The author and developer of FarmAdvisor AI is Dr. John S. Bircham - B.Agr.Sc.; M.Agr.Sc. (Hons); Ph.D.; a graduate of Massey University (New Zealand) and Edinburgh University (Scotland).
His career as research scientist began in the late 1960s, when he was appointed to the position of Field Research Officer for the Southern Hawkes Bay and Wairarapa regions in New Zealand. He was the Officer responsible for the Masterton Field research Area (East Taratahi Road, Masterton) and the research undertaken both there and in the region's hill country.
In the mid 1970s, he relocated to the Whatawhata Hill Country Research Station and then a few years later to the Hill Farming Research Organization in Midlothian, Scotland, where he undertook his Ph.D. studies. Upon completion of his studies, he returned to Whatawhata for a number of years.
His seminal work on the pasture-animal interface, herbage tissue flows, ruminant grazing behaviour and productivity has stood the test time, being as relevant today as it was when he completed his Ph.D. studies over 40 years ago. Upon his return to Whatawhata, he developed a number of landmark models based upon his knowledge and understanding of the pasture-animal interface. The most notable of these was a general model for ruminant pasture intake, a model that has stood the test of time, as has another, which describes the relationship between incident rainfall and soil moisture on steep and rolling sloping land.
After resigning his position as a scientist at Whatawhata, he developed and marketed the first commercially available pasture growth predictor for New Zealand, followed by the prototype to FarmAdvisor AI, before becoming, for a decade or so, an organizational systems analyst and developer. During this time, he developed an interest in organization risk and resiliency, an interest that led to speaking, teaching and consultancy engagements for many years in Australia, North America, United Kingdom & Europe.
For the last few years, his focus has been on the development of an AI system for pastoral farmers that not only represents the uniqueness of their Physical Environment (land form - slope, aspect, soils and local climate - rainfall, temperature & radiation) in which their pastoral ecosystems are embedded, but also on the achievement of "Production Objectives." Unlike many tech products on the market today, many of which are task-efficiency focused, FarmAdvisor AI's focus is on underpinning "Provisioning", "Resource Utilization & Management" actions and decision-making with "Future Analytics" derived knowledge and understanding; knowledge and understanding that can guide and assist the pastoral dairying community to navigate our increasingly VUCA (volatile, uncertain, complex and ambiguous) world.
A trained pilot, he understands the use and value of instruments when flying in Instrument Meteorological Conditions; i.e. flying blind in cloud or at night with no visible horizon except the artificial one on the instrument panel. Indeed, it was such experiences and the realization that managing a pastoral ecosystem has "flying blind" moments inclusive of feelings of uncertainty, that prompted his modelling of a Pastoral Farm Management Expert System on the Aviation Sector's Flight Training Simulator . Moreover, that such simulators impart the experience-based learning required to teach a pilot to fly, to familiarise an aircraft's crew with in-flight emergency procedures or the Air Traffic Control procedures and requirements for a new destination. Furthermore, that if mistakes are made whilst training in a Simulator, there are no impacts or consequences - just the opportunity for experientially based learning and the acquisition of knowledge that success cannot teach.
What attracted him most to underpinning a Pastoral Farm Management system with an expert-system that could reflect the constraints of a Physical Environment (land form, soils & climate) and other influences (Climate Change, Environment Protection, Socio-Economic, Geo-Political, etc.) on the performance of a Pastoral Ecosystem, was the opportunity to experientially learn using "Trial & Error" techniques. The objective being, to learn from both success and failure, the latter not only recognizing and quantifying "Unknown Knowns" but also creating awareness of previously unrecognized "Unknown Unknowns." and the risk they could represent to the achievement of "Production Objectives."
Dr. John S. Bircham