Why invest in tech for farming?

Every second business writer today seems to be talking about ag-tech, big data, and the internet of things. If you’re an agriculture sector organisation, or a company servicing or purchasing from primary producers, you might be forgiven for thinking you missed a day in the office and overnight farming has become a connected, automated, artificially-intelligent system.

Reality of course is still far from that utopia (or dystopia, depending on your point of view). What the writers are telling us is that there are a range of interesting technical possibilities that might have application in agriculture: and that some of the very early adopters, enthusiasts, and visionaries are trialling these. In some cases, they’ve used technologies in interesting experiments and learned useful things about their supply chain or farming system.

All well and good; but if you don’t consider yourself a leading edge visionary (or perhaps you don’t have the same appetite for risk) should you just ignore the hype, and wait until the technology matures?

For the pragmatists among us, who are more interested in achieving practical goals and strategic goals than experimenting, here are some areas where I think there is value in leveraging technology into your business today.

Improving communication

We all know that good communication between people is what keeps the wheels of business oiled and turning. Technologies, systems, and business rules are no replacement for good people relationships.

Your customers, suppliers, and business partners see all of your interactions with them as part of that same interpersonal relationship. Are your reports or invoices late? Do they lack critical information your business partners need? Personal reassurances will go so far, but if you can’t achieve timely and data-rich information delivery that helps your partners, they may look elsewhere.

We’ve helped a number of our customers lift their communications with suppliers or customers. In some instances, we’ve delivered apps that help farmers access key pieces of information as they become available. In other cases, we’ve implemented reports and visualisations that are valued by business partners for the timely insight they provide. This isn’t just data: it’s business communication.

Understanding critical business metrics

Many businesses try and track too many metrics, and don’t always closely manage the key metrics that are leading indicators of success.

What drives your business? Primary production and processing businesses are often heavily influenced by factors such as weather and global market demand, but these factors are outside the control of most businesses and may have less impact on long-term profitability than we imagine.

Its typically our response to outside factors, and our ability to continue to produce value despite them that determines long term success. Measures of productivity per unit of input, and effectiveness at delivering high-value products are better indicators than raw dollar returns or kilograms of product shipped.

For some of our customers, this has meant improving alignment between their financial data and physical data records. For instance, benchmarking kilograms of product produced, farm working expenses and profit against the potential pasture or crop production for that season, allowing more effective comparison of improvements across seasons. For others it has meant focusing on the proportion of product meeting specification for high-value markets, regardless of whether the market actually delivered the desired price premium in that particular season.

Data integration can help bring these disparate data sets together for timely comparison, and in-field monitoring technologies or remote sensing can deliver the physical data needed to make sense of the product and financial outcomes.

Responding to changing conditions

How do you assess and respond to the risk of changing weather and markets?

Studies of farmer responses to drought and similar challenges indicate that we tend to respond too late, and in a conservative, “piecemeal” fashion. We seem to bet that things will trend back to normal sooner rather than later, and under-do our response.

Monitoring tools such as climate stations and market data visualisations allow us to understand trends and risks early – before their impacts really start to bite. Of course, responding to these is still a challenge: will I reduce stock numbers only to see the weather change?

Mathematical models don’t yet give those definitive answers some futurists might lead you to expect, but they allow you to ask the “what if” questions, looking at potential decisions and impacts. These allow you to build a plan for your business and understand what your critical review and decision points need to be.

Time to start learning

The pace of change in technology is only likely to accelerate in coming years, and the technology we use in farming in ten years may be very different than what is now available. It is tempting to just “wait and see” what evolves, but advanced agricultural businesses choose to embrace technologies that can deliver concrete benefits and which align with their goals. Consider ways that technology can help you achieve more effective communication, improved understanding of business metrics, and the ability to assess and respond to change.

What technologies are you embracing in your business, and why?

Is connectivity interrupting your agricultural vision?

The last few years (even the last few months) have seen a surge in organisations exciting us about what farmers will do with sensors and mobile devices. We’ll be able to collect data with drones flying above our fields and tiny devices scattered across our farms. We’ll collect data with smart ear-tags and boluses in livestock, and we’ll crunch it all with powerful cloud-based analytics and smartphones will be a convenient way to tap into these analytics so that we can make decisions on the move.

That’s the promise.

Given time, much of this is achievable, though being savvy business people, farmers will only adopt technologies that deliver value or reduce risk. Even if the technology does provide significant value the may also be a challenge in connectivity; how do all these devices connect together and to the cloud?

I was thinking about this just last week, when I was demonstrating livestock management software to a group of farmers. It was a wintery day with snow on the hills, and we were standing out in the sheep yards, protected from the sun (but not the wind) by the steel roof.

We had just demonstrated how trivially easy it was to capture information about animals and synchronise it onto a smartphone, and now we were going to show the same information synchronised to the cloud, through a web browser and a mobile data connection.

We pressed “refresh” and we waited – and waited.

Did I mention that I had plenty of time to think?

Of course, eventually the page loaded and the demonstration carried on, reasonably successfully too. The farmers of course took the opportunity to point out that their remote yards would have no coverage at all!

We face a variety of different connectivity challenges in rural environments:

  • Low bandwidth and high latency connections;
  • Connectivity black-spots and intermittent coverage; and
  • Areas with no connection at all.

Low bandwidth and high latency

In many cases, rural networks (fixed or mobile) provide significantly lower bandwidth than those in the cities, or they may have significantly higher latency (time to respond). For some applications, this doesn’t matter at all, but for others it may be a show stopper.

I watched a drone software manufacturer demonstrate the features of a very smart unmanned aerial vehicle (UAV). On-board software used the GPS to navigate the device over a flight plan we outlined using Google Maps. A multi-spectral camera captured high resolution images at 1cm per pixel, and the device transmitted the images to the cloud while it was still flying. That’s pretty incredible!

Transmitting images as they are captured is a great innovation. The intensive processing power required to stitch images together and analyse them is provided by a remote data centre and applied to data arriving from drones around the world. It also frees the operator from messing about with memory cards or thumb drives and processing software.

This works just great on the 4G mobile networks in the Salinas Valley, California. Not so much in rural Wales where the mobile networks drop back to GSM or EDGE, with significantly lower throughput. Still, there may be opportunities to address this. If the drone has sufficient memory, it could cache images until bandwidth improves, or when it returns to a connected base. Alternatively, flying at 400ft above the terrain may provide better coverage than we experience on the ground.

High latency rural connections provide a different challenge. We typically experience an increase in latency with satellite connections, as signal travels through a far-distant satellite, to and from ground stations. Satellite connections can still be very high bandwidth (high data throughput), but have a measurable delay, as you’ll notice if you use a satellite based phone service – “over”.

This latency won’t affect most applications to any noticeable extent, but consider the case of a livestock auction happening at a remote location. Smart auction software allows internet bids to be synchronised with the bids happening on site, right down to subscribers hearing and seeing the auction in real time. A delay of one or two seconds in this case becomes significant, so auction planning and operation needs to take this into account.

Mobility “black spots”

Much of the rural countryside lacks mobile coverage. Hills, trees, and buildings can all affect local reception, especially as distance from a cell tower increases.

This limits our dependence on these networks for “life and death” situations. There’s a reason why Search and Rescue services encourage hikers and hunters to use Personal Locator Beacons (PLBs) rather than rely on mobile phones when in remote areas, and the same should apply to tools that are triggered when an ATV rolls on the farm – the vehicle could well be in a gully outside of cellular network coverage.

We should also plan on intermittent connectivity when developing apps for the farming sector. Requiring an internet connection to start or use an application will limit its use to favourable environments close to home where that coverage exists. An answer of course is smart synchronisation of relevant data, when devices come back into network coverage.

I was quite confident demonstrating our livestock management application remotely for example, as the list of animals had already been stored by the mobile device and most importantly the application was designed to work disconnected and sync later. If there was no coverage, the new data I had captured would be sent to the server when a connection became available.

Bringing your own network

There are always spots with no connectivity: sheep yards in a valley between steep hills; installing nitrate sensors in a creek in a ravine; even equipment in the shadow of a large steel building. What options are there if we must install our technologies where there is no connection?

It turns out there are a range of options, but the need to be technology savvy and the cost of equipment rises in these cases.

  • Consumer networking such as Wi-Fi and Zigbee mesh networks operate at 2.4GHz, providing line-of-sight connectivity over relatively short distances. Trees, hills, and even buildings can block these signals. Wi-Fi’s real strength is that it is a relatively low-cost and easily deployed option. It’s less suitable where extreme battery life and low power is a requirement.
  • There are also specialist wireless networks. These often use lower frequency radio transmissions, operating at 433, 868, or 900-921 MHz. They require a larger antenna, but these frequencies can travel longer distances without increasing the power requirement, and may be less prone to blockage by trees. Some of these networks transmit point-to-point between sender and receiver, and others form a mesh communicating between multiple devices.
  • New standards are evolving for low-power, long-range wireless networks such as the LoRaWAN and SigFox networks. Telecommunications providers are starting to adopt these standards to provide specialist connectivity for “Internet of Things” devices and remote locations. Where these are used at low frequencies in rural networks, they may well provide better coverage for monitoring devices in previously poor locations.
  • Finally, we might consider using mobile phones to “collect and deliver” data from monitoring devices in places where there are no coverage, but where coverage spots are regularly visited or passed. A remote sensor with some memory and Bluetooth Low Energy capability might deliver summary information to your smartphone when you pass by. This is the same approach that is used by activity sensors you wear on your arm – data is captured, and delivered to your phone at intervals.

So there are possible solutions even to those areas with currently poor or non-existent coverage – but many of these require some skills, choices or trade-offs, and often a higher investment cost, and this makes adoption of technology more challenging. Companies developing new products can’t cater for every possible network technology, and may end up integrating a just subset of connectivity options.

Our team at Rezare Systems often discusses these challenges and the evolving set of solutions, because these will enable some of the software solutions we “brain-storm”. We’re not telecommunication providers or hardware developers, but we are very interested in how connectivity influences adoption of new technology and our ability to capture and leverage data.

Have you had experience with connectivity issues in rural applications? Can you share advice for farmers and rural professionals about some of the suggestions above and their alternatives? Let us know your thoughts.

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.