Soft fruit analysis through phenotyping
|cookielawinfo-checkbox-advertisement||1 year||Set by the GDPR Cookie Consent plugin, this cookie records the user consent for the cookies in the "Advertisement" category.|
|cookielawinfo-checkbox-analytics||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Analytics".|
|cookielawinfo-checkbox-functional||11 months||The cookie is set by GDPR cookie consent to record the user consent for the cookies in the category "Functional".|
|cookielawinfo-checkbox-necessary||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookies is used to store the user consent for the cookies in the category "Necessary".|
|cookielawinfo-checkbox-others||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Other.|
|cookielawinfo-checkbox-performance||11 months||This cookie is set by GDPR Cookie Consent plugin. The cookie is used to store the user consent for the cookies in the category "Performance".|
|CookieLawInfoConsent||1 year||CookieYes sets this cookie to record the default button state of the corresponding category and the status of CCPA. It works only in coordination with the primary cookie.|
|_GRECAPTCHA||5 months 27 days||Google Recaptcha service sets this cookie to identify bots to protect the website against malicious spam attacks.|
|ac_enable_tracking||1 month||This cookie is set by Active Campaign to denote that traffic is enabled for the website.|
|_fbp||3 months||Facebook sets this cookie to display advertisements when either on Facebook or on a digital platform powered by Facebook advertising after visiting the website.|
|_ga||1 year 1 month 4 days||Google Analytics sets this cookie to calculate visitor, session and campaign data and track site usage for the site's analytics report. The cookie stores information anonymously and assigns a randomly generated number to recognise unique visitors.|
|_gat_gtag_UA_*||1 minute||Google Analytics sets this cookie to store a unique user ID.|
|_ga_*||1 year 1 month 4 days||Google Analytics sets this cookie to store and count page views.|
|_gid||1 day||Google Analytics sets this cookie to store information on how visitors use a website while also creating an analytics report of the website's performance. Some of the collected data includes the number of visitors, their source, and the pages they visit anonymously.|
|prism_26259200||1 month||Description is currently not available.|
Soft fruit analysis through phenotyping
The Soft-Fruit Analysis project assessed the latest in plant monitoring technology through a collaboration between Rothamsted Research, FOTENIX and CHAP. It took the laboratory method of deploying colours of light to monitor subtle changes in crop samples (multispectral analysis) and translated it to operate over the plant canopy reliably.
Background: The project set out to take the use of phenotyping into a commercial growing (glasshouse/polytunnel) environment, with the aim of providing the ability for automated crop monitoring at a level currently restricted to research laboratories. With this additional information, breeders can find resistant lines in a fraction of the time, and producers can be confident in the data that informs their protective applications. The demonstration of this tool has an immediate impact on the increasing number of automation tools available for UK production, with labour intensive tasks such as harvesting and spraying now informed by enhanced insight.
Challenge: The project allowed FOTENIX’s latest DELTA Platform to be characterised and benchmarked within CHAP’s Digital Phenotyping Laboratory, before being taken into Rothamsted’s glasshouse facilities.
Initial stages focused on tailoring the system for the target crops – strawberry and tomato – where the shape has a significant impact on the currently available monitoring solutions. The refined product was then compared to the research standard equipment before a series of libraries were created, illustrated with recorded metrics such as thermal time and disease evolution; combining the latest machine learning classifications with pathology capabilities.
Methodology: Over 12 months the project produced more than 100GB in raw data, over 12 separate experimental studies, ranging from fruit ripening to powdery mildew detection. During this time the user experience was refined to minimise time spent on recording valuable information, key to training new models to enable the production industry.
Rothamsted’s contribution was led by Prof Jon West who is an expert in the surveillance of crop diseases and integrated disease management in a number of crops including tomatoes. His group worked closely with Dr. Tom Ashfield in the CHAP Fine Phenotyping Centre to generate the required plant material and with the subsequent imaging.
Rothamsted also provided the glasshouse facilities required for growing the plants.
The CHAP Digital Phenotyping Laboratory, located on the Rothamsted site, is equipped with advanced imaging technology and works with partners to automate the detection of crop biotic threats (pests, weeds and diseases), to assess their impact on plant performance, and to determine the effectiveness of control strategies. In this project the facility was sub-contracted by Fotenix to work with Rothamsted to generate the experimental material and to conduct the imaging. In additional to providing the imaging expertise and delivery, the laboratory’s 2D multispectral cameras allowed a comparison to be made between the Fotenix imager and commercially available 2D systems.
FOTENIX’s approach is simple, it uses LEDs to deploy various colours of light and records their reflection from plant samples. The innovative step is how this interaction of light is used to create the 3D shape of the plant, removing the variability and cost of modern spectral systems. This method also means that there is no need for manual sample preparation, no destructive methods or sending samples to laboratories for testing. Think of it as a diagnostic tool, similar to those used in Radiology departments, alerting producers to problems and informing insight to agronomists.
Findings: Initial scans were taken of detached fruit in order to identify regions in the spectrum on which to build the ripeness classifier (See image, 1).
These models were then applied to groups of fruit to move the currently used grades 1-6 into a 1-255 with multiple areas on each fruit possible – improving the identification of ripe fruit and inputting into crop models (See image, 2).
The system was then refined to be able to monitor fruit during the growth period in a glasshouse setting (See image, 3).
During the trials a method for detection and grading of powdery mildew was also developed (See image, 4).
The final deliverable was a commercial 3D multispectral system (DELTA) that is available for purchase from FOTENIX, with the first installed at CHAP conducted in March 2020 (See image, 5).
Conclusion: CHAP is currently running a study into the use of the technology for autonomous monitoring in indoor farming. FOTENIX is moving to moving to scale production for the DELTA system to plant breeders. The technology is also being integrated into an autonomous platform, to enable its use all over the farm, and into vertical farm lighting, to permit continuous monitoring in a closed environment.
To discuss a collaboration and/or grant for a commercially funded project, complete the form below.
© 2019 CHAP - Crop Health and Protection Limited