VizAg:Visulisation of agricultural field performance

Project Detail

VizAg:Visulisation of agricultural field performance

As an overview, there is an increasing interest in the use of data collected on-farm to improve on-farm efficiency and sustainability. There are also an increasing number of technologies to help collect (or sense) data; and to help interpret this data. This provides business opportunities both in the design and development of these technologies but also in the interpretation of data and in the development of platforms for the integration and visualization of this data. However, difficulties can arise in that on-farm data collections are impractical or too costly to implement and that, if collected, the data are not transformed into useable information to the farmer. In this respect, this project provides a novel niche in this market where on-farm data collections are kept to a bare minimum (minimum cost) and the required data are instead generated (simulated) using a proven agricultural model. This is coupled with the development of visualization tools, so that the farmer is usefully informed by this data. Here Rothamsted Research provides the expertise in the agricultural model, whilst Glas data provides the expertise in the design of a highly visual platform through which farmers will be able to utilise the output of this model. Through a synergistic R&D relationship between project partners, the agricultural model will be seamlessly integrated into a platform designed to deliver complex outputs in clear, easy to understand, visual formats, in order to achieve a high level of accessibility and usage. This project aims to demonstrate the practical value in the combined use of outputs from an agricultural field-scale model together with novel visualization tools to provide an arable or livestock farmer with a portable decision support tool that is at the same time both highly informative for farm management but where the model itself is robust to the effects of incomplete and poor information for its calibration (i.e. it requires minimal field information through sampling).

People

Site

  • Rothamsted Research

Scientific Theme

Collaborators