About the project
This project focuses on leveraging remote sensing data (satellite imagery and related datasets) to produce high-resolution, low-cost socioeconomic and environmental maps, with a particular emphasis on scalable algorithms rooted in submodularity and combinatorial optimization.
The broader goal is to transform the growing availability of satellite imagery (e.g., from Planet Labs, SkyBox, SpaceX Starlink) into actionable insights for sustainability domains such as poverty mapping, pollution monitoring and transportation planning, where ground-truth data is scarce or expensive to collect.
Computational Sustainability (CS) seeks to balance environmental, economic, and social needs by developing optimization and machine learning methods that support sustainable decision-making. Prior work has shown that neural networks on satellite imagery can predict poverty indicators (e.g, Jean, Science, 2016; Yeh, Nature, 2020), and that remote sensing supports pollution mapping (e.g., Duncan et al., Environmental Science & Technology, 2014), the key challenges remain: scalability.
Current methods rely heavily on deep learning with extensive ground-truth data. These models are computationally expensive and struggle to adapt across regions with limited labeled data. Interpretability: Deep learning approaches often provide little transparency in features selection, which is critical for policy adoption in sustainability contexts. Efficient use of limited ground data: ground-truth surveys (e.g., World Bank LSMS) are sparse, costly, and unevenly distributed. Methods to optimally select where and what data to collect remain underdeveloped.
Novelty of the project: introduce submodularity-based optimization into the remote sensing for sustainability pipeline. Submodular functions, with their property of diminishing returns, are well-suited for:
- data subset selection (choosing the most informative satellite images or features to annotate/ground-truth)
- sensor placement & survey design (optimizing where to deploy costly ground measurements)
- interpretability (since submodular optimization often selects representative and diverse features, offering insights into spatial drivers of poverty and pollution)
- integrate nonnegative matrix factorization (NMF) with submodular priors to generate interpretable latent factors from high-dimensional satellite data - develop a low-cost pipeline that requires minimal ground data but achieves comparable or better predictive performance than purely deep learning-based approaches.
This combination of 'remote-sensing' + 'submodular optimization' +' interpretable factorization' has not been systematically applied to computational sustainability, filling a research gap between "black-box" predictive models and actionable, resource-aware methods.
This is part of the UKRI AI Centre for Doctoral Training in AI for Sustainability (SustAI), a 4-year integrated programme (iPhD). You will be part of a dynamic and diverse cohort, benefiting from expert mentorship and interdisciplinary collaboration. The programme includes comprehensive training in sustainability, AI and machine learning, and digital design, preparing students for a career at the forefront of research in this area. Students will have access to state-of-the-art facilities and resources, fostering an environment of innovation and excellence.
The School of Electronics & Computer Science is committed to promoting equality, diversity inclusivity as demonstrated by our Athena SWAN award. We welcome all applicants regardless of their gender, ethnicity, disability, sexual orientation or age, and will give full consideration to applicants seeking flexible working patterns and those who have taken a career break. The University has a generous maternity policy, onsite childcare facilities, and offers a range of benefits to help ensure employees’ well-being and work-life balance. The University of Southampton is committed to sustainability and has been awarded the Platinum EcoAward.
