Data-Driven Decisions: Artificial Intelligence Paves the Way for Accurate Crop Yield Estimates for Blueberry and Grape Growers
Fiona has farming in her veins, having grown up on a beef and sheep farm in rural New Zealand. She admits that she "fell" into the world of new product development and management when she moved to Australia. In this space, she Fiona has created results-oriented technology based on AI and predictive analytics, she has gained experience using large-scale machinery, production lines, and lots of big data.
After 15 years developing new products and management tools in various industries, Fiona is back down to earth.
“I think you always have that farmer's blood in you. I really like big data, but I decided I wanted to go back to the land, so I bought a vineyard,” said Fiona.
Not long after buying Jinglers Creek Vineyard In 2017, Fiona identified problems with the data set and available software that was supposed to help her manage her crops.
“I had no experience in horticulture or viticulture, and I needed a way to get information to people who could tell me what to do,” he said.
“I was trying to solve my own problems and started taking videos of my crops. I have a lot of experience in technology and product development, and I realized that the problem is bigger than what I'm doing. This is how the product was born Bitwise Agronomy GreenView ".
Provide growers with meaningful crop-level data
After speaking with colleagues and stakeholders in the wine industry, Fiona discovered that there was strong market demand to improve the accuracy of yield estimates, to address challenges such as market supply and labor recruitment. Therefore, GreenView was developed with a farmer-centric approach.
GreenView combines computer vision, machine learning and artificial intelligence to count and measure the development stages of horticultural crops, providing growers with information such as number of berries and bunches, shoot length, and fruit maturity.
Fiona said the technology provides a different view to aerial imagery that grape and berry growers have relied on in the past for information about crop production.
“Aerial imagery looks at an entire block and uses predictive analytics based on canopy cover, while GreenView sits on the plant and looks at the individual pieces of fruit, which cannot be seen from top to bottom, and performs a count and forecast based on what we can actually see,” Fiona said.
“The product works by using a GoPro camera, attached to existing farm machinery, which records side-by-side video images of crops, plant by plant, all while the grower performs jobs like mowing, mulching or spraying.”
She said the images are then uploaded to the GreenView portal and analyzed using AI.
“We teach the AI to see like an agronomist or viticulturist, look for the different phenological stages of the crop and measure and count the fruit. Growers then receive this information in a report format that is valuable for forecasting crop yields or changing operational tasks.”
Fiona said this information can be beneficial in managing labor, reducing crop loss, improving quality and providing an estimate of crop yields. All the critical factors for the final result of a business.
“The berry industry spends thousands a year counting blueberries. We can count those blueberries for a fraction of the cost, saving labor costs and increasing count accuracy,” Fiona said.
“Greater accuracy leads to better forecasts that can then be passed on to the market. This means that producers are less likely to lose out, be turned away or penalized for not having the feed that was originally forecast.”
The Bitwise Agronomy GreenView product is now used by 70 companies in eight countries. In 2021, Fiona's AI work with Bitwise Agronomy earned her second finalist for the Women in AI Innovator of the Year award and winner in the Agribusiness AI category.
Most recently, in partnership with Burro, a collaborative robotics platform seeking to solve labor issues facing farmers, Bitwise Agronomy has been selected as one of the top 10 winners for new products at World Ag Expo 2023.
Agtech development with a farmer-first approach
When it comes to agtech and data, Fiona believes there is no one-size-fits-all solution on the farm. She said integrated solutions, data sets and software companies are needed to provide growers with a complete picture of their farm to enable data-driven, profitable decisions.
“It's about bringing together all these different data sets and agtech companies to get the results that the farmer was looking for,” he said.
Fiona is passionate about putting the farmer first, listening to what they say to understand what they want and how to support them to succeed.
“There are so many parameters and environmental factors involved when you are in the field that make it difficult to develop agricultural technology,” he said.
“Hot weather, cold weather or rain and everyone is short on time too. You need to make your product easy for farmers to use and fit for purpose. If you don't understand who you are selling to or their needs, adoption will be really difficult.
“It's also important to focus on farmers who are early adopters and have an appetite to use the new technology, and then really work with them to become advocates for the product. Then other farmers who might be more risk averse feel more comfortable testing the technology because their neighbor has confirmed that the farm technology was tried, tested and worked, as well as having a positive return on investment,” said Fiona.
Previous articleMore than 600 exhibitors and attendees are expected at the XXV International Blueberries & Cherries Seminar on April 13