Food Protection Trends - November/December 2024 - 406

for a given investment). Food safety is a unique business
aspect because, while required, it is often seen as a cost
center; a reduction in food safety risk rarely leads to a
quantifiable direct increase in profits, but rather a reduction
in potential capital lost through a food safety incidence (e.g.,
a recall). Research geared towards identifying a connection
between reduction in food safety risk or recall risk and profits
may help with decision making on AI implementation and
incentivize companies to invest in shifting their food safety
strategy towards AI and digital tools. At the same time,
changes in the legal environment are needed to alleviate
the barriers to adopting these technologies, for example to
alleviate industry concerns about the potential increase in the
liability and expense from using food safety predictions and
knowledge generated by AI and digital tools (1).
CONCLUSIONS
While it is enticing to conclude that AI for microbial
food safety is a wise application for CEA due to the
industry's reputation as being " high-tech, " there are still
many challenges that need to be overcome prior to the
adoption of this technology. Namely, there is an effort
needed from academia and industry to (i) research and
better understand the contamination sources, routes and
microbial environment of known and unknown pathogens
in a variety of CEA facilities, (ii) implement stronger, basic
facility hygiene and sanitation practices and (iii) generate
vast amounts of high quality data sources. Additionally, the
creation of AI models needs to take into account the wide
range of CEA facilities and data infrastructures and, through
this, the vast amounts of private data required to be shared.
REFERENCES
1. Alexander, C. S., A. Smith, and R. Ivanek.
2023. Safer not to know? Shaping liability
law and policy to incentivize adoption of
predictive AI technologies in the food system.
Front. Artif. Intell. Frontiers 6.
2. Allende, A., M. I. Gil, and P. Truchado.
Occurrence and transfer of pathogens from
the production environment to leafy greens
grown in controlled environment agriculture.
3. Barnett-Neefs, C., G. Sullivan, C. Zoellner,
M. Wiedmann, and R. Ivanek. 2022. Using
agent-based modeling to compare corrective
actions for Listeria contamination in produce
packinghouses. PloS One 17(3):e0265251.
4. Barnett-Neefs, C., M. Wiedmann, and
R. Ivanek. 2022. Examining patterns
of persistent Listeria contamination in
packinghouses using agent-based models. J.
Food Prot. 85:1824-1841.
5. Belias, A., G. Sullivan, and M. Wiedmann.
2021. Root cause analysis can be used to
identify and reduce a highly diverse Listeria
population in an apple packinghouse: A case
study. Food Prot. Trends 41:555-567.
6. Benke, K., and B. Tomkins. 2017. Future
food-production systems: vertical farming
and Controlled Environment Agriculture.
Sustain. Sci. Pract. Policy. Taylor & Francis
13:13-26.
7. Berg, G., and T. Cernava. 2022. The plant
microbiota signature of the Anthropocene
as a challenge for microbiome research.
Microbiome 10:54.
8. Beyan, O., A. Choudhury, J. van Soest, O.
Kohlbacher, L. Zimmermann, H. Stenzhorn,
Md. R. Karim, M. Dumontier, S. Decker, L.
O. B. da Silva Santos, and A. Dekker. 2020.
Distributed analytics on sensitive medical
data: The personal health train. Data Intell.
2:96-107.
9. Bihn, E. A., and S. Reiners. 2018.
Good Agricultural Practices and Good
Manufacturing Practices for vegetable
production, p. 109-134. In handbook of
vegetables and vegetable processing. John
Wiley & Sons, Ltd.
10. Bo, Y., Y. Zhang, K. Zheng, J. Zhang, X.
Wang, J. Sun, J. Wang, S. Shu, Y. Wang, and
S. Guo. 2023. Light environment simulation
for a three-span plastic greenhouse based on
greenhouse light environment simulation
software. Energy 271:126966.
406 Food Protection Trends November/December
11. Callens, K., F. Fontaine, Y. Sanz, A.
Bogdanski, K. D'Hondt, L. Lange, H. Smidt,
L. van Overbeek, T. Kostic, E. Maguin, A.
Meisner, I. Sarand, and A. Sessitsch. 2022.
Microbiome-based solutions to address
new and existing threats to food security,
nutrition, health and agrifood systems'
sustainability. Front. Sustain. Food Syst.
Frontiers 6.
12. Calvo‐Bado, L. A., G. Petch, N. R. Parsons,
J. A. W. Morgan, T. R. Pettitt, and J. M.
Whipps. 2006. Microbial community
responses associated with the development
of oomycete plant pathogens on tomato roots
in soilless growing systems. J. Appl. Microbiol.
100:1194-1207.
13. Castro-Ibáñez, I., F. López-Gálvez, M. I.
Gil, and A. Allende. 2016. Identification of
sampling points suitable for the detection
of microbial contamination in fresh-cut
processing lines. Food Control 59:841-848.
14. Centers for Disease Control. 2021. CDC:
Salmonella outbreak linked to BrightFarms
packaged salad greens. Cent. Dis. Control
Prev. Available at: https://www.cdc.gov/
salmonella/typhimurium-07-21/details.html.
Accessed 22 December 2023.
While there are opportunities (such as the use of federated
learning) to circumvent data privacy, the large majority of
private firms are still reluctant to share confidential data. The
range of CEA facilities not only makes it challenging to have
one model fit multiple firms but it also poses the challenges
of (i) data from different systems " being able to talk to each
other " and (ii) application of AI models into systems with
ranges of technological maturity. AI for microbial food safety
in CEA is most likely utilized best towards specific food
safety related challenges, such as validating clean breaks
between lots, and allowing for targeted and specific microbial
sampling plans to capture rare but serious contamination
instances. Finally, it is important to remember that while AI
can be seen as an attractive " fits all solution " , food safety risks
carry numerous interdisciplinary and intricate consequences
for both firms and consumers, and ultimate decisions
regarding such risks should be made by humans.
ACKNOWLEDGMENTS
This research was supported in part by the intramural
research program of the U.S. Department of Agriculture,
National Institute of Food and Agriculture, 2023-6702138909.
Authors A. A. and M. G. acknowledge the support
provided by the Spanish Ministry of Science, Innovation
and Universities (Project PID2022-141708OB-I00). The
findings and conclusions in this publication have not been
formally disseminated by the U.S. Department of Agriculture
and should not be construed to represent any agency
determination or policy. Partial support was also received
from the Cornell Institute for Digital Agriculture (CIDA).
https://www.cdc.gov/salmonella/typhimurium-07-21/details.html https://www.cdc.gov/salmonella/typhimurium-07-21/details.html
Food Protection Trends - November/December 2024

Table of Contents for the Digital Edition of Food Protection Trends - November/December 2024
