/how-a-peek-inside-broccoli-genes-might-help-solve-food-waste-plight/ The Dailyadvant News: The title of the news report is 'How a Peek Inside Broccoli Genes Might Help Solve Food Waste Plight'. The link to this report: https://www.dailyadvent.com/news/9098ba2043f738da3da7dc3b84626cfe-How-a-Peek-Inside-Broccoli-Genes-Might-Help-Solve-Food-Waste-Plight The Growing America: The title of the news report is 'Fighting food waste: Researchers identify broccoli genes that affect freshness'. The link to this report: https://www.growingproduce.com/production/how-a-peek-inside-broccoli-genes-might-help-solve-food-waste-plight/ The Morning AgClips:The title of the news report is 'Fighting food waste: Researchers identify broccoli genes that affect freshness'. The link to this report: https://www.morningagclips.com/fighting-food-waste-researchers-identify-broccoli-genes-that-affect-freshness/ The Vegetables and Speciality Crops News (VSCnews): The title of the news report is 'Fresh Produce: How UF Scientists Are Using AI to Cut Food Waste, Loss'. The link to this report: https://specialtycropindustry.com/fresh-produce-florida-ai/ The News Break: The title of the news report is 'UF Scientists Use AI To Cut Food Waste'. The link to this report: https://www.newsbreak.com/news/2240387533315/uf-scientists-use-ai-to-cut-food-waste UF/IFAS News: The title of the news report is 'From Yellowed Broccoli to Mushy Avocados: How UF Scientists Are Using AI to Cut Food Waste, Loss'.The link to this report: http://blogs.ifas.ufl.edu/news/2021/05/04/how-uf-scientists-are-using-ai-to-cut-food-waste-loss/ UCDavis Postharvest Technology center "Research Highlights" newsletter. Changes/Problems: Nothing Reported What opportunities for training and professional development has the project provided?We have provided machine learning and genomics analysis training for graduate students and undergraduate students. Two graduate students and more than five undergraduate students have been recruited to this project. The PD has contributed to AI related online course, How have the results been disseminated to communities of interest?The project has drawn considerable attention to communities including newspapers (The Gainesville Sun, The Villages Daily Sun), TV station 20 (WCJB-TV20 news), news report (The Growing Produce, The Morning AgClips etc), Podcast (Streaming Science Podcast 2022). The entire list can be found in the 'Target Audience' sections. What do you plan to do during the next reporting period to accomplish the goals?We are going to submit two one research article and one review article related to this project in fall 2022. One of patent was under review right now. The results of this project will be presented in local, national and international conference as well as extension related workshops for local growers, farmers and consumers. We will collaborate with industry personel to devlelop FreshID App and easy-accessibel device to measure freshness of vegetables and fruit.

Impacts
What was accomplished under these goals? Under these goals, what we have accomplished are listed below: 1. We published one research article on the journal of Plant Phenomics to study freshness signature using AI and hyperspectral imaging; 2. We has published one review aricle on the journal of Frontier in Genetics; 3. Both transcriptional and proteomics analysis have been performed. A number of genes and proteins have been identified for freshness signature that will be tested in the second year; 4. One patent has been under reviewed.

Publications

• Type: Journal Articles Status: Published Year Published: 2022 Citation: X Guo, Y Ahlawat, Liu T. A Zare, (2022) Evaluation of Postharvest Senescence in Broccoli Via Hyperspectral Imaging. Plant Phenomics. https://spj.sciencemag.org/journals/plantphenomics/2022/9761095/
• Type: Journal Articles Status: Accepted Year Published: 2022 Citation: Liu T. Albornoz K., Deltsidis A., Beckles, D. (2022) Editoral: Postharvest Ripening, Senescence, and Technology. Frontier in Genetics. https://www.frontiersin.org/articles/10.3389/fgene.2022.920584/full
• Type: Conference Papers and Presentations Status: Accepted Year Published: 2022 Citation: Liu, T., Guo X., Zare A. (2022). Imaging-based Machine Learning for Evaluating Freshness of Fruit and Vegetables. The XXIX Plant & Animal Genome Meeting. San Diego, CA
• Type: Conference Papers and Presentations Status: Accepted Year Published: 2022 Citation: Liu, T., Guo X., Zare A. (2022). Machine Learning for the Molecular Evaluation of Fresh Produce Quality. XXXI International Horticultural Congress, August 14-20, 2022 - Angers, France.
• Type: Conference Papers and Presentations Status: Accepted Year Published: 2022 Citation: Liu, T., Guo X., Zare A. (2022). Machine Learning for Evaluating Freshness of Fruit and Vegetables. The XXIX Plant & Animal Genome Meeting. San Diego, CA
• Type: Conference Papers and Presentations Status: Accepted Year Published: 2021 Citation: Liu T. (2021) Molecular Evaluation of Fresh Produce. Horticulture Research online webinar
• Type: Conference Papers and Presentations Status: Accepted Year Published: 2021 Citation: Liu T. (2021) Machine Learning for the Molecular Evaluation of Fresh Produce. American Society of Horticultural Sciences (ASHS) Annual Conference.