Farming from space: model-data fusion approaches for simulating crop nitrogen and yield estimates

A. Revill; V. Myrgiotis; M. Williams

doi:10.1117/12.2600826

12 October 2021 Farming from space: model-data fusion approaches for simulating crop nitrogen and yield estimates

A. Revill, V. Myrgiotis, M. Williams

Proceedings Volume 11888, Space, Satellites, and Sustainability II; 118880D (2021) https://doi.org/10.1117/12.2600826
Event: Space, Satellites + Sustainability (S3), 2021, Glasgow, United Kingdom

Abstract

Farmers are under increasing pressure to manage agricultural resources in a more sustainable and efficient manner. Information on crop nitrogen (N) status can be used to support variable rate fertiliser applications. Furthermore, yield forecasts can aid the logistical planning of harvest operations and ameliorate any negative economic impacts on food supply chains. Complex crop models simulating crop N dynamics and yields often require extensive model inputs that are seldom available. By combining observations of leaf area index (LAI) with a process-based crop model, this research presents a novel and scalable analytical solution for generating robust daily estimate of wheat N and yield, which can be applied at the sub-field scale. The crop model, DALEC-Crop, is a carbon cycle model that simulates the key processes involved in crop growth and development in response to daily meteorological observations. The model was first calibrated for wheat leaf N and yields across field experiments covering N applications ranging from 0 to 200 kg N ha^-1 for two consecutive growing seasons. Leaf N was accurately retrieved by the model (NRMSE = 6%). Yield could also be reasonably estimated (NRMSE = 11%). Using these developments at the plot scale, the model yield estimates had a high agreement with observations (mean R² = 0.7 and NRMSE = 7%) when applied at the sub-field scale across field sites under the constraints of Sentinel-2 data. Although additional field sites and seasons are required for further testing, the modelling approach could be feasibly applied to estimate yields across large areas with only minimal inputs.

Conference Presentation

Citation Download Citation

A. Revill, V. Myrgiotis, and M. Williams "Farming from space: model-data fusion approaches for simulating crop nitrogen and yield estimates", Proc. SPIE 11888, Space, Satellites, and Sustainability II, 118880D (12 October 2021); https://doi.org/10.1117/12.2600826

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available