Tools for precision agriculture, climate resilience and environmental benefits

 

3 Minute read

Applications are no longer being accepted for this project

This is one of two research projects developing new data-driven tools for precision agriculture, climate resilience and environmental benefits. The University of Melbourne is the home institution for this project.

Quantifying N loss from agriculture to the environment is crucial for addressing crop productivity, environmental degradation and climate change, as well as the efficiency and profitability of food production.

To achieve efficient agricultural N management, agroecosystem simulation models are often used to simulate, predict and evaluate the impacts of management practices on N losses through different pathways.

However, the wide application of these models is hindered by tedious, costly and stringent calibration and validation processes. It is often impractical or ineffective to calibrate and validate process-based models against data for all experimental sites where the data originates.

Therefore, we need to find a novel way to model the linkage between N loss pathways and soil, environmental and climatic conditions to address the limitations of process-based models.

Machine learning provides a promising way, which allows complex relationships between input and output variables to be modelled in a data-driven way and enables revealing important relationships never recognised previously.

Multispectral/hyperspectral remote sensing data are now available for calibrating, parameterising and validating agroecosystem models.

Project goals

By incorporating machine-learning-based data analytics into agroecosystem process-based modelling, this project aims to advance the simulation capacity and prediction reliability of process-based models. The research findings are highly relevant to agricultural management, agricultural policy-making and environmental quality. The success of this project will result in:

  • Significant advances in process-based modelling, decision support systems, and hence improvement in N management in agroecosystems and environmental quality;
  • Providing promising directions for sustainable agriculture and food security that are of national and international significance, and will be beneficial to the economy, society and environment; and
  • Being highly beneficial to digital and high-precision agriculture and relevant to the development of environmental costs for N pollution damage to biodiversity, the society and the environment.

Supervision team

The University of Melbourne: Doctor Shu Kee LamDoctor Alexis PangProfessor Pablo Zarco Tejada

*Click on the researcher's name above to learn more about their publication and grant successes.

The University of Manchester: Doctor Tim FosterDoctor Ben Parkes

Who we are looking for

We are seeking a PhD candidate with the following skills:

  • Demonstrated experience in the field of biogeochemistry and machine learning.
  • Demonstrated experience with optimisation/modelling.
  • Demonstrated ability to work independently and as part of a team.
  • Demonstrated time and project management skills.
  • Demonstrated ability to write research reports or other publications to a publishable standard (even if not published to date).
  • Excellent written and oral communication skills.
  • Demonstrated organisational skills, time management and ability to work to priorities.
  • Demonstrated problem-solving abilities.

Further details

The PhD candidate will benefit from the combined expertise of the project supervisors, and the embedding into two research environments.

This PhD project will be based at the University of Melbourne with a minimum 12-month stay at the University of Manchester.

The candidate will be enrolled in the PhD program at the Department of Agriculture and Food at the University of Melbourne and in the PhD program at the Department of Mechanical, Aerospace and Civil Engineering (MACE) at the University of Manchester.

Dr Shu Kee Lam at the University of Melbourne will contribute expertise in soil carbon and nitrogen dynamics in agroecosystems, Dr Alexis Pang will contribute expertise in GIS application and modelling, and Professor Pablo Zarco-Tejada will contribute expertise in thermal and hyperspectral remote sensing imagery. These align closely with ongoing research within Dr Tim Foster and Dr Ben Parkes’ research group focused on the development of data-driven crop yield modelling (including several long-term projects using the APSIM model (which the Melbourne candidate will use) and data assimilation approaches for precision agricultural management (e.g., irrigation use and crop choice optimisation) in farming systems globally.

The candidate will benefit from these related projects through access to relevant datasets (e.g. agricultural surveys, field datasets) to support calibration and validation of modelling approaches developed in the PhD, along with access to wider University of Manchester expertise in agronomy and soil science through the N8 Agri-Food Network and Manchester Environmental Research Institute (MERI).

Applications are no longer being accepted for this project

First published on 21 March 2023.


Share this article