Category Archives: AgTech

Variable Rate N Fertiliser – the Value Proposition

Adrian Hunt is a crop scientist at Plant and Food Research.

He recently completed a PhD at the University of Tasmania, investigating Pre-Harvest and Post-Harvest factor effects on the quality of onion bulbs exported to Europe for counter seasonal supply.  He now works across the vegetable and arable sectors to improve yield, profitability and environmental outcomes.

Together with colleagues Joanna Sharp, Paul Johnstone and Bruce Searle, Adrian has been investigating the value proposition for variable rate fertiliser application.

The technology to deliver variable rate fertiliser in an automated manner has advanced substantially in recent years. This has been aided by new or adapted spreading technologies coupled with location awareness using GPS (Global Positioning System). It is now technically possible to distribute fertilisers in a wide range of spatial patterns within a paddock, however the value proposition of variable rate fertiliser application is not thoroughly understood.

The Plant and Food team looked at the difference in productivity, profitability and potential environmental impact of a range of spatial management scales.

Based on a sampling grid of 105 points in a Hawke’s Bay paddock and used mineral N and a N mineralisation assay to quantify the underlying variability in N processes/cycling within the paddock they “grew” both irrigated and unirrigated maize in the crop simulation model APSIM Next Generation for the 105 sampling locations for 35 growing seasons, using long term weather data.

Adrian will present this work and the results at the LandWISE 2017 Conference in Havelock North.

Report on Australian SPAA Expo 2017

Hugh Ritchie reports from the 2017 Expo

(C) SPAA

The Society of Precision Agriculture (SPAA) is a non-profit and independent membership based group formed in Australia in 2002 to promote the development and adoption of precision agriculture (PA) technologies.

I attended the SPAA expo in March this year which was a grower focused day to present the latest tools and services available to growers. All speakers were service providers or users of the technology as opposed to researchers presenting their studies. This made for a day of very applied learning.

A common theme of the day was that tools selected had to deliver a positive return; i.e. they had to earn their keep. This was very good to hear as I feared I would be seen as a laggard to comment on the lack of variable rate and prescription maps. Most of the speakers identified a problem and the use of tools to find a solution.

There was also a range of farm types and again the message was any one can use PA concepts and you do not need to have high tech tools to practice PA.

The work with Near Infrared, Infrared and Short Wavelength InfraRed has come a long way and the work being done by Dr Ian Yule from Massey University leads the way. Of special interest was a camera manufacturer who could allow you to choose which bands you required and build a camera to suit at an affordable cost, putting this technology in everyone’s hands.

So, if we can do the research around what we want to sense and which wavelength it requires we could get real time data to enable prescriptions without the need to ground truth. This would be the next major leap forward in PA tools.  

Counting buds and berries

James Beech and Tony Cooper are data scientists and the principals of Precision AI Ltd. Tony and James will present to “LandWISE 2017: Are we ready for automation?” and discuss how machine vision and machine learning can be used to automate such things as counting buds, shoots and fruits in orchards and vineyards. 

Capturing quality imagery with changing light conditions, when your target is hiding behind leaves and you are traveling at speed on bumpy ground is quite a challenge. Identifying and quantifying the things you are interested in is a challenge as well.

What are the tools that can help? How close are we to automatically collecting this type of data?

James has over 15 years’ experience in software development, advanced analytics and data visualisation.

James specialises in open data, data infrastructures, business intelligence dashboards and predictive modelling. James is has particular interest in the application of big data through the use of statistical and analytic techniques to solve business problems. His experience spans across financial services, telecommunications and the agricultural sectors.

Tony has a distinguished track record in predictive analytics and data mining. His specialties include machine learning and computer vision. 

Tony has made exciting advances in quantitative research and received industry accolades. He holds a Bachelor of Science (Hons.) in Statistics and Computer Science from Massey University and a Master of Science in Statistics from Stanford University (USA).

Tree climbing robots in forestry

Richard Parker

Richard Parker is a Senior Scientist at Scion in Christchurch.  His research focuses on difficult, dangerous and essential occupations such as forest harvesting and rural fire fighting from the perspectives of human factors and technology.  

Richard is involved in the development of novel robots for forest operations and the human factors of forest work. He was a tree faller and breaker out in a former life.  He is also leads research on rural fire fighter performance and new technologies for fire detection and suppression and is a volunteer rural firefighter.

Delegates at LandWISE 2017: are we ready for automation? will hear Richard say that robotics is inevitable in forestry as specialised machines for forest tasks are developed.  The mining industry already has a history of robot development and automation and forestry is learning from their experience. However, forestry has particular challenges – much of the commercially forested land in New Zealand is on steep and remote terrain. 

Forest harvesting operations have been traditionally considered physically demanding and potentially dangerous, with forest workers on foot exposed to heavy and fast-moving trees, logs and machinery.  Many tasks in forestry have already been mechanised to reduce hazards to the worker and increase productivity.  For example, the axe was replaced by the chainsaw, which was replaced by the excavator based harvesting machine.  However large machines can damage the sensitive forest soils and cannot work on steep terrain where many forest grow.  This presentation will discuss the next stage of forest machine development which uses the standing trees for support.

Animals have lived in the trees for millions of years and have developed behavioural, structural and physiological adaptations to the arboreal environment.  Some animals move slowly from branch-to-branch like the stick insect.  Others, such as gibbons, can move rapidly using brachiation, engaging in the arboreal equivalent of running through the forest from branch to branch.  An opportunity exists to use this form of locomotion, although more slowly than gibbons, for the movement of forestry machinery. 

The proposed machine could always stay above ground moving from tree-to-tree using the trees for support. The machine would eliminate the problem of soil disturbance and would not be limited by terrain steepness.

Bottle Lake Trial Robot

With funding from Scion, the Ministry for Primary Industries and the Forest Growers Levy Trust, the concept of a tree-to-tree forestry machine became real.  Scion and University of Canterbury Mechanical Engineering and Mechatronics students built a working radio controlled tree-to-tree locomotion machine. Development of a real machine demonstrated that being independent of the ground makes operator control easier because the ground conditions (holes, rocks, loose soil) do not have to be adjusted for.

Soil to sprinkler, automating irrigation management

Anthony (Tony) Davoren is a Director of Aqualinc with responsibility for the HydroServices business unit that provides irrigation and environmental management services; soil moisture, and water level and water meter monitoring. 

Tony’s expertise in and knowledge of soils and hydraulic properties, irrigation systems and design, and crop water demand has been applied and enhanced over the last 35 years working in these fields.

We asked Tony to talk about automating irrigation – from the soil to the sprinkler and round again. He’s doing just that at LandWISE 2017: Are we ready for automation?

Tony says several questions need to be asked and honest answers or solutions given:

  • Are we and you ready?
  • What do we need?
  • Is automating irrigation management wise or the right solution?

Are we or you ready?

When considering automating irrigation management, both the provider and the user must be an “innovators”; i.e. they must be in the top 2.5% of the industry.  It may be that some “early adopters”, the next 13.5% of the industry, might be ready for the technology and its application to automate irrigation management.

What do we need?

Because it will be the innovators who adopt and field prove any technologies, these technologies must be robust and proven with a sound scientific backing.  Innovators will identify the financial benefits of the automation, which needs:

  • Well-designed irrigation systems
  • High uniformity irrigation systems
  • Well maintained irrigation systems
  • Precise soil moisture and/or crop monitoring systems
  • Interface “model” to irrigation controller

Are these all in place?

Is automation wise or the right solution?

Tony established HydroServices providing on-farm irrigation management services based on in situ soil moisture measurements in Canterbury, Pukekohe, Waikato, Gisborne, Hawkes Bay, Manawatu, Wairarapa and Central Otago. During this he provided specialist soil moisture monitoring for Foundation for Arable Research, LandWISE, Crown Research Institutes, Regional Councils, Clandeboye Dairy Factory and others.

Tony completed his PhD in Engineering Science at Washington State University, Pullman, USA.

Agricultural robotics in a French farming context

Thibaut Delcroix is a an agronomist and viticulturist convinced that robots will help to increase productivity while respecting the environment and making agriculture more human again. 

A key speaker at LandWISE 2017, he will discuss about Naio’s philosophy and their robotic options, in a French farming context.

Naïo Technologies is a French company that develops and markets robots for agriculture and viticulture. 

Naio Technologies’ goal is to offer practical and durable solutions to agricultural issues while reducing workload with autonomous tools for vegetable farmers and wine growers.

Naio Technologies TED vineyard robot

Thibaut says being at Naïo Technologies is both a human and technological adventure. The company spirit advocates social responsibility: they strive to durably help farmers while respecting their customers, employees and suppliers and the environment and society as a whole.

Thibaut has an Engineering Degree with Major in Agronomics. His thesis focused on Spatial extrapolation model of vine water status at a field scale. Then he joined Naio as a business developer and technical adviser for farmers. 

Thibaut will demonstrate Oz440 at the LandWISE Conference Field Sessions. He is looking forward to meeting New Zealand farmers, growers and viticulturists.

Supporting digital innovation

We are delighted that Dr Amanda Lynn is confirmed as a key speaker at our Annual AgTech Conference LandWISE 2017: Are we ready for automation?

Amanda’s focus for this event is on moving “change” away from something that happens to us, to something we do as a natural part of our personal, business, economic and social development. This is called “purposive change” and she will explain how we create, adapt and integrate it.

When we talk about change we often do so without a clear idea of what is meant, and without recognition of our own—individual and collective—roles in adapting to change, or even catalysing it. 

We seldom talk about levels of change and processes of development; instead, getting caught in black and white terminology like “disruption” and forgetting that change is natural, incremental and evolutionary. 

Innovation is purposive change.  We can sometimes forget that purposive change is something we—people—are very, very good at.  And there’s a lot of us; resulting in a lot of purposive change. 

The Executive Director of the Innovation Partnership, and Chair of the Innovation Partnership Forum,  Amanda specialises in development. 

The Innovation Partnership is a not-for-profit Trust.  Sponsored by Google, Chorus and InternetNZ, the Innovation Partnership connects businesses, educators and Government entities to support digital innovation. 

In addition to working with the Innovation Partnership, Amanda leads her own contracting enterprise, Mandolin Associates, undertaking public speaking, research and advisory services, and through this has worked closely with some of New Zealand’s leading agriculture and aquaculture innovators. 

Amanda is a member of the New Zealand Association of Economists, and a Professional Member of the Royal Society of New Zealand.

Is the Juice worth the Squeeze?

Chris Roberts

Chris Roberts, Head of Industrial Robotics at Cambridge Consultants UK is confirmed as a keynote speaker for our Annual Conference. LandWISE 2017: Are we ready for automation?

Cambridge Consultants is a world-class supplier of innovative product development engineering and technology consulting with more than 500 staff including scientists, mathematicians, engineers and designers.

Chris was one of the presenters at AgriTech-East’s Robotics Pollinator in October 2016, which Dan attended as part of his Trimble Foundation Study Trip investigating farm robotics.

“I was really impressed with Chris and his presentation. He worked clearly  and methodically through the issues that need very careful consideration.” 

In this presentation Chris will take a look at the prospects for robotic fruit harvesting, an issue of note in New Zealand as production levels rise and labour availability reduces.

Some of Chris’ questions:

  • Automation has existed in agriculture for decades: what’s new?
  • Why hasn’t it happened everywhere already?
  • Which tasks to automate?
  • What has to come together for a  successful harvesting robot?

Chris will address these questions and more at LandWISE 2017.

Hyperspectral imaging to map species distribution

Tommy Cushnahan is a PhD student at Massey University within the NZ Centre for Precision Agriculture.

Tommy is presenting some of his research at LandWISE 2017: Are we ready for automation?

Remotely sensed hyperspectral data provides the possibility to categorise and quantify the farm landscape in great detail, supplementing local expert knowledge and adding confidence to decisions.

In his presentation, Tommy will explain how hyperspectral aerial imagery is being used to classify various components of the hill country farming landscape. He focuses on development of techniques to identify and classify various vegetation components including water, tracks/soil, Manuka, scrub, gum, poplar and other tree species. 

Tommy’s PhD has been funded by Ravensdown and MPI as part of the PGP project “pioneering to precision”.  A background in agronomy and 15 years’ experience in golf course design, construction and project management has developed an array of real-world skills that has helped shape his research. His goal is for his work to produce tangible benefits for hill country farmers.

Refill Scheduling for Agricultural Robots and Other Vehicles

Rob Fitch

Refill scheduling is the problem of deciding when a robot or other agricultural vehicle should pause in its work to replenish a resource, such as herbicide or fuel. This problem is commonly solved in broadcast spraying, for example, by simply running the spray tank dry and then refilling it.

This strategy actually leads to lost time in traveling to the refill location, and we can show that these time losses can be significant. When multiple machines must queue at a refill location, the problem is made worse.

In this talk, Rob will explain the theoretical difficulty of this problem and give examples from robotic spot-spraying and broadcast spraying to illustrate the potential time losses. He will present an optimisation approach that chooses optimal refill times to minimise travel distance and queuing time. These results apply to agricultural robots, human-driven spray rigs, and any other machine that must refill or empty some material at a fixed location during the course of its work.

Rob will conclude the talk by tying these results into the larger research program in agricultural robotics, including novel machine learning methods for fruit/vegetable detection that support selective harvesting.

Rob Fitch is Associate Professor at University of Technology Sydney.He was previously a Senior Research Fellow with the Australian Centre for Field Robotics (ACFR) at The University of Sydney where he retains an honorary position. He is a leading research scientist in the area of autonomous field robotics. He is interested in systems of outdoor robots and their application to key problems in agriculture and environmental monitoring.

Robert received his PhD in computer science from Dartmouth (USA). He has led research in planning and collaborative decision-making for both ground and aerial robots in a variety of government and industry sponsored projects including those in broad-acre agriculture, horticulture, bird tracking, and commercial aviation.