How on-farm data and analysis can support credence attributes

Can on-farm technologies and “big data” support food and fibre product attributes that consumers value?

In a previous article I noted a Hartman Group study that suggested that consumers are interested in attributes other than just the look and price of a product, wanting to know:

  • What ingredients are in the food or beverage product (64%);
  • How a company treats animals used in its products (44%); and
  • From where a company sources its ingredients (43%).

We call these informational aspects of a product “credence attributes”, meaning that they give credence to our decision to purchase (or not purchase) a product or service, but can’t be directly assessed from the product itself, either before purchase (on the basis of colour or feel) or after purchase (on the basis of taste, for instance).

Characteristics such as “organic”, “environmentally responsible”, “grass-fed”, and “naturally raised” relate to the story behind a product. A product may communicate these through advertising, packaging, and other ways of telling the product story.

But consumers are also looking for authenticity and integrity in their food and other products. There’s a consumer backlash when the product story on the pack is in conflict with other data sources – such as claims in news articles or secret video footage.

We’ve been exploring ways that feeds of data from on-farm technology could be used to support the product provenance and credence story – or at least signal to farmers and their supply chain partners where checks and improvements should be considered. Here are a couple of examples.

Monitoring carbon footprint

Carbon life-cycle assessments (LCAs) are used to understand the extent to which production, manufacture, and distribution of a product impacts on climate change through deforestation or release of greenhouse gases such as carbon dioxide, methane, and nitrous oxide. We learn some interesting things from these, sometimes showing that shipping food products from the other side of the world can have a lower impact than growing products locally if the local environment is less hospitable.

Importantly, producing a Life-cycle assessment creates a model – a series of equations and if-then logic that describes the calculation. We can use this model with appropriate local farm and supply chain data to understand how management decisions and activities, timing and stock or crop productivity impact on emissions.

Automated systems on farms that capture data about crop production, livestock weights and production, and farm activities can also deliver data for a custom life-cycle assessment. Benchmark data across multiple farms and it becomes possible to identify the patterns of complete vs missing data, to understand how climatic constraints change emissions, or to identify outliers that need to be more closely examined.

A note of caution here: as we’ve learned from nutrient budgeting, farm systems can be varied and life-cycle assessment models are frequently based on the “typical”. An outlier result may indicate greater variation than the model can handle, rather than a more or less efficient farming system.

Demonstrating animal welfare

Animal welfare and the ability to live a healthy and natural life is another area of concern to consumers. Here too, metrics collected on-farm can be the subject of automated analysis to demonstrate good practices are followed.

In Europe where a premium is payable for “grass-fed” dairy in some regions, farmers are experimenting with the use of monitoring devices – smart tags and neck bands for example. These devices capture data that provide farmers with early warning of heats and potential animal health issues – raised temperatures, more or less movement, and reduced eating for example – but can also be analysed for patterns that only show up in outdoor grazing.

In other jurisdictions, veterinary product purchase, use, and reordering records can help to demonstrate compliance with animal health plans worked out between farmers and veterinarians, and hence demonstrate good welfare practices and appropriate use of medicines. Paper records have been used for this purpose for many years, but software technologies and automated data analysis can reduce the burden of data collection and the need for manual audits and analysis.

Practical application

Some producers will find the thought of such automated systems invasive and potentially threatening. Certainly, given the potential for outliers, for good practices that just don’t quite fit the expected mould, and for technology glitch or human error, you couldn’t use these measures as legal baselines that determine “rights to farm”.

Nevertheless, application of technology and analytics such as these can help us as we seek to improve farming practice and improve the integrity of our food supply chains. A good starting point might be to apply these as tools for committed producer groups that are already aligned with supply of a premium product or market.

 

This article was first published at http://www.rezare.co.nz/blog/.
Contact us to learn how

we apply software and models to agricultural data.

What do consumers know about your supply chain?

Consumers. A jaded and cynical bunch. I include myself in that statement.

Just last weekend, a lovely salesperson was extolling the praises of a new smoothie product (“would you like to try it sir, it’s packed with fruit”), while I was remembering comments from my children about the level of sugar in smoothies and trying to see what was on the ingredients panel.

Studies by the Hartman Group would suggest that consumers are interested in more than just what a product’s packaging looks like, instead wanting to know:

  • What ingredients are in the food or beverage product (64%);
  • How a company treats animals used in its products (44%); and
  • From where a company sources its ingredients (43%).

Of course, that’s not to say we are always completely logical and analytical. When I buy Bella Pane bread at our local farmers’ market, I don’t ask to see the ingredients list, or the best-before date, or ask when it was made. Probably Mike has already told me he got up at 3am to bake the day’s bread, but even if he hasn’t done so, I gain a level of confidence and trust from his local proximity, previous discussions, and the farmers’ market brand story.

That level of trust and confidence in product quality, source, and ingredients is what supports positioning of premium food products. A large North American corporate recently discovered that promising “Food with Integrity” was only a start, and those promises needed to be backed with processes and checks to maintain confidence in their products.

I’ve spent a while recently considering how the information we collect on farm can support the broader story about premium protein products. The Hartman Group research would tell us that consumers in the US are interested in:

  • Hormone free (52%);
  • Free of antibiotics (49%);
  • Artificial (48%);
  • GMO-free (41%); and
  • Organic (31%).

When it comes to animal welfare consumers want to know that companies avoid inhumane treatment of animals – and while they may not know the details of what that means, the proportion of people who care is rising:

  • Other animals are not harmed in capture/raising (e.g. bycatch) (68%);
  • Animals are raised in as natural environment as possible (65%);
  • Animals are not used for product safety testing (65%);
  • Animals are not given hormones or antibiotics (63%);
  • Company supports animal welfare causes/organisations (51%);
  • No animals at all used in products (45%); and
  • Animals fed only organic food (33%).

We know that products and processes that meet these criteria – and more importantly, have a compelling story in these areas – may command a premium in the market, and are in a position to build stronger, more defensible brands.

Consumers expect products and brands to live up to the brand story they are told. When lack of integrity in process or supply chain is exposed, consumers act angrily, as though we have been “tricked” (read Seth Godin’s “All Marketers are Liars” to learn more of how this works).

For that reason, any claims we make about our agricultural products having green origins or being “very pure indeed” need to be backed up by guides, processes and records that demonstrate our commitment to those brand values. Claims of greenness or purity are potentially for naught if we don’t have both safeguards and evidence in place.

Hence the importance of Farm Assurance or Good Agricultural Practice programmes, and the need for audits and for simple to use, on-farm record keeping tools that back up the story. We’re working on some of the latter with our partners. It’s hard work, because farmers are busy people with limited finance. In order for supply programmes to really deliver the benefits promised by the brand, I think we need to do two key things:

Link the activities to the brand story

Make sure everyone who has a role in the supply chain understands how their role contributes to the brand and to the consumer experience. Spell out how actions on farm impact the supply chain: safety, provenance, and in-market claims. Ensure staff know the risks to the business if product integrity fails.

Make it easier to comply than not

Most audit schemes today run on paper – recording pages in a paper book or filling in forms. For practical reasons, these are filled in at the farm office, and often updated just before the auditor arrives. We remove a substantial barrier if it is easy to capture information in the field rather than spending evenings in the office. Reusing information captured for farm assurance records to provide insights for farm management aligns goals and makes adoption more likely.

Your thoughts?

Consumer expectations have been changing over the last decade. Our supply chains and production systems are evolving to meet those expectations. This will require a greater commitment from us all to transparency and integrity, making sure what we do lines up with what we claim.

Do you manage a supply programme, or participate as a farmer, grower or processor? We’re interested in your thoughts. Drop me a note in the comments, or contact me directly.

Getting the most from farm data

Increasing pressure from commodity returns, input costs and environmental compliance means that farming today relies on consistent, quality decision-making. Good information, viewed properly to gain insights, is the life-blood of great farm decisions.

Unfortunately, the most useful data is often hardest to collect and interpret. Pasture information relies on pasture walks (or drives); stock condition must be assessed manually or using advanced equipment; and even understanding growth rates of cattle or sheep requires pulling them off feed and into yards where the risk of transferring disease increases.

Many advisors from fertiliser and feed planning to finance and animal health now have tools that help with visualising outcomes and supporting decisions. In turn, these tools are also hungry for data – sometimes detailed and sometimes high-level farm information. Some farmers tell me they feel every second person up their driveway needs to ask “twenty questions”.

So how can we satisfy our craving for more and better data, without turning farmers into field technicians or survey gurus?

Start with making better use of the data we have

This might include the farmer’s own records in their tool of choice – whether that’s a feed planning tool, paddock recording system, or their financial management system (which often capture product quantities and inventory as well as sale and purchase records). At the moment this existing data is in silos – unable to be accessed because it is locked away, or perhaps in a different format.

Where forward-looking software vendors have made some data available, it is often unable to be directly applied to answer other questions – at least without a human to interpret. Take the example of one tool asking information about calving dates and peak milking numbers, while another asks for monthly cows in milk. With experience and farm system knowledge, a human can readily translate one from the other – but these inferences are hard to automate.

The Farm Data Standards are the New Zealand industry’s approach to getting a common vocabulary, so that our computer systems will be able to meaningfully re-use data. This vocabulary is supported by the Data Linker (a DairyNZ and Red Meat Profit Partnership project), creating standard protocols so that software tools can share farm data through APIs, with explicit farmer permission. Organisations in the Data Linker early-adopter group are building streamlined processes so farmers can re-use their data with little or no overhead.

Towards more automated collection

The “Internet of Things” (IoT) promises to connect sensors and measurement devices from the farm to farm software and databases, making the most of recent advances in consumer electronics to reduce the cost of the electronics, enhance reliability and improve battery life.

IoT devices now available include remote monitoring and alerts for your water supply, pumps and tanks, as well as devices monitoring the state and efficacy of electric fences and effluent spreaders. There have been electronic solutions in this space for quite some time, but improved mobile and on-farm wireless networks, along with smaller and lower-cost electronics, are now making them more attractive.

Coming IoT devices may monitor water quality in real time, assess pasture cover, assist with matching dams and progeny, or with diagnosing animal health challenges. A key for farmers will be ensuring that they can access this data and re-use it for a wider range of purposes where it makes sense.

Filling in the gaps with remote sensing

Lately I’ve been privileged to meet farmers and technology companies in the United States and Australia, where broad-acre cropping of corn, soybeans, and wheat are the predominant farming practice. Farmers are starting to make great use of multispectral and hyperspectral imagery regularly captured from aircraft, low-earth orbit satellites, and even drones (though the range of most drones is too short for larger farms).

Image analysis from these platforms has been around for a long time now (using normalised vegetation difference index or NVDI, for example), but instead of just displaying images and leaving the farmer to guess what is going on, companies are now applying machine learning to correlate the patterns in the images with known crop issues and yields. For large enterprises, this remote sensing data “fills in the gap” between what the farmer observes by walking in the fields, and the wider enterprise. Hyperspectral imaging that captures additional wavelengths will support more sophisticated analysis, and I look forward to seeing some new crop-specific analyses in the future.

Weather and climate data from MetService and NIWA can also be considered remote sensing data to can support decision making, even for those without their own on-farm weather station. The NIWA Virtual Climate Station Network (VCSN) provides a grid of historic climate data and weather data across New Zealand, and that data is combined with soil drainage and fertility information in the Pasture Growth Forecaster. Other countries provide similar climate data services.

A word to the wise regarding Pasture Growth Forecaster: free regional averages are just that – averages over a broad area and a range of soils. You’ll get better mileage by paying the trivial amount each month to get a custom forecast based on your location and soils.

Bringing it all together

I’ve painted a bright picture of how the data available from a number of sources – existing databases and suppliers or customers, small in-field devices connected with the Internet of Things, and remote sensing data – could reduce the overhead that currently puts many farmers off collecting data.

The challenge for farmers and their service providers is now to bring those assorted pieces of data together to provide information and insight for better decisions.

For service providers (including software developers such as Rezare Systems) that means lifting our sights from simplistic tools that regurgitate input data in pretty graphs, to providing predictions, visualisation, and insights that support decisions which matter to farmers. For farmers, that will mean grasping technologies that show potential to address future farming needs, and challenging vendors to make systems as open, connected, and useful as possible.

 

Agricultural Tech Reloaded

MobileTECH 2016 in Rotorua, New Zealand was a showcase and discussion forum for the adoption of smart technology in primary industries: agriculture, horticulture, and forestry. 300 attendees from a broad spread of primary sector organisations and technology companies spent two days discussing the application of all things sensor, wireless, and cloud.

I thought it worth summarising four major themes from my perspective.

Read More

Four ways to make your farming app engaging

So you’ve decided to build a mobile app for your rural customers or users. You have spent time on the overall value proposition, deciding how your app will deliver enough value to your users that they will spend the requisite time – and money – to use your service. No doubt you’re also modelling the likely market penetration and adoption curves, because you want to make sure you can get a return for all the investment in software development, testing, and marketing.

You know that up to 20% of mobile apps are downloaded, used once, and then never touched again (perhaps uninstalled when the user runs out of space). How can you avoid your app ending up in that category? Better than that, can you provide an experience sufficiently valuable and engaging that users tell their friends?

Read More

The next step in farmer-mediated data sharing

Agricultural data: who holds it, who is using it, and who “owns” or controls it has been recurring news worldwide, featuring in places as diverse as Wall Street Journal, Fortune Magazine, the American Farm Bureau Federation, ABC Rural in Australia, and European Union projects.

A quick summary of the opinions expressed are that increasing use of

Read More

Decision making in the face of El Niño

Seasonal weather forecasting is a tricky thing – forecasters don’t necessarily have a great track record. This year is interesting as international researchers and the Crown Research Institute NIWA have provided clear, early forecasts for a strong El Niño event. Rezare Systems’ Farm Systems Analyst Graeme Ogle explores the implications for farmers and tactics they should consider below.

Read More

How shared data supports good agricultural practice and marketing

Agricultural supply chains have become increasingly complex and for those serving discerning markets, increasingly demanding. Product integrity, safety, and quality attributes are moving from being based on reassurances to evidence and audit.

In the past, a handshake, a solid conversation, a trusted voice on the phone would have provided the necessary

Read More
Page 1 of 212