Advanced technologies for efficient crop management: A participatory approach with application at farm scale

Lead Research Organisation: University of Edinburgh
Department Name: Sch of Geosciences

Abstract

Changing climate, variable yields, and resource constraints are challenging UK agriculture and global food security. Our goal is to enhance sustainable and efficient production for two crops of major importance in the UK, wheat and potatoes. We will work with farmers and end users in the application and deployment of novel crop sensing and diagnostic technologies. We will develop a tool that can predict and diagnose crop response to water and nutrient related limits. In turn, this knowledge will guide crop management and help to inform stakeholders from across the arable supply chain about the best approaches for land management towards more sustainable and efficient production, using precision agriculture.
We will test remote sensing technologies and couple them with methods for analysing crop and soil processes. We will deploy sensors at farm sites on fixed towers and unmanned aerial vehicles (UAV), and compare these against satellite sensors with global coverage. We will evaluate whether changes in leaf temperature, fluorescence and reflectance are related to yield reductions, comparing sensor data against field measurements of plant growth, yield and ecophysiology, and plant and soil temperature and moisture. We will understand how, and under what circumstances, sensors and platforms can be employed to determine and diagnose crop yield limits. Links to simulation process modelling will provide a rich set of diagnostics related to the plant-soil system, and forecast its sensitivity to management changes. Data assimilation approaches will allow model updates and improvements based on field observations and sensor output, to generate more reliable, near real-time and robust analyses.
Our technologies will underpin a crop diagnostic system, indicating crop water and nutrient status, quantifying reductions to yield, that can be used at sub-field to farm scale, with a clear quantification of reliability. Working with farmers, our technologies will be combined to generate a decision support tool, with capacity for (i) immediate (near-real time) mapping of crop stress, and its likely impact on crop yield and (ii) providing detailed spatial information on optimal management interventions to support decision making for sustainable high yield.
This work directly addresses a priority of the UK research councils to support UK farming with high quality and practical research to support consistent high returns from crop production against a background of changing climate and increasingly competitive global markets. Our deliverables will provide advanced diagnostics for farmers, and guide cost effective strategies for water and nutrient management for consistent yield.

Technical Summary

We will develop technologies with the ability to predict, analyse and guide response to yield reduction for specific UK crop production systems (wheat and potatoes), with a focus on water and nutrient challenges. Using these technologies, in partnership with farmers and other stakeholders, we will construct a tool to inform better management decisions, to minimise risk and improve efficiency of resource use. Our key technologies are multi-platform sensors, process modelling, and data assimilation algorithms for generating robust diagnostics and analyses. A challenge for farmers is to know when and how much fertiliser to apply, so that nutrient limitations to yield are avoided, while the use of agronomic inputs are minimised and made more efficient. We will evaluate technologies to determine in near real time the degree of nutrient limitation (with N as a focus) and the optimal timing and amount of fertilizer addition. A second challenge for farmers is to understand the effects of moisture stress on yield, to evaluate the potential benefits of irrigation or soil improvement for water retention, on yield. We will produce toolkits that determine the degree of such limitation and its links to soil structure and water inputs, at high spatial resolution (sub-field) and up to farm scale. Central to this proposal is the understanding that attitudes, behaviours and networks of end users must be integrated into the development of the tool from the start. The 'Innovation Systems' approach recognises that the needs and application opportunities of end users must be understood and integrated into the final tool in order to increase uptake and relevance. This proposal will include a robust social science work package, fully integrated, providing a range of opportunities for the co-creation of a user friendly tool.

Planned Impact

Improving resource use efficiency and yield stability are critical challenges faced by the UK agricultural sector at a time of increasing climate variability and resource scarcity. The outcomes of our research into these topics will therefore be highly relevant to the development of the wheat and potato sectors in coming decades.
We will work with farmers and agronomists to develop an effective support tool for more sustainable and reliable yield, linking to our activities on Focus Farms and Monitor Farms, and discussions with Arable Business Groups. We will have project demonstrations at SRUC and AHDB events. Close engagement with SARIC members will be sought for maximum impact on growers (e.g. AHDB), technological applications (e.g. Ursula) and for international crop sustainability (ABagri).
Other businesses, related to precision farming technology, environmental and fertilizer management, will be encouraged to have direct involvement in the evaluation and adoption of crop and land management practices emerging from this project through our workshops and open-days.
We will engage with policy makers through APHA, SASA, and with Scottish policy advisers linked to the Centre for Expertise in Climate Change, the Centre for Knowledge Exchange and Impact (CKEI) and the newly developing Centre of Expertise on Plant Health, through generating policy notes.
The role of our consortium partner SRUC as a founder member of the Centre for Agricultural Informatics and Sustainability (AIMS) and the Agricultural Engineering Precision Innovation Centre will ensure close liaison, benefits from their industry links, and maximum interactions with related projects. Connections to the centres will ensure (i) data originating from the project are fully integrated for use by the research community with wider assessment of their agricultural development, and (ii) the evaluation and uptake by industry partners of new technology from the outcomes of our research.
The amplification of our research through the involvement of experimental and validation platforms across a network of commercial farms will ensure the maximum potential impact of our research. There will also be an opportunity to deploy new decision support tools through the national consultancy service operated by SRUC, using its existing network of advisory offices and staff. Understanding the attitudes and behaviours among a network of end users will be integrated into the development and uptake of decision tools. The project will work with AHDB in local and national knowledge exchange activities to demonstrate technologies and support tools, and their value in adoption on farm.
We will discuss with relevant SARIC industry members (including water companies) the potential value generated by our landscape analyses of soil states for water management and conservation. Our dissemination programme to the farming community and supporting industries will be extended to outreach activities including the Edinburgh International Science Festival, with an exhibit based on the technologies developed and a prototype of the decision support tool displayed to the public. Our UAV for capturing information on crop and soil status, will be displayed, with videos of it in action, and the data it records. Across all our activities, presented in the Pathways to Impact, we will explain the technologies we are deploying, the challenges we are addressing and opportunities gained in our research.

Publications

10 25 50
 
Description Leaf Area Index (LAI) and chlorophyll content are strongly related to plant development and productivity. Spatial and temporal estimates of these variables are essential for efficient and precise crop management. The availability of open-access data from the European Space Agency's (ESA) Sentinel-2 satellite-delivering global coverage with an average 5-day revisit frequency at a spatial resolution of up to 10 metres-could provide estimates of these variables at unprecedented (i.e., sub-field) resolution. We evaluated the potential of Sentinel-2 data for retrieving winter wheat LAI, leaf chlorophyll content (LCC) and canopy chlorophyll content (CCC). In coordination with destructive and non-destructive ground measurements, we acquired multispectral data from an Unmanned Aerial Vehicle (UAV)-mounted sensor measuring key Sentinel-2 spectral bands (443 to 865 nm). We applied Gaussian processes regression (GPR) machine learning to determine the most informative Sentinel-2 bands for retrieving each of the variables. We further evaluated the GPR model performance when propagating observation uncertainty. When applying the best-performing GPR models without propagating uncertainty, the retrievals had a high agreement with ground measurements-the mean R2 and normalised root-mean-square error (NRMSE) were 0.89 and 8.8%, respectively. When propagating uncertainty, the mean R2 and NRMSE were 0.82 and 11.9%, respectively. When accounting for measurement uncertainty in the estimation of LAI and CCC, the number of most informative Sentinel-2 bands was reduced from four to only two-the red-edge (705 nm) and near-infrared (865 nm) bands. This research demonstrates the value of the Sentinel-2 spectral characteristics for retrieving critical variables that can support more sustainable crop management practices
Exploitation Route This research shows the optimal spectral bands from Sentinel 2 for characterising crops. This information can be used to enhance data products from satellite sensors for supporting agricultural yield and food security applications.
Sectors Agriculture, Food and Drink

URL https://doi.org/10.3390/rs11172050
 
Description Our findings have now generated licensed technology that are being taken to commercialisation by a spin out company, Mercury Ltf.
First Year Of Impact 2022
Sector Agriculture, Food and Drink
Impact Types Economic

 
Description Agri-Tech in China Newton Network+
Amount £124,413 (GBP)
Funding ID LG007 
Organisation Rothamsted Research 
Sector Academic/University
Country United Kingdom
Start 04/2018 
End 03/2019
 
Description Cocoa; future yields across West Africa
Amount £131,084 (GBP)
Funding ID NE/S013598/1 
Organisation Natural Environment Research Council 
Sector Public
Country United Kingdom
Start 11/2019 
End 05/2021
 
Description Model-Data fusion CARbon DAta MOdel fraMework (CARDAMOM) and DALEC-Crop - IAA grant
Amount £20,964 (GBP)
Organisation Biotechnology and Biological Sciences Research Council (BBSRC) 
Sector Public
Country United Kingdom
Start 09/2021 
End 01/2022
 
Description Trade in Space - Satellite Analytics Project
Amount £70,000 (GBP)
Organisation The Datalab 
Sector Charity/Non Profit
Start 08/2019 
End 02/2020
 
Title ATEC manuscript 1 - supporting data: "The value of Sentinel-2 spectral bands for the assessment of winter wheat growth and development" 
Description Manuscript Figure 2a. Destructive sample and non-destructive (Delta-T SunScan device) of winter wheat leaf area index (LAI) at the ATEC experimental trial plots. measurements. (952bytes) Manuscript Figure 2b. Chlorophyl meter leaf measurement (SPAD; x 10 replicates) and leaf nitrogen (N) content estimates derived from destructive leaf samples (x 2 replicates) from the ATEC winter wheat experimental trial plots. (2.818Kb) Manuscript Figure 1. Vector grid (ESRI Shapefile) outlining the ATEC East Saltoun 2017/2018 wheat trial plots. Vector dataset is shown in Figure 1 and used for sampling multispectral unmanned aerial vehicle (UAV) data included in the analysis detailed in this manuscript.. (4.348Kb) Orthomosaic geotif files generated from the UAV multispectral camera (MAIA-S2) acquisitions over the ATEC experimental winter wheat trial plots. Files correspond to orthomosaics generated from observation dates corresponding to five key wheat growth stages (see description in manuscript Table 1). Imagery files composed of 10 bands. The first nine are spectral bands centred on 443 nm (band 1), 490 nm (band 2), 560 nm (band 3), 665 nm (band 4), 705 nm (band 5), 740 nm (band 6), 783 (band 7), 842 nm (band 8), 865 nm (band 9). The imagery also include the image alpha band/mask (i.e. band 10). (226.7Mb) 
Type Of Material Database/Collection of data 
Year Produced 2020 
Provided To Others? Yes  
Impact Data supports the publication 
URL https://doi.org/10.7488/ds/2883
 
Title ATEC manuscript 2 - supporting data: "Quantifying Uncertainty and Bridging the Scaling Gap in the Retrieval of Leaf Area Index by Coupling Sentinel-2 and UAV Observations" 
Description Leaf area index (LAI) estimates can inform decision-making in crop management. The European Space Agency's Sentinel-2 satellite, with observations in the red-edge spectral region, can monitor crops globally at sub-field spatial resolutions (10-20 m). However, satellite LAI estimates require calibration with ground measurements. Calibration is challenged by spatial heterogeneity and scale mismatches between field and satellite measurements. Unmanned Aerial Vehicles (UAVs), generating high-resolution (cm-scale) LAI estimates, provide intermediary observations that we use here to characterise uncertainty and reduce spatial scaling discrepancies between Sentinel-2 observations and field surveys. We use a novel UAV multispectral sensor that matches Sentinel-2 spectral bands, flown in conjunction with LAI ground measurements. UAV and field surveys were conducted on multiple dates-coinciding with different wheat growth stages-that corresponded to Sentinel-2 overpasses. We compared chlorophyll red-edge index (CIred-edge) maps, derived from the Sentinel-2 and UAV platforms. We used Gaussian processes regression machine learning to calibrate a UAV model for LAI, based on ground data. Using the UAV LAI, we evaluated a two-stage calibration approach for generating robust LAI estimates from Sentinel-2. The agreement between Sentinel-2 and UAV CIred-edge values increased with growth stage-R2 ranged from 0.32 (stem elongation) to 0.75 (milk development). The CIred-edge variance between the two platforms was more comparable later in the growing season due to a more homogeneous and closed wheat canopy. The single-stage Sentinel-2 LAI calibration (i.e., direct calibration from ground measurements) performed poorly (mean R2 = 0.29, mean NRMSE = 17%) when compared to the two-stage calibration using the UAV data (mean R2 = 0.88, mean NRMSE = 8%). The two-stage approach reduced both errors and biases by >50%. By upscaling ground measurements and providing more representative model training samples, UAV observations provide an effective and viable means of enhancing Sentinel-2 wheat LAI retrievals. We anticipate that our UAV calibration approach to resolving spatial heterogeneity would enhance the retrieval accuracy of LAI and additional biophysical variables for other arable crop types and a broader range of vegetation cover types. 
Type Of Material Database/Collection of data 
Year Produced 2020 
Provided To Others? Yes  
Impact Supports the ATEC publications 
URL https://doi.org/10.7488/ds/2889
 
Title ATEC manuscript 3 - supporting data: "Combining Process Modelling and LAI Observations to Diagnose Winter Wheat Nitrogen Status and Forecast Yield" 
Description Climate, nitrogen (N) and leaf area index (LAI) are key determinants of crop yield. N additions can enhance yield but must be managed efficiently to reduce pollution. Complex process models estimate N status by simulating soil-crop N interactions, but such models require extensive inputs that are seldom available. Through model-data fusion (MDF), we combine climate and LAI time-series with an intermediate-complexity model to infer leaf N and yield. The DALEC-Crop model was calibrated for wheat leaf N and yields across field experiments covering N applications ranging from 0 to 200 kg N ha-1 in Scotland, UK. Requiring daily meteorological inputs, this model simulates crop C cycle responses to LAI, N and climate. The model, which includes a leaf N-dilution function, was calibrated across N treatments based on LAI observations, and tested at validation plots. We showed that a single parameterization varying only in leaf N could simulate LAI development and yield across all treatments-the mean normalized root-mean-square-error (NRMSE) for yield was 10%. Leaf N was accurately retrieved by the model (NRMSE = 6%). Yield could also be reasonably estimated (NRMSE = 14%) if LAI data are available for assimilation during periods of typical N application (April and May). Our MDF approach generated robust leaf N content estimates and timely yield predictions that could complement existing agricultural technologies. Moreover, EO-derived LAI products at high spatial and temporal resolutions provides a means to apply our approach regionally. Testing yield predictions from this approach over agricultural fields is a critical next step to determine broader utility. 
Type Of Material Database/Collection of data 
Year Produced 2021 
Provided To Others? Yes  
Impact Supports an ATEC publication 
URL https://doi.org/10.7488/ds/2989
 
Description Environment Systems 
Organisation Environment Systems
Country United Kingdom 
Sector Private 
PI Contribution We have summarised the research data we have generated from drone and in situ studies on crop.
Collaborator Contribution ES have provided insights into the products they would like to generate for their customers, guiding us towards the analyses we could undertake - specifically on the information content of radar data. ES have provided access to satellite databases to advance our activity.
Impact This work is ongoing.
Start Year 2017
 
Description Agri-Tech in China Newton Network+ meeting Beijing; Wuhan University visit, seminar and student lecture 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact Attended and spoke at Agri-Tech in China Newton Network+ meeting in Beijing, addressing UK and Chinese researchers in agriculture and food security.
Visited Wuhan University and delivered departmental seminar and a training lecture to undergraduate students.
Year(s) Of Engagement Activity 2019
 
Description Potsdam GHG Flux workshop 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact Scientific workshop on novel techniques to measure greenhouse gas exchanges
Year(s) Of Engagement Activity 2017
 
Description SAC Association of Potato Producers, 20th Annual Conference 2019, Perth, Scotland 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact SAC Association of Potato Producers, 20th Annual Conference 2019, Perth, Scotland
Year(s) Of Engagement Activity 2018
 
Description SARIC 2018 Dissemination event, Manchester - October 10-11th 2018 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact SARIC 2018 Dissemination event, Manchester - October 10-11th 2018
Year(s) Of Engagement Activity 2018
 
Description SARIC Dissemination Event, Oxford 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact This was a dissemination event for the Sustainable Agriculture Research and Innovation Club. We presented our research outputs to a mix of academics and industry. We held some breakouts with industry representatives to discuss knowledge transfer.
Year(s) Of Engagement Activity 2017
 
Description Stakeholder participation workshop 
Form Of Engagement Activity A formal working group, expert panel or dialogue
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact In December 2017 ATEC project partners met with 4 growers who had expressed interest in imagining for crop management. Researchers presented the initial images and processed data from the first year of the ATEC project, and a facilitated discussion took place focusing on growers interpretation of the technology and data. The findings of this workshop will be combined with other engagement activities and fed into the development of the second year of data collection in the ATEC project.
Year(s) Of Engagement Activity 2017
 
Description Talk at Royal Botanic Gardens Edinburgh symposium 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact A talk on biodiversity from space to a broad audience from research, policy, NGOs and education
Year(s) Of Engagement Activity 2020