Application Deadline: 31 January 2026
Details
Irrigation is critical to food security and climate resilience, producing 40% of the world’s food on just 20% of farmland. But irrigated agriculture also accounts for 70% of global freshwater withdrawals, driving water scarcity and insecurity. Monitoring irrigation is therefore essential to support the design and implementation of sustainable water and agricultural management. However, traditional methods of monitoring irrigation wate use (e.g., field surveys, in-situ sensors) are costly and inefficient. Satellite remote sensing provides a scalable alternative, enabling agricultural land and water use to be mapped over large areas at high temporal frequencies. However, the challenge lies in converting vast, complex satellite datasets into actionable insights—such as where irrigation is expanding, what technologies are being used, and how efficiently water is applied.
This PhD project will pioneer the use of deep learning (DL) techniques to detect and forecast irrigation practices across global agricultural systems. While conventional machine learning (e.g., Random Forests) has been used to monitor irrigation, DL offers the potential to improve our ability to quantify and forecast complex spatial and temporal patterns of irrigation leveraging the growth of big geospatial data including satellite imagery. The project will address three key research questions:
- Can DL outperform conventional machine learning in monitoring irrigation, and how does accuracy vary across indicators (e.g., irrigated area vs. volumetric abstraction)?
- How transferable are DL models across different geographies (Europe, North America, Africa) and farming systems (smallholder vs. commercial)?
- Can DL, when integrated with physics-based crop models (e.g. AquaCrop-OSPy), improve forecasts of irrigation demand under climate, land-use, or management change?
The project will benefit from access to extensive groundtruth observations of irrigated land and water use collected via major international projects led by the supervisory team (TRANSCEND, IrrEO, IaaS) and via longstanding collaborations with global partners.
Expected Outcomes
A key expected outcome of the PhD project will be the development of robust DL-based tools for irrigation monitoring and forecasting, which provide intelligence for governments, donors, agribusiness, and regulators to support and enable sustainable and resilient water management. It is anticipated that the project will lead to high-impact publications in leading interdisciplinary journals (e.g., Nature Sustainability, Environmental Science & Technology), and that the selected candidate would have the ability to embed their research in major global projects led by the supervisory team (e.g. ongoing work with the Gates Foundation to develop national-scale irrigation mapping tools for governments in Africa).
Training and Supervision
The successful candidate will be supported by an interdisciplinary supervisory team with expertise in water engineering, AI and data science, remote sensing, and crop modelling, who all have extensive prior expertise in interdisciplinary research that develops data-driven solutions to global environmental challenges. As part of the PhD, the candidate will benefit from bespoke technical and transferable skills training, access to relevant MSc-level courses within University of Manchester (e.g., Earth and Environmental Data Science), participation in international research networks (e.g., IAHS irrigation working group), and integration into the vibrant postgraduate research community of the Manchester Environmental Research Institute (MERI).
How to apply: To be considered for this project you’ll need complete a formal application through our online application portal. If you already have an applicant account this link will directly open an application for FSE Bicentenary PhD. If you don’t already have an applicant account, please follow the instructions here.
When applying, you’ll need to specify the full name of this project, the name of your proposed supervisor/s, details of your previous study, and names and contact details of two referees. You also need to provide a Personal Statement describing the motivation to apply to the project and your CV. Your application cannot be processed without all of the required documents, and we cannot accept responsibility for late or missed deadlines where applications are incomplete.
Equality, diversity and inclusion: Equality, diversity and inclusion are fundamental to the success of The University of Manchester, and are at the heart of all of our activities. We know that diversity strengthens our research community, leading to enhanced research creativity, productivity and quality, and societal and economic impact. We actively encourage applicants from diverse career paths and backgrounds and from all sections of the community, regardless of age, disability, ethnicity, gender, gender expression, sexual orientation and transgender status.
We also support applications from those returning from a career break or other roles. We consider offering flexible study arrangements (including part-time: 50%, 60% or 80%, depending on the project/funder).
Eligibility: Applicants are expected to hold (or be about to obtain) a minimum upper second-class undergraduate honours degree (or equivalent). An additional master’s level degree is also desirable. Degree education should be in a relevant field or discipline such as data or computer science, remote sensing, environmental science, physical geography, agricultural or water engineering, or other related disciplines.
In addition to their educational background, candidates are required to also demonstrate strong programming proficiency (preferably in Python or R), awareness of and/or experience applying machine/deep learning techniques in their studies, prior research and/or work experience, and a strong interest in applying AI and data science methods to solve global environmental and sustainability challenges.
Prior knowledge and experience of irrigation is not a requirement for this project, and specialist training on irrigation fundamentals and modelling would be provided as part of the PhD training programme.
FSE_Bicentenary
Funding Notes
Funding for this project covers tuition fees, UKRI minimum annual stipend (currently ÂŁ20,780/annum) and up to a ÂŁ5k/annum research training support grant for the full duration of the 4-year programme.
