Skip to content

Science Topic

Artificial intelligence and machine learning

We apply artificial intelligence and machine learning techniques to address environmental challenges

Artificial Intelligence (AI) and Machine Learning (ML) is a rapidly growing and increasingly important research technique, with potential applications in all aspects of research. As more and more environmental data is collected, AI/ML is playing a vital role in analysing, interpreting, and producing meaningful outputs for use by other researchers and wider society.

Through the NERC (Natural Environment Research Council) Earth Observation Data Acquisition and Analysis Service (NEODAAS), PML has a team of AI/ML experts that can consult, advise, train, and provide support on the development and use of AI/ML in environmental research.

Alongside PML’s AI/ML experts, state-of-the-art AI infrastructure has been installed in a bespoke, energy efficient data centre. The MAssive GPU cluster for Earth Observation (MAGEO) is an incredibly powerful computer intended to apply artificial intelligence algorithms to Earth observation (EO) data, to help develop ‘environmental intelligence’ applications that leverage patterns in the natural world. Work already undertaken on the system includes research on wildfires, oil spills, microplastic detection and habitat mapping
 

Selected publications


Smyth T, Moffat D, Tarran G, Sathyendranath S, Ribalet F, Casey J. Determining drivers of phytoplankton carbon to chlorophyll ratio at Atlantic Basin scale. Frontiers in Marine Science. 2023 Jul 11. https://doi.org/10.3389/fmars.2023.1191216

Skakala, J., Awty-Carroll, K., Menon, P. P., Wang, K., & Lessin, G. (2023). Future digital twins: emulating a highly complex marine biogeochemical model with machine learning to predict hypoxia. Frontiers in Marine Science, 10, 1058837. https://doi.org/10.3389/fmars.2023.105883

Biermann, L; Clewley, D; Martinez-Vicente, V; Topouzelis, K; 2020. Finding Plastic Patches in Coastal Waters using Optical Satellite Data. Scientific Reports.

Graban, S; Dall’Olmo, G; Goult, S; Sauzède, R; 2020. Accurate deep-learning estimation of chlorophyll-a concentration from the spectral particulate beam-attenuation coefficient. Optics Express.

Campbell, AM; Racault, MF; Goult, S; Laurenson, A; 2020. Cholera Risk: A Machine Learning Approach Applied to Essential Climate Variables. International Journal of Environmental Research and Public Health.

Kerr, T; Clark, JR; Fileman, ES; Widdicombe CE; Pugeault, N; 2020. Collaborative Deep Learning Models to Handle Class Imbalance in FlowCam Plankton Imagery. IEEE Access.

People who work in this area of research

Deep S. Banerjee

Modelling Scientist
dba3/28/2024 9:23:15 AM@pml.ac.uk

Dr James Clark

Marine Ecosystem Modeller
jcl3/28/2024 9:23:15 AM@pml.ac.uk

Dr Dan Clewley

Senior Research Software Engineer
dac3/28/2024 9:23:15 AM@pml.ac.uk

Professor Steve Groom

Head of Science - Earth Observation
sbg3/28/2024 9:23:15 AM@pml.ac.uk

Dr Angus Laurenson

Scientific Python Guru
anla3/28/2024 9:23:15 AM@pml.ac.uk

Dr David Moffat

Artificial Intelligence and Machine Learning Data Scientist
dmof3/28/2024 9:23:15 AM@pml.ac.uk

Professor Matthew Palmer

Head of Science - Digital Innovation & Marine Autonomy
mpa3/28/2024 9:23:15 AM@pml.ac.uk

Silvia Pardo

Earth Observation Scientist
spa3/28/2024 9:23:15 AM@pml.ac.uk

Dr Dale Partridge

Modeller
dapa3/28/2024 9:23:15 AM@pml.ac.uk

Dr Saskia Rühl

Digital Marine Biologist
sru3/28/2024 9:23:15 AM@pml.ac.uk

Dr Jozef Skakala

Ecosystem modeller
jos3/28/2024 9:23:15 AM@pml.ac.uk