14TSB_ESAP: Tru-Nject: Proximal soil sensing based variable rate application of subsurface fertiliser liquid injection in vegetable/combinable crops

The research team at Cranfield will be responsible to carry out the on-line visible and near infrared (vi-NIR) measurment in
selected experimental fields. Prior and during the on-line soil measurement, soil samples will be collected for upgrading the
general calibration functions already developed at Cranfield University. These upgraded calibration functions will be
validated for accuracy estimation against laboratory measured soil organic carbon (OC), total nitrogenv(TN), pH,
phosphorous (P), magnesium (Mg), calcium (ca), moisture content (MC) and clay content (CC). The laboratory analyses of
these soil properties will be carried out in soil laboratory of Cranfield University for 300 calibration and validation soil
samples collected from the experimental fields. The upgrade of Cranfield calibration models will be based on chemometric
tools consisting of a combination of principal component analyses (PCA) and partial least squares regression (PLSR)
analysis to be carried out with Unscrambler 7.8 software (Camo Inc.; Oslo, Norway). Cranfield will also develop two types
of soil maps e.g. full-point and comparison maps using ArcGIS ArcMap (ESRI ArcGISTM version 10, CA, USA). The
comparison maps will aim to compare between on-line predicted and laboratory measured soil properties. The full-point
maps will be used for understanding and evaluation of within field variation in soil fertility, and how these are correlated with
crop growth and yield. By this, it is hoped to identify crop yield limiting factors.
Cranfield team will be also responsible for data fusion and geostatistical analysis. Data fusion will include artificial neural
network, support vector machine and other tools, as necessary. Data fusion will be carried out with STATISTICA 10
(StatSoft, Inc. USA) software. An unsupervised classification algorithm will be employed to identify spatially similar classes.
The clustering output will be imported into ArcGIS ArcMap (ESRI ArcGISTM version 10, CA, USA) to assist visualisation
and spatial analysis. A homogenous set of management zones will be derived by using a moving-window filter to minimise
the occurrence of smaller clusters. This will be followed by the development of fertility maps for the experimental fields, with
management zones of each class having similar yield potential. After the fertility maps have been developed, N
recommendation maps will be generated using RB209 (SEFRA), in collaboration with STC ltd., and agronomist Mr. Philip
Effingham.
Cranfield will also assist STC Ltd. in the cost benefit analysis to evaluate the economic viability of the system. This analysis
will be based on input data obtained from the trial plots, comparing between subsurface homogeneous and variable rate N
fertilisation. Together with Manterra, Cranfield team will assess the technology integration, to allow for final evaluation of
the system, and identify further technical and software development needed if any.
Cranfield will also play an important role in the exploitation and dissemination of the results achieved. They will lead on
publishing scientific papers in top journals on precision agriculture e.g. Precision Agriculture, Biosyatems Engineering,
Computers and Electronics in Agriculture, and top international and national conferences e.g. European Conference on
Precision Agriculture, HGCA Precision Agriculture Workshop and EurAgEng2016. The team will promote the on-line based
subsurface variable rate N application system in trade workshops e.g. Cereals. They will also provide the needed input for
training workshops organised by Manterra.

In current practice, a tractor mounted sensor to calculate Normalized Difference Vegetation Index (NDVI) detects live, green vegetation from a target area and can be used to analyse crop nutritional requirements. By adding high-resolution satellite data it is possible to achieve a variable rate (VR) fertiliser recommendation. Current practice lacks two key factors in the determination of optimum N supply to growing crops: availability of high-resolution data to inform on soil fertility status; and technologies that ensure accurate and consistent placement of nutrient. The aim of this project is to combine crop-sensing technologies with an internationally patented on-line soil visible and near infrared (vis-NIR) sensor (Mouazen, 2006) incorporating large soil fertility datasets. The nutrient will be applied in combination with a spoke-wheel fertiliser injection system, which places the nutrient subsurface into the moist rootzone of the crop, thus maximising efficiency and consistency of uptake. Extended benefits include improved farm profitability, reduction of environmental impact associated with fertiliser usage, and the production of a higher-quality and more uniform crop at harvest.

The project will have impact on sustainable intensive crop production. It will progress the development of the new paradigm
for agriculture in the UK based on within field (sub-field) land and crop management. The main purpose of this project is to
increase farms competitiveness by providing a system consisting of hardware and software that is both a support for
improved spatially targeted variable rate nitrogen application. The integration of data on soil, crop cover and yield will
furnish the farmers with ground truth decisions on applications of subsurface N fertiliser. There is a broad range of
stakeholders, with varying and often unexpected levels of potential interest in the results of the current project. The main
end users will be farmers, and farming groups. In addition, service providers (i.e. contractors, precision farming services
and agronomists) are expected to be also amongst the major project stakeholders. Homogeneous application of N fertiliser
is adopted by majority of farmers worldwide. Variable rate application is expected to result in increasing crop yield, while
reducing environmental impact by reducing amount of agrochemicals applied into the environment. The overall economic
impact will be increase farming efficiency that will affect UK farmers and farmers worldwide. More profitable agriculture
would advantage farmers as well as the wider national economy. It is foreseen that the economic saving due to the lower
amount of input applied together with the increased yield will overcome the cost of using the envisaged integrated solution.
The research is expected to have a significant positive environmental impact by enabling the reduction of fertiliser use by
only targeting areas of the field where there is need for N application. A reduction in fertiliser use would lead to reduced soil
and ground water contamination and therefore this research will be of significant interest to those concerned with the
presence of agrochemicals in the environment. The reduced amount of fertilisers will also reduce greenhouse gas emission
(GHG) global warming potential (GWP), which will have a positive impact on the environment, with reference to the EU
framework directive for "A thematic strategy on the sustainable use of pesticides" (COM(2006)372, COM(2006)778). In this
context, water utilities, deemed to be a highly influential stakeholder group are likely to be extremely important, given their
high levels of interest and influence. Since Tru-Nject is expected to lead to reduction of water contamination with
agrochemicals, it will reduce investment in extracting these chemicals from drinking water. Hence, commercial water
companies and the Environment Agency, who are responsible for protecting the ecological status of bodies of water, will
also be interested. Other potential beneficiaries from the public sector include Defra who are interested in minimising
environmental impact, whilst improving food security. Fertiliser manufacturers will benefit through improving product
stewardship and reducing environmental impact.
This project is expected to improve the reliability of management zones delineated for variable rate N applications. In
addition it is expected to make N fertilisation more cost effective by reducing the cost associated with traditional soil
sampling and laboratory analyses. Therefore, manufacturers of subsurface injectors and precision farming software will
benefit because it will improve their product performance and so make these products more attractive to farmers.
Finally, FarmingTruth precision farming service provider to be launched in 2016 will benefit from the final product of Tru-
Nject (e.g. subsurface variable rate N recommendation), as this will be a new service that FarmingTruth can provide to end
users.