ClearSky: cloud-free monitoring of UK agriculture

Lead Research Organisation: University of Hertfordshire
Department Name: School of Physics, Astronomy and Maths

Abstract

Earth Observation satellites can monitor every part of the globe, offering a detailed view of the Earth's surface on a daily basis. This is a valuable source of intelligence for the agricultural industry, since one can - in theory - map all farmland to determine, for example, the rate of growth of crops, signatures of crop stress and disease, the presence of flooding or signs of drought. These factors are vital to the efficient production of food and maintaining food security. On one hand, a precise view of crop health allows farmers to optimise the use of fertiliser and water, and the rapid identification of threats allows food producers to respond in a timely manner to mitigate their impact on the food supply.

There is a problem: cloud cover. Clouds obscure the view of Earth Observation satellites in the visible and infrared spectral range, and this is where the vast majority of remote sensing analysis is performed. This limits the value of imagery, because if it is cloudy when the satellite passes over, the intelligence is lost.

Our solution is to exploit radar data. Satellites equipped with radar can reflect radio waves off the ground and detect their reflectance. Since radio waves are not affected by cloud, this offers an uninterrupted and reliable view of the ground. However, the challenge has been in the interpretation of radar data. We have solved this challenge by developing an algorithm that can accurately predict what would have been seen in the traditional V/IR images (e.g. the RGB image our eyes would see) for cases where the surface is obscured by cloud. We call our algorithm ClearSky.

In this project we will use ClearSky to monitor every single field in the UK, every week. Our predictions will allow us to assess the presence and density of vegetation and its rate of growth, as well as determining local threats such as flooding and the onset of drought. Our aim is to deliver this intelligence direct to farmers and the food supply industry in order to aid the decision making process with regards the most efficient use of resources in producing food, and enabling us to be agile to potential threats to food security associated with a changing climate.

Publications

10 25 50
 
Description Agrimetrics Ltd. 
Organisation Agrimetrics
Country United Kingdom 
Sector Private 
PI Contribution My team led the project with Agrimetrics as a project partner. The goal was to work with Agrimetrics to perform market validation of the "ClearSky" algorithm for providing cloud-free imaging of agricultural land. Agrimetrics are a big data provider to the agtect industry, and a named partner on the grant.
Collaborator Contribution Agrimetrics brought subject level expertise for market validation, as well as marketing research and promotion of the product to their marketplace. This interaction helped take the basic product towards commercial readiness.
Impact Commercially sensitive
Start Year 2021
 
Title PREDICTING VISIBLE/INFRARED BAND IMAGES USING RADAR REFLECTANCE/BACKSCATTER IMAGES OF A TERRESTRIAL REGION 
Description The present invention relates to a method and apparatus that can predict the visible- infrared band images of a region of the Earth's surface that would be observed by an Earth Observation (EO) satellite or other high-altitude imaging platform, using data from radar reflectance/backscatter of the same region. The method and apparatus can be used to predict images of the Earth's surface in the visible-infrared bands when the view between an imaging instrument and the ground is obscured by cloud or some other medium that is opaque to electromagnetic (EM) radiation in the visible-infrared spectral range, approximately spanning 400-2300 nanometres (nm), but transparent to EM radiation in the radio-/microwave part of the spectrum. Regular, uninterrupted monitoring of the Earth's surface is important for a wide range of applications, from agriculture to defence. 
IP Reference WO2021028650 
Protection Patent granted
Year Protection Granted 2021
Licensed Yes
Impact Aspia Space is commercialising this technology through a licence with the University of Hertfordshire. It is being applied in a number of fields, including precision agriculture, insurance, and environmental monitoring.
 
Company Name ASPIA SPACE LIMITED 
Description Founded in 2021 and based in Cornwall, UK, Aspia Space is a company pushing the limits of Earth Observation data. With over two decades of expertise in image and spectral analysis rooted in astrophysics, and bringing to bear cutting-edge deep learning techniques, Aspia Space is innovating in downstream Earth Observation analysis. We are passionate about deriving meaning from remote sensing data, unlocking value and gaining insights that others cannot. This allows our customers to make better decisions based on reliable intelligence, leading to improvements in efficiency, productivity and sustainability. 
Year Established 2021 
Impact Aspia Space is already working with Origin Digital. Origin Digital provides advanced agricultural software that enables organisations to engage with their farmer and grower customers about the output from their land, informing better on-farm and business decision making. Origin Digital is part of Origin Enterprises Group, which has leading market positions in Ireland, the United Kingdom, Poland, Romania, Ukraine, and southern Africa. Origin Enterprises PLC is listed on the XESM market of Euronext Dublin. Aspia Space has partnered with UK ag-tech company Origin Digital to bring its 'ClearSky' cloud-free imaging service to the UK agriculture sector. Farmers using the revolutionary service, launching imminently, are guaranteed to receive a satellite image every six days showing them how their crop is developing, whatever the weather. This is in contrast to traditional, weather-dependent imagery which can often have gaps of several weeks between cloud-free views.
Website https://aspiaspace.com