Tools & data

Background

How to get value from agricultural data

Proving if a precision technology works starts with remembering trial basics – and taking the time to scrutinise results.

Methods of generating value from farm data might differ based on adoption level, but there are some universal truths – namely the need to employ proper comparison trials and analysis techniques.

Indeed, some experts in Ontario, Canada, see the failure of many growers and tech-advocates to conduct proper field trials of precision-ag technologies as a notable barrier to wider adoption.

Text continues underneath image

Informed risk management and precision agronomy can be employed early in the growing season. This can mean monitoring weather impacts in each field, scouting and tracking crop stressors. - Photo: Matt McIntosh
Informed risk management and precision agronomy can be employed early in the growing season. This can mean monitoring weather impacts in each field, scouting and tracking crop stressors. - Photo: Matt McIntosh

Take the time to learn

“Are you actually going to analyse the data in a timely fashion? Make sure you take the time to learn,” says Dale Cowan, senior agronomist and sales manager with AGRIS and Wanstead Cooperatives – a grain marketing and farm-input supply company based in the province’s Southwest region.

As an agronomist specialising in 4R nutrient management and precision-ag technologies (AGRIS and Wanstead Cooperatives operate a wide variety of precision data services for farm clients), Mr Cowan says the first hurdle any successful data-generator must jump is determining what they’re trying to do, what data needs to be collected to do it, and from where.

Text continues underneath image

Dale Cowan: “Are you actually going to analyse the data in a timely fashion? Make sure you take the time to learn." - Photo: Dale Cowan
Dale Cowan: “Are you actually going to analyse the data in a timely fashion? Make sure you take the time to learn." - Photo: Dale Cowan

Good agronomy should take top priority

This, he says, applies universally – from the most entrenched analogue to the most tech-driven producers. Indeed, Mr Cowan emphasises good agronomy should always take top priority in any field crop management system. Data generated in this context will inherently have more value.

It’s also important to get help interpreting data, if required, and to keep all raw data. This latter point is particularly important in preventing data loss as it is transferred through different formats and platforms.

Record keeping crucial for any tech improvement

Nicole Rabe, land resource specialist with Ontario’s provincial ministry of agriculture (Ontario Ministry of Agriculture, Food and Rural Affairs), shares Cowan’s view that ag-tech should be driven by agronomy rather than “shiny” pieces of equipment – many of which she says do not fundamentally fix basic agronomic issues, referring to them as “solutions searching for a problem.”

Nicole Rabe:

Before you jump in, ask yourself, what shape is my farm in? What are my basic issues and can I fix those first?

Poor record keeping in the first place, by extension, means improvements brought by precision technologies cannot be accurately quantified or realised.

“Before you jump in, ask yourself, what shape is my farm in? What are my basic issues and can I fix those first? Then what input do I find the most risky and has a need for better management?” says Ms Rabe. “You need to have a basic understanding of your bottom line.”

Text continues underneath image

Nicole Rabe: "You need to have a basic understanding of your bottom line.” - Photo: Nicole Rabe
Nicole Rabe: "You need to have a basic understanding of your bottom line.” - Photo: Nicole Rabe

Steps for tech-beginners

For the late adopter of digital technologies – or those not necessarily engaged in precision farming – Ms Rabe cites 3 main ways to accrue value from data. The objective being to scale down from a ‘one size fits all’ (macro) approach to a field-by-field profitability (micro) approach.

  • Firstly, centralise all financial notes relating to the cost of production in one place. Use this to identify areas for improvement across the farm and translate that into one or a series of management goals.
  • Secondly, centralise knowledge on each parcel of land being managed (e.g. location, size, crop rotation, soil type, drainage, crop inputs, yield). Identify areas of the farm operation that consistently perform poorly, and use fundamental agronomic information to inform new management approaches for those areas. Then develop field-by-field near-term and long-term management goals, such as a five-year plan to mend drainage systems and address fertility issues.
  • Thirdly – look at equipment. Identify what data is being collected and how it can be used (e.g. fuel efficiency and other fleet information). If equipment is GPS enabled, centralise any harvest and spatial data. Training needs should also be identified. Professional advice should be sought to work with the data being generated, as well as to assess historical performance by observing field-by-field trends over time.

Want to learn more about how to generate value from farm data? Read the full story, including steps for advanced tech-users and information on how to succesfully conduct trials in the digital issue of Future Farming.

Or register to be able to comment.