Data

The capture of data is critical to improving where, how and why we farm in the UK today. Unlocking the data and the learning it holds will support the future and technological advances in agriculture, horticulture and aquaculture.
Supporting better and greater collection and analysis of data, Agri-EPI explores and delivers precision farming engineering, technology and innovation in UK agriculture across soil, crops and livestock.

Improving wheat yield predictions with crop image technology

Novel applications developed by researchers at BioSense Institute in Serbia are dedicated to make deep learning technology a widely accepted practice in agriculture, providing small and big farm holders to benefit from precision farming technology.

BioSense, the Serbian Research and Development Institute for Information Technologies in Biosystems, is a multidisciplinary research institute for agriculture of the future. The wheat yield prediction research conducted in Serbia aims to increase the collection of farm management data, help farmers understand more about their farm business by using sensor technology and IoT applications, and reduce farm labour.

Wheat yield experiments

Wheat is one of the most important crop types in food production worldwide. Due to increasing food demand and rising population, it is necessary to boost production and supplies of wheat and other cereals.

In 2019, BioSense Institute, observed wheat in different experimental field stages and did this for three consecutive seasons. Cameras used during the experiment were the FLIR SC620 in season one and two, and a thermal camera in the third season. By taking pictures of the wheat growing in their field (four weeks before harvest), and uploading it through a mobile application, farmers were able to gain information about the wheat yield estimate based on the current state of growth.

The objective of this research is to enable the farmer to use imagery to detect at an earlier stage when estimated yields are below average and timely apply agronomic treatments to improve yield.

Farm efficiency with data management

The automatization of ear density calculation (number of ears per unit ground area, usually 1m2), which is one of the main agronomic yield components in determining grain yield in wheat, can provide fast evaluation of this attribute and potentially save 200 hours of manual work, ease monitoring, and increase crop management practice efficiency. This will save money from potential yield reduction, which can cause big losses in the farmers’ investments.

The currently used process of yield prediction includes manual and tedious work. The farmer takes samples from the area of 1m2 from the field (if the field is larger, then from a few locations within a field), and measures the biomass. The next step is to separate and count the ears of wheat manually. Since the counting of one sample requires up to 1 hour, while the number of samples can easily exceed 200, this can result in more than 200 working hours, or two to three weeks of manual labour that could be avoided.

The collected dataset comprises RGB and thermal images. Thermal images give us information about the difference in temperature between the ears and their background through their colouring and ease ear detection. Images were taken in four dates on two locations in two stages of wheat growth.

Power of deep learning

Since we have witnessed a huge breakthrough of neural networks, especially in image processing, deep learning has greatly outperformed classical models and algorithms. The nature of deep learning is that the addition of more data improves the quality of results, so by uploading images from farmers (crowd sourcing), the initial database will be expanded, so the algorithm will achieve better and more accurate results.

For more information about the methodologies used in this research by BioSense Institute, visit the DRAGON website.

 

Photo gallery:

 

Data-driven precision agriculture by DRAGON

Agri-EPI Centre is a core partner within the data-driven agriculture services and skill acquisition project DRAGON. The aim of the project is to enable communication skill transfer and knowledge exchange between research organisations and end users through big data and effective data analytics.

 

—————-

This article is an extract from an article of Željana Grbović – Junior Researcher, BioSense Institute – published on www.datadragon.eu.

Farming digitalisation and agriculture

Enabling smart decisions

Wyoming Interactive is a digital consultancy providing farming digitalisation and agriculture data services, software engineering and user experience design to medical, veterinary, agri-tech and life science organisations. Wyoming Interactive helps producers, breeders and veterinarians achieve high impact outcomes through smarter use of data and digital. Launched in 2008, Wyoming have built long-term relationships and a solid reputation for seamless end-to-end digital solutions amongst both US and UK clients over the last 12 years.

Digitalisation can reduce costs, increase revenues and build value-added services and Wyoming have been heavily involved in delivering these benefits to clients in Europe and North America. Much of their work in the agri-tech sector is to help organisations digitalise traditionally farming processes, such as data collection, through the use of smartphone apps, for example. Connecting new data sources, such as those based on GPS, weather, soil, herd health, crop health, etc. is a relatively new but rapidly increasing need and progressive users are seeing benefits accrue.

Wyoming incorporate these digital data sources into smart tools and power visual dashboards (which can support mobility through smartphone apps). Predictive tools can also be built on top of these data sources to move beyond ‘what happened’ to ‘what will happen’. Consequently, farms can enable smart decisions to be made and poor decisions avoided.

Data-driven farming

Agriculture and farming require digital tools to offer new growth potential. However, many producers have technology from different time periods and from different providers. While ‘point solutions’ can be adept at controlling finances, monitoring yield or tracking pesticide use, this does trend towards data silos making it harder to project an integrated view of farm performance. Data management techniques and digital dashboards marshal those various sources, abstracting the interpretation and action away from clunky source systems and into rich reporting and visualisation tools creating a holistic business view.

Allowing for better visibility and management of the wealth of data both livestock and crop farmers produce, will enable them to make data-driven decisions that will optimise yield, boost revenue, minimise expense and predict the best time to plant.

A recent example of Wyoming’s work was with an organisation that helps farmers to manage farm operations. The data generated from the farm is used throughout the food supply chain and with veterinarians. Wyoming helped to make sense of this data, creating customised models and dashboards tailored to the varying needs of different stakeholders.

For more about farming digitalisation and Wyoming Interactive, visit: www.wyoming-interactive.com.

Boosting the uptake of Precision Agriculture in Serbia

The limited adoption of precision agriculture is causing a lag in productivity in the sector – something which Agri-EPI is trying to alter through its involvement with the DRAGON project in Serbia. 

The three-year project aims to increase the adoption of precision agriculture technologies, practices and strategies by upskilling and educating young researchers in both hard and soft skills. Funded by H2020, it’s a consortium of four partnersBioSense, a Serbian University that cross-fertilizes two most promising sectors in Serbia: ICT and agriculture, recognising that ICT today plays a pivotal role in ensuring sustainable, smart and inclusive growth of agriculture. The other partners in the project are Agri-EPI Centre, Strathclyde University and Wageningen University in The Netherlands. 

At the end of November, Agri-EPI’s CTO, Shamal Mohammed, attended a four-day training school at the BioSense Institute in Serbia, to sit on the B2B panel. He was joined by Jim Wilson at SoilEssentials, who delivered a talk on online precision farming platform KORE, and Ben Scott-Robinson at the Small Robot Company, who spoke about AI driven robotic services for farming. 

The training school has presented students with technical information about innovation in agriculture, agri-tech and applied science solutions on farm, while also demonstrating how to present and profile research. 

Through further organised trips to the Netherlands and the UK over the course of the project, it is expected that skills and expertise will be transferred to BioSense researchers. The longterm outcome of the project will help them improve their capability to communicate practical big data knowledge across the supply chain and to the non-scientific community.  

For more information about DRAGON, please visit the website: www.datadragon.eu/.  

Sensor technology at Dairy Parkend Farm the new norm

Sensors that make sense: from farming to water control

Dairy farming has been a family affair at Parkend Farm in Scotland for three generations. But keeping an eye on the cows has never been easier. On his smartphone, Brian Weatherup receives automatic emails from the farm’s computer system, that alert him of any changes in the cows’ health or fertility status. The data is collected by collars the animals wear around their neck.

Collars for cows

“The collar indicates that there’s been a drop in a cow’s average eating time or average rumination time or average activity. And any one of these factors could be a primary indicator that the cow is either sick or just starting to get sick, and the key factor in these collars is that they can pick up these problems before they become very serious,” Brian explains.

When the animal eats, its neck muscles move – the movement is captured by the collars’ sensors, and wirelessly collected and processed. The collar’s developers are planning to add location tracking, which would be particularly valuable for free-grazing cows.

Milking cows: a robot’s affair

Milking robots measure the volume and composition of the milk produced by each cow. Farmers use this data to boost productivity and improve the well-being of their animals. These and other smart innovations are being studied at farms across Britain as part of an EU-funded research project aimed at making agriculture more sustainable and more efficient.

Ivan Andonovic is a researcher in communication systems at the University of Strathclyde in Glasgow, which is a partner of the project.

“What’s happened with the technological evolution over the last ten years is that processing power has become cheaper, the energy spent in processing has dropped, and the functionality – the form factor, the shape, the size of it – is much more manageable. It’s only under those criteria that you can use technology to create an economic solution for the farming sector,” he says.

According to Freddie Reed, project manager and part of the Agri-EPI Farm Network Team:

“The first stage of it is to find the extent of issues, collect the data over the farms, so we know what’s going on on the farm, then we can identify the causes of inefficiencies on the farm, and once we know the causes we can find the problems to solve those solutions.”

Brian says that in the six months since he adopted the new technology, production has increased by one fifth and his animals’ health has improved, too. Researchers see even greater potential in integrating sensor data along the production chain, by developing a common standard for data exchange.

“The way we can have a real impact and make life even easier for Brian and his colleagues in this sector is to create a consistent and coherent database which takes both the data coming in, the collar system, and the output, the robot system, and then match input to output, says researcher Ivan Andonovic.

….

———-

Source: this is a synopsis of an article that has been published on Euro News on 6 November 2017. Read the full article.

Stay informed

Keep up to date with the latest impact and results of our work, plus, news, innovation and approaches across the sector. Read our latest news and Agri-EPI blogs.