Big Data Technology
in Agricultural Research
Megan Z Cushnahan – PhD Candidate New Zealand Centre for Precision Agriculture, Institute of Agriculture and Environment, Massey University, Palmerston North, New Zealand.
The use of big data technology is becoming more common in agricultural research. These emerging technologies, such as hyperspectral sensing and imaging (HIS) tools proffer to replace the expensive, laborious and time-consuming data-collection methods conventionally used in agriculture.
New approaches involve non-invasive, rapid collection of high volume, versatile data at a very high spectral and spatial resolution. Experience from other industries suggests however, that refining value from big data technologies will be a key challenge for the agricultural sector.
In order to understand the challenges and opportunities created by what we call a new data economy, the author is following a precision agriculture science team tasked with developing highly advanced hyperspectral techniques for a ‘low tech’ sector.
HSI creates multi-layered, geo-referenced data early in the science process in superabundance. This data is created at high speed in real time and does not require expensive ground sampling. The data is extremely versatile and has the potential for many different measurements from one record. Early observations from the study indicate that these data traits may increase the likelihood of producing ‘surplus science’, that is, science that exceeds what was judged necessary to solve the problem as defined at project launch.
The production of superabundant and highly versatile data early in the science process appears to increase the possibility of discovering new forms of valuable knowledge (methods and solutions) during the course of an investigation. However, realizing the value of these opportunities may require a departure from the classic science model.
Under data-scarcity conditions, such surplus science would be classified as undesirable ‘project creep’. In response, we propose an alternative process based on a non-linear, iterative approach that utilises heterogeneous actors to refine value from hyperspectral data.
In addition, it is proposed that for innovation in the PA sector to make the necessary rapid advances both technically and in terms of adoption, changes are needed in the way research projects are funded and structured to accommodate a new approach to science-making.