<?xml version="1.0" encoding="UTF-8"?><ns2:project xmlns:ns1="http://gtr.rcuk.ac.uk/gtr/api" xmlns:ns2="http://gtr.rcuk.ac.uk/gtr/api/project" xmlns:ns3="http://gtr.rcuk.ac.uk/gtr/api/fund" xmlns:ns4="http://gtr.rcuk.ac.uk/gtr/api/person" xmlns:ns5="http://gtr.rcuk.ac.uk/gtr/api/project/outcome" xmlns:ns6="http://gtr.rcuk.ac.uk/gtr/api/organisation" ns1:created="2026-06-03T15:52:43Z" ns1:href="http://gtr.ukri.org/gtr/api/projects/9AF03071-63ED-4AE5-A12F-BEE16707ECF7" ns1:id="9AF03071-63ED-4AE5-A12F-BEE16707ECF7"><ns1:links><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/persons/8EF9AF99-519E-4397-8A9F-F493CF71EC8F" ns1:rel="PM_PER"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/0D591577-49C6-432C-9C71-B36DCBD45269" ns1:rel="LEAD_ORG"/><ns1:link ns1:href="http://gtr.ukri.org/gtr/api/organisations/0D591577-49C6-432C-9C71-B36DCBD45269" ns1:rel="PARTICIPANT_ORG"/><ns1:link ns1:end="2021-09-29T23:00:00Z" ns1:href="http://gtr.ukri.org/gtr/api/funds/5FAEAEB8-980A-4730-8566-9E9823F4369B" ns1:rel="FUND" ns1:start="2020-03-31T23:00:00Z"/></ns1:links><ns2:identifiers><ns2:identifier ns2:type="RCUK">45016</ns2:identifier></ns2:identifiers><ns2:title>Variable Rate Applications for Agrochemical Inputs per Head of Lettuce</ns2:title><ns2:status>Closed</ns2:status><ns2:grantCategory>Study</ns2:grantCategory><ns2:leadFunder>Innovate UK</ns2:leadFunder><ns2:abstractText>Lettuce growers currently make 7 to 8 'interventions' in the course of a crop life-cycle listed below;

* Soil testing / Base nutrient (N,P,K) application
* Planting - Phosphorous (P) application
* VRN Trials
* Weeding and nitrogen (N) application at 3 weeks
* Weekly pass with prophylactic pesticide, 6 to 7 applications in total
* Secondary fertiliser application
* Harvest
* Post-harvest herbicide application

For each intervention, Hummingbird will collect and analyse data and subsequently conduct trials to build models that can help growers target their interventions more effectively, efficiently and profitably. The ultimate aim for this project is to allow growers to achieve data driven variable rate applications per individual plant based on the plant's needs.

Each area is highlighted below:

Base Application: _Soil_

1. Field History: Field shapefiles, Digital Elevation Models (DEM), previous crops, and soil quality reports. This will form the 'Evidence' used to determine the current quality of the field.
2. Application Model: taking field history and crop type as inputs, determining the nutrient requirements of the field in an idealised application.
3. Instruction Generation: considering physical constraints (farm machinery used, fertiliser available, etc) converting the ideal application into a variable rate instruction map.

Plant Applications: nitrogen &amp;amp; pesticides_

1. Sizing &amp;amp; counting maps: NDVI from remote sensed imagery will be combined with elevation maps, soil and weather data to generate the idealised application. Data on the crop performance and response to the first application will then be used to inform the subsequent applications.
2. Application Model: Using the results from step 1 - determining the nutrient requirements of the field in an idealised application.
3. Instruction Generation: considering physical constraints (farm machinery used, fertiliser available) and converting the ideal application into a variable rate instruction map.

Pesticides: Disease resistant varieties are currently given unnecessary pesticide applications as they are planted in the field with non-resistant varieties. Shapefile application maps based on variety type will target these applications where needed.

Harvest: Most yield loss occurs at harvest due to plants that are either too small/big. Base &amp;amp; Plant Applications will aim to reduce this variability but continuations of the sizing &amp;amp; counting maps will direct the harvest rig to areas of the field that, due to their size, will be ready first then onto the next zone.

Post-harvest Herbicide: Vary rates according to; harvested crops, residual crops and weeds thereby reducing chemical overspray, potential runoff and environmental impact.</ns2:abstractText></ns2:project>