1MG FlippingBooks
Rooting Out Plant Diseases: Are Computers Ready To Run Our Farms?
Published with permission from Charles Darwin University
Nature is still too complex for artificial intelligence (AI) modelling to be effective, but the tipping point is close, according to a new study that found the technology may still trip at the last real-world hurdle.
The study into how AI can help protect crops from diseases and improve food security by identifying diseases and forecasting outbreaks, has revealed that most AI models that work in the computer lab are overwhelmed when put into the field.
There is growing interest in using AI in crop protection because infectious plant diseases, if unchecked, can compromise anywhere from 10 to 40 per cent of a farm’s crop yield depending on the disease. The diseases could cause nutritional deficiencies among crops typically rich in vitamins and minerals.
In recent years, machine and deep learning algorithms have served as the backbone of mobile applications, drone-base monitoring, automated irrigation and treatment systems, and precision agriculture platforms that have advanced to reliably recognise budding diseases.
But in-field applicability remains one of the major challenges faced by the growing technology.
Study supervisor Dr Thuseethan Selvarajah, a CDU Lecturer in Information Technology, said real-world agricultural scenarios were often more complex than AI models are capable analysing, leading to misdiagnoses and inappropriate treatment recommendations.
Dr Selvarajah said the study highlighted the need to develop diverse, real-world plant disease datasets that capture the variability in crop types, disease stages, and environmental conditions to train AI models.
“Some of the more common field issues that affect an AI model’s accuracy include changes in lighting, overlapping leaves, background clutter, and inconsistent image quality,” he said.
“Techniques like data augmentation, domain adaptation, and training AI models to handle noise and distortions would help overcome this, but it’s also important to create lightweight and efficient deep learning models that can be used on resource-limited devices like smartphones and drones.
“In regions like Darwin and across the Northern Territory where network coverage can be limited, deploying AI models directly on mobile devices is critical because it allows farmers to access these tools without needing a constant internet connection.”
University of Peradeniya PhD candidate Romiyal George, who led the study, said healthy crops were crucial for feeding communities, preserving biodiversity, and supporting economic development around the world but the growing threat of plant diseases puts all of this at risk.
Mr George said farmers had historically relied on visual inspection of crops to monitor the presence of plant diseases – a method that is time-consuming, costly, and often inaccurate.
“A deep learning model trained on images of plant leaves showing different stages of disease can spot early signs of infection with high accuracy,” he said.
Catching these symptoms early is crucial because traditional visual checks often miss them until the disease has already advanced, leading to more severe crop loss.
“In comparison, AI systems powered by deep learning can provide immediate feedback, helping farmers make quicker and better decisions.”
This research was published in Computers and Electronics in Agriculture and contributes to Goal 2 of the United Nations Sustainable Development Goals, which relates to zero hunger.
NEWS
Prodoz, a Proudly Australian and family-owned agribusiness, based in Melbourne, is strengthening its positions as national/international leader in advanced crop – science solutions through a growing portfolio of global innovation partners and a distribution footprint supported by all major distributors - includes Nutrien Ag, Elders, Lindsay Rural and Independent Rural stores.
Australia’s climate is tougher than ever. Heat spikes, dry periods, salinity, waterlogging and sudden frost events are becoming an everyday part of farmers lives.
Trace minerals are required for optimal growth, reproduction, and immunity. Optimising trace mineral status relying solely on oral supplements across a herd may fail because of variation in individual intake and reduced absorption due to antagonism of other ration components and minerals. The use of injectable trace mineral supplements has been associated with positive reproductive outcomes including improved conception rate, increased odds of pregnancy and greater final in calf rate. A study conducted on 2,168 dairy cows, administered injectable trace minerals, four weeks prior to calving and again four weeks prior to the start of mating showed treated animals had a 3.3 per cent greater final in-calf rate, and a reduced time from start of mating to conception, compared to control animals 1 . The Importance of B12 Dr Carl Eden, Technical Services Veterinarian with Boehringer Ingelheim says “Vitamin B12 is sometimes referred to as a ‘super vitamin’ because it is only required in very small amounts but vital to many essential metabolic pathways. However, demand for B12 can vary considerably during the year and we see serum levels of B12 fall at critical times, such as the first few months after calving.” Vitamin B12 contains cobalt, so deficiency in cobalt can lead to deficiency in vitamin B12 because ruminants get most of their B12 as a byproduct of ruminal fermentation where the bacteria in their rumen assemble B12 from cobalt for use by the cow. Sub-optimal trace mineral and vitamin B12 status at calving, mating, and drying off has been shown to negatively impact growth, reproduction, and immunity. Using a trace mineral injectable containing vitamin B12 can improve trace mineral and vitamin B12 status at these critical times. Marks-Min with Vitamin B12 – The Evidence In the largest trace element study to date, Marks-Min Injectable Trace Mineral with Vitamin B12 demonstrated remarkable results when compared to a reference trace mineral injection. “Given the differences between Marks-Min and other products on the market, we wanted to generate a compelling data set to demonstrate how effective it was compared to the pioneer product. We entrusted this work to a third-party research company” says Dr Eden. “We chose farms that were at the top of their game from a reproductive perspective. We made sure that the farms had no evidence of trace element or vitamin B12 deficiencies or excess.” Across all outcomes of interest, Marks-Min demonstrated clear non-inferiority when compared to the reference product. Outcomes measured included submission, pregnancy and conception rates, and six week in-calf rate. Marks-Min demonstrated it is highly suited as an alternative treatment to the reference product. Reference: 1. Hawkins, D., and B. V. S. Franklin. New Zealand Dairy Veterinarians Newsletter 24 (2007): 12-16 Company website: livestockfirst.com.au Company email address: CustomerCare.Australia@boehringer-ingelheim.com Company video: https://vimeo.com/1138807630?fl=pl&fe=cm
Find out why the first summer drench can be so important in protecting your flock’s health, plus what to look for in your summer drench of choice.
A NSW-based innovator has developed a patent-pending, front-mounted firefighting and utility system for tractors, giving farmers instant, in-cab-controlled fire suppression, water and fuel on hand, and safer solo operations.
Barko Security is bringing drone technology to agriculture while building on a decade of security and a lifetime of agricultural know-how.
