Satellite data and HPC combine to improve arable farming

21 March 2023

A key objective of our role in the EuroCC project was the transfer of knowledge to industry. As part of this, EPCC helped UK startup Mercury Environmental Systems Ltd develop a service that uses satellite data and high-performance computing to monitor and forecast crop growth. This Mercury data service aims to aid more efficient and sustainable farming as well as broader ecological and environmental decision-making.

Mercury Environmental Systems is preparing to offer a commercial service that combines satellite observations with computational simulations in a novel way to provide farmers with continual crop growth monitoring and yield forecasting for fields under their management. This will enable farmers to plan ahead based on expected crop yields several months in advance of harvest.

Insights from the Mercury growth tracking and forecasting system should, thanks to the inclusion of nitrogen cycle modelling, also help facilitate more efficient use of fertiliser – an increasingly costly global commodity – by providing variable-rate nitrogen application maps to farmers. These maps can support better decisions relating to the optimal applications of nitrogen across a field while simultaneously reducing cost and environmental impacts. Moreover the inclusion of carbon cycle modelling supports environmental monitoring and carbon accounting.

At any stage of the crop growth cycle, satellite observations of crop vegetation are used to calibrate a growth model at the sub-field scale, which is then used to produce a forward forecast through simulation. EPCC has optimised execution of these runs on ARCHER2, the UK national HPC service, reducing their overall computational cost by a factor of 2.5. This is a significant saving in Mercury’s projected operational costs.

We also implemented multi-node parallelisation so the time required to generate a forecast remains constant regardless of field size or the spatial resolution of the model. This has the identical financial cost to using only the cores on a single compute node, to which the software was previously restricted.

Finally, we helped Mercury design and implement in software an operational model underpinning its service that will enable it to efficiently automate batch executions of forecast workflows for all its customers. This was done with ARCHER2 as an initial target execution platform, but with sufficient generality and flexibility to allow execution on other HPC and cloud computing resources, thereby enhancing Mercury’s operational resilience and safeguarding against compute resource lock-in.

Mercury’s forecasting system has the potential to have a significant impact on arable farmers and on broader agriculture, forestry, and emerging environmental markets in Scotland and worldwide. Innovative, data-driven forecasts will help farmers improve productivity and help reduce carbon emissions. Carbon forecasting and monitoring services will be a critical tool in planning and verifying land-based carbon sequestration projects at local to regional scales.

We are therefore pleased that by optimising and parallelising Mercury’s software to make use of HPC, providing software architecting consultancy, and skills transfer with regards to parallel computing we have helped put the company in a better position to progress towards an operational launch date and to serve and grow its future customer base.

What our partner says

“We are very grateful for the expertise and guidance provided by EPCC, which was essential for developing a robust modelling framework that has the capacity to generate multiple outputs at the spatial and temporal scales required to deliver the Mercury data products. Comprehensive profiling and subsequent code development was carried out by EPCC to ensure the central model structure ran as efficiently as possible across multiple cores.

“The assistance and advice provided throughout the collaboration was crucial to overcoming issues related to interacting with HPC resources. Further support received from EPCC included safeguarding and future proofing the Mercury workflow when producing timely estimates of crop carbon and nitrogen fluxes along with yield forecasts.”

Andrew Revill,

Mercury Environmental Systems

Image: Getty Images/Chris Hepburn

satellite view of crops and wood

Author

Dr Arno Proeme
Arno Proeme