Postgraduate research opportunities

Multimodal remote sensing and Machine Learning for Precision Agriculture

The project will explore the use of Machine Learning for the analysis and fusion of data from multiple sensors in agricultural applications. Satellite and drone multispectral imagery together with ground sensors will inform decision support tools for advanced farm management.

Number of places



7 March 2021


3 years


Students applying should have (or expect to achieve) a minimum 2.1 undergraduate degree in a relevant engineering/science discipline, and be highly motivated to undertake multidisciplinary research.

Knowledge and/or experience in data analytics, data fusion, machine learning, programming skills (e.g. Python, Matlab, PyTorch/TensorFlow), multispectral/hyperspectral imaging and agricultural systems are desirable.

Project Details

With the world population expected to reach 8.5 billion by 2030 and 9.7 billion by 2050, the demand for food and agricultural products will rise significantly in the coming years. In order to meet this requirement without significant impact on the environment, the agricultural sector will need to develop new innovative solutions that increase production efficiency using the same land resources. Decision support tools for Precision Agriculture that enable farmers to take informed actions based on more accurate and relevant data are therefore essential. Aerial imaging of farms from satellites, planes and drones can provide useful information to enable precise soil mapping and crop classification, enhance crop yield and manage fertiliser application. Combined with a network of sensors on the ground that yield granular data on soil conditions, these data streams constitute the base to assess the state of the farm continuously and predict future outcomes early in the season. However, individual sensors generally show limitations in terms of spatial and temporal resolution due to reduced availability of data, affordability, and the effect of adverse weather conditions. This restricts the ability of models based on a single source of data to produce reliable predictions of the performance of farms at the early stages of crop life.

The aim of the project is to investigate the use of Machine Learning and Deep Learning methods for the analysis and fusion of data streams to derive consistent and reliable information for farm management. The main challenge will be to integrate the different spatio-temporal resolutions of the data into accurate solutions for farmers. Through continuous engagement with key industrial partners, the project will ensure the relevance of the research and will catalyse the ongoing revolution in the agricultural sector.

In addition to undertaking cutting edge research, students are also registered for the Postgraduate Certificate in Researcher Development (PGCert), which is a supplementary qualification that develops a student’s skills, networks and career prospects.

Information about the host department can be found by visiting:

Funding Details

This PhD project is initially offered on a self-funding basis. However, excellent candidates will be considered for a University scholarship.


Contact us

James Weir Building, 75 Montrose Street, Glasgow, G1 1XJ

How to apply

Apply for this project here – please quote the project title in your application.

During the application you'll be asked for the following information and evidence uploaded to the application:

  • your full contact details
  • transcripts and certificates of all degrees
  • proof of English language proficiency if you are not from a majority English-speaking country as recognised by UKVI
  • two references, one of which must be academic. Please see our guidance on referees
  • funding or scholarship information
  • international students must declare any previous UK study

By filling these details out as fully as possible, you'll avoid any delay to your application being processed by the University.

Useful resources

Your application and offer

Application System Guide

Fees and funding