16AGRITECHCAT5: Tools and Technology for Predicting Tomato Glasshouse Production

UK sales of fresh tomatoes are valued at £625M with UK production providing £175M worth of these sales. Current estimations used to predict production are within 10% correct only 30% of the time. Over-estimation of production results in costly imports, whilst under-estimation incurs financial losses from the disposal of surplus fruit. There is considerable potential to reduce waste and financial losses, and increase the proportion of UK sales by improving the accuracy of weekly production forecasts. We will develop a glasshouse-based imaging system TomVision that is fully automated to predict future production.

The proposed scientific and technological innovations represents leading edge applied science and engineering and have not been developed by others for glasshouse production. The consortium will: 1) develop TomVision, an imaging system to count fruit and determine their ripeness; 2) develop an automated platform for TomVision to image fruit in a glasshouse; 3) refine mathematical models to predict production based on the image data generated and future weather conditions (PredictTomPro); 4) test and run the system in UK and NL glasshouses prior to product launch.

We will deliver a system that will lead to greater efficiency in the use of resources, improved productivity from waste reduction and improved grower margins from more accurate production forecasts. We anticipate UK revenue gains of £6M p. a. (£30K/ha) farm gate value by adoption of the outputs and further income to project partners by sales of TomVision and PredictTomPro (£1.3M/£11.7M/£26M UK/NL/W total sales for tomato production).

The route to market will be via roll-out to other UK tomato growers and overseas partners in the first instance, then to other UK, EU and worldwide producers of tomato towards advancing sustainable intensification and delivering economic impact. The proposed project meets all the requirements of duration, project size, business involvement and RTO lead and funding balance for an Agri-Tech Catalyst Industrial Research Award.



NIAB-EMR will be carrying out their research as a RTO requiring 100% FEC.

We aim to develop a commercial prototype of Tomvision an imaging system and PredictTomPro, mathematical software, that will predict the ripeness of intensively grown tomatoes under commercial production. This system will be able to navigate in the glasshouse in an autonomous way.

To do this we will:
1) Mathematically model the rate of tomato ripening in commercial conditions and relate this too the internal and external environmental conditions.
2) Generate TomVision, an image capture device, that can automatically collect and analyse images that will provide discrete values of the ripeness of tomatoes.
3) Provide mathematical models of ripening linking the image data, yield collected and environmental data. The models developed will be iteratively improved and tested as more data is generated.
4) Develop yield prediction models by incorporating future weather forecast data with the rate of ripening models previously generated.
5) Design and build a platform for the imaging technology so that it is able to move throughout a glasshouse in an automatic/semi-automatic way.
6) Carry out commercial scale trails of the TomVision prototype in the UK and in the Netherlands. Refining the prediction models based on the data obtained.





NIAB-EMR will be carrying out their research as a RTO requiring 100% FEC.

Our collaborative research between academia and industry is aimed at improving the efficiency of tomato production leading to less waste and increased revenues.

WHO WILL BENEFIT AND HOW?
OUR CONSORTIA
Firstly our consortia will benefit in applying our collective research experience to generate a working commercial prototype of TomVision; a system that will predict future tomato yields. This research and development will enable the generation of new ideas and new analytical equipment. It will provide training of researchers in interdisciplinary activities, the development of new techniques and the use of state of the art tools and technology.
More specifically the impact on Thanet Earth will be the competitive advantage of being the first adopters of this technology and the £540K pa savings that they can gain in their tomato production.
The project will allow RailVision to develop new capability in the area of tomato fruit detection and counting which is fundamental for any production calculations. This new IP will support the development of a new line of products for yield prediction with NIAB-EMR, and will also open up new opportunities for other types of fruit production forecasting in glasshouse environments. The new products based on this study will further strengthen RV's presence as a key player in the automated machine vision systems for glasshouse crop monitoring sector, and provide new sources of income not possible otherwise.
The impact to NIAB-EMR will be in developing new models and enhancing modelling skills that will be deployed on other projects. It will ensure retention of staff and strengthen links with industry in developing technologies for precision agriculture.

GROWERS
The key driver for TomVision is the savings growers will make (£30K/ha), in reducing waste and gaining more value from the supply chain. This will help ensure TE remains as leading one of the leading UK tomato producers in a highly competitive market. Once the system is rolled out to all growers they will all benefit from the reduced waste and more profitable supply chain.

PRODUCE RETAIL
Retailers will gain from the strong UK market for fresh tomatoes enabling increased premium of product sales.

PUBLIC
The public will benefit from less waste and more resilient UK supply chain of tomatoes.

LABOUR
The additional impact will be via employment of personnel working on this project and the future personnel required for R&D of the system, sales and support.
Other key beneficiaries include academics and the wider research community. They will gain from the research insights into ripening and the models of predicting future tomato production. More specifically subject to prior commercial protection and agreement form the consortia they will be able to utilise the data that we will generate in modelling fruit ripening and experimental results that will be provided by scientific publications and presentations at scientific meetings.



NB NIAB-EMR will be carrying out their research as a RTO requiring 100% FEC.