Artificial Intelligence (AI) Lab
The BAS AI Lab is a cross-disciplinary group of scientists and engineers developing AI and machine learning technologies to address polar environmental and sustainability challenges.
Our digital technologies are embedded across the breadth of BAS science, engineering, digital twin and net zero projects including: machine learning sea-ice forecasting; AI based marine fuel/time route planning; wildlife observation from space; machine learning oceanographic modelling; marine autonomous planning for decarbonisation; and satellite based tracking of sea ice and icebergs.
The BAS AI Lab has two overarching objectives:
- To advance understanding and prediction of environmental change
- To decarbonise polar operations, including ships and fleets of autonomous underwater vehicles and drones
PhD opportunities
- Centre for Doctoral Training (CDT) in the Application of Artificial Intelligence to the study of Environmental Risks, University of Cambridge and British Antarctic Survey
IceNet
IceNet is a probabilistic, deep learning sea ice forecasting system developed by an international team and led by British Antarctic Survey and The Alan Turing Institute [Andersson et al., 2021]. …
Autonomous Marine Operations Planning
AI systems will provide automated decision support in polar navigation delivering optimal fuel economy and minimising carbon emissions.
AI for smart conservation
In the AI for smart conservation project BAS are collaborating with the Government of Nunavut and WWF to develop practical tools for conservation decision making. By combining satellite observations, GPS …
DI4EDS
Environmental data science relies on digital infrastructure (hardware, software and methods) to provide services that help researchers answer questions about the environment around us, and innovators to work out ways …
AI tool to revolutionise polar ship navigation
15 November, 2022
Artificial Intelligence (AI) will enable ships navigating in polar ocean conditions to be more efficient using a new route planning tool created by British Antarctic Survey (BAS) researchers. The tool …
Space technology and artificial intelligence to monitor whale mass stranding events
18 November, 2021
An international team of scientists led by British Antarctic Survey have published research today on using new technology to study mass stranding of whales from space and how the technology …
Artificial intelligence to help predict Arctic sea ice loss
26 August, 2021
A new AI (artificial intelligence) tool is set to enable scientists to more accurately forecast Arctic sea ice conditions months into the future. The improved predictions could underpin new early-warning …
Using AI to track whales from space
4 February, 2021
British Antarctic Survey (BAS) scientists will work with an Artificial Intelligence company after being awarded a contract from the Canadian Space Agency (CSA) to support the protection of an endangered …
PhD centre will nurture new leaders in Earth observation
9 January, 2020
A new centre will enable 50 fully-funded PhD researchers to harness satellite data to tackle global environmental challenges. The Centre for Satellite Data in Environmental Science (SENSE) will bring together expertise in …
Using AI to help tackle global environmental challenges
26 February, 2019
A new Centre for Doctoral Training, involving researchers from British Antarctic Survey, will develop Artificial Intelligence (AI) techniques to address critical environmental challenges. Climate change and environmental hazards pose some …
Watching whales from space
1 November, 2018
Scientists have used detailed high-resolution satellite images provided by Maxar Technologies’ DigitalGlobe, to detect, count and describe four different species of whales. Reported this week in the journal Marine Mammal …
Seeing double: Digital twins and net zero
5 July, 2022 by Jonathan Smith
Reaching net zero, as a country or a business, requires new measures, technology and innovations. Digital twins are an example of this; they can be a powerful tool to drive innovation and efficiency.
BLOG: Predicting September 2021 Arctic sea ice using artificial intelligence
24 September, 2021 by Tom Andersson
Tom Andersson, a data scientist at British Antarctic Survey Artificial Intelligence (AI) Lab, shares the latest predictions from a new Arctic sea ice forecasting AI tool as this year’s Arctic …
Innovative Research Sprints Tackle Challenges in Biodiversity and Exposure
11 May, 2021 by Anita Faul
Over the last decade, digital technologies, including Artificial Intelligence, developed rapidly as did our capability to monitor our home planet from space with Earth Observation satellites. How can we most …
Earth Day 2020: A new age of Arctic science discovery – the AI way
24 April, 2020 by Scott Hosking
When we see news reports on climate change on our TV, they are often accompanied by footage of a polar bear walking over the icy Arctic landscape. But the Arctic …
Official launch of the BAS AI Lab!
4 December, 2019 by Risa Ueno
Today we officially launched the BAS AI Lab – thank you everyone for coming!
AI Lab presents at the First Artificial Intelligence for Copernicus Workshop
22 November, 2019 by Anita Faul
Andrew Fleming and Anita Faul present their research at the First Artificial Intelligence for Copernicus Workshop
Machine Learning for Environmental Sciences
21 July, 2019 by Rachel Furner
Rachel Furner is a PhD student at British Antarctic Survey, which has recently opened up its new AI Lab, that aims to foster the application of various machine learning (and …
Data Study Group: Automated monitoring of seals via high-resolution satellite imagery
8 April, 2019 by Premdeep Gill
Prem hosted at Data Study Group at the Alan Turing Institute Seals from space: automated Antarctic ecosystem monitoring via high-resolution satellite imagery Antarctic seal populations are potential indicators for the …
Automated clustering of storm tracks for interpreting ice core records
22 August, 2017 by Scott Hosking
Accumulation in coastal West Antarctic ice core records and the role of cyclone activity Cyclones are an important component of Antarctic climate variability, yet quantifying their impact on the polar …
Finale: Impact of the ORCHESTRA/ENCORE programmes on Southern Ocean heat and carbon understanding
8 May, 2023 by Alexandra Weiss, Andrew Meijers, Dave Munday, Dani Jones, Emma Boland, Povl Abrahamsen, Alexander Brearley, Michael Meredith, Shenjie Zhou
The 5-year Ocean Regulation of Climate by Heat and Carbon Sequestration and Transports (ORCHESTRA) programme and its 1-year extension ENCORE (ENCORE is the National Capability ORCHESTRA Extension) was an approximately…Technical note: Unsupervised classification of ozone profiles in UKESM1
24 March, 2023 by Dani Jones
The vertical distribution of ozone in the atmosphere, which features complex spatial and temporal variability set by a balance of production, loss, and advection, is relevant for both surface air…Read more on Technical note: Unsupervised classification of ozone profiles in UKESM1
Species-specific and seasonal differences in the resistance of salt-marsh vegetation to wave impact
14 December, 2022 by Ben Evans
The coastal protection function provided by the vegetation of tidal wetlands (e.g. salt marshes) will play an important role in defending coastlines against storm surges in the future and depend…A sensitivity analysis of a regression model of ocean temperature
30 August, 2022 by Dave Munday, Dani Jones, Rachel Furner
There has been much recent interest in developing data-driven models for weather and climate predictions. However, there are open questions regarding their generalizability and robustness, highlighting a need to better…Read more on A sensitivity analysis of a regression model of ocean temperature
Tipping cycles
1 August, 2022 by Michael Thorne
Instability in Jacobians is determined by the presence of an eigenvalue lying in the right half plane. The coefficients of the characteristic polynomial contain information related to the specific matrix…Efficient Temporal Piecewise-Linear Numeric Planning with Lazy Consistency Checking
1 August, 2022 by Maria Fox
Temporal planning often involves numeric effects that are directly proportional to their action’s duration. These include continuous effects, where a numeric variable is subjected to a rate of change while…Read more on Efficient Temporal Piecewise-Linear Numeric Planning with Lazy Consistency Checking
Microsporidia: a new taxonomic, evolutionary, and ecological synthesis
1 August, 2022 by Martin Rogers
Microsporidian diversity is vast. There is a renewed drive to understand how microsporidian pathological, genomic, and ecological traits relate to their phylogeny. We comprehensively sample and phylogenetically analyse 125 microsporidian…Read more on Microsporidia: a new taxonomic, evolutionary, and ecological synthesis
Causes of the 2015 North Atlantic cold anomaly in a global state estimate
6 July, 2022 by Dani Jones, Rachael Sanders
The subpolar North Atlantic is an important part of the global ocean and climate system, with SST variability in the region influencing the climate of Europe and North America. While…Read more on Causes of the 2015 North Atlantic cold anomaly in a global state estimate
Localized impacts and economic implications from high temperature disruption days under climate change
20 May, 2022 by Charles Simpson, Erik Mackie, Scott Hosking, Risa Ueno
Most studies into the effects of climate change have headline results in the form of a global change in mean temperature. More useful for businesses and governments, however, are measures…Vegetation interactions with geotechnical properties and erodibility of salt marsh sediments
5 February, 2022 by Ben Evans
Salt marshes provide diverse ecosystem services including coastal protection, habitat provision and carbon sequestration. The loss of salt marshes is a global scale phenomenon, of great socio-economic concern due to…The Time Machine framework: monitoring and prediction of biodiversity loss
1 February, 2022 by Scott Hosking
Transdisciplinary solutions are needed to achieve the sustainability of ecosystem services for future generations. We propose a framework to identify the causes of ecosystem function loss and to forecast the…Read more on The Time Machine framework: monitoring and prediction of biodiversity loss
Ventilation of the Southern Ocean pycnocline
1 January, 2022 by Dani Jones
Ocean ventilation is the transfer of tracers and young water from the surface down into the ocean interior. The tracers that can be transported to depth include anthropogenic heat and…Convolutional conditional neural processes for local climate downscaling
1 January, 2022 by Scott Hosking
A new model is presented for multisite statistical downscaling of temperature and precipitation using convolutional conditional neural processes (convCNPs). ConvCNPs are a recently developed class of models that allow deep-learning…Read more on Convolutional conditional neural processes for local climate downscaling
Regional disparities and seasonal differences in climate risk to rice labour
15 November, 2021 by Charles Simpson, Scott Hosking
The 880 million agricultural workers of the world are especially vulnerable to increasing heat stress due to climate change, affecting the health of individuals and reducing labour productivity. In this…Read more on Regional disparities and seasonal differences in climate risk to rice labour
Defining Southern Ocean fronts using unsupervised classification
2 November, 2021 by Anita Faul, Dani Jones, Erik Mackie
Oceanographic fronts are transitions between thermohaline structures with different characteristics. Such transitions are ubiquitous, and their locations and properties affect how the ocean operates as part of the global climate…Read more on Defining Southern Ocean fronts using unsupervised classification
Untangling local and remote influences in two major petrel habitats in the oligotrophic Southern Ocean
1 November, 2021 by Dani Jones, Eugene Murphy, Richard Phillips
Ocean circulation connects geographically distinct ecosystems across a wide range of spatial and temporal scales via exchanges of physical and biogeochemical properties. Remote oceanographic processes can be especially important for… Seasonal Arctic sea ice forecasting with probabilistic deep learning
26 August, 2021 by Dani Jones, Emily Shuckburgh, James Byrne, Scott Hosking, Jeremy Wilkinson, Tony Phillips, Tom Andersson
Anthropogenic warming has led to an unprecedented year-round reduction in Arctic sea ice extent. This has far-reaching consequences for indigenous and local communities, polar ecosystems, and global climate, motivating the…Read more on Seasonal Arctic sea ice forecasting with probabilistic deep learning
Bridging observations, theory and numerical simulation of the ocean using machine learning
22 July, 2021 by Dani Jones
Progress within physical oceanography has been concurrent with the increasing sophistication of tools available for its study. The incorporation of machine learning (ML) techniques offers exciting possibilities for advancing the…
Matrix scaling and tipping points
16 June, 2021 by Anje-Margriet Neutel, Michael Thorne
To assess which ecosystems are most vulnerable it is necessary to compare the resilience of complex interaction networks in a meaningful way. A fundamental problem for the comparative analysis of…
Inhomogeneity of the surface air temperature record from Halley, Antarctica
1 June, 2021 by Andrew Orr, Gareth Marshall, Hua Lu, Scott Hosking, John King, John Turner, Steve Colwell, Tony Phillips
Commencing in 1956, observations made at Halley Research Station, Antarctica provide one of the longest continuous series of near-surface temperature observations from the Antarctic continent. Since few other records of…Read more on Inhomogeneity of the surface air temperature record from Halley, Antarctica
AI Lab Leadership
- Scott Hosking (Leader)
- Maria Fox (Deputy)
Share this
Featured
Autonomous Marine Operations Planning
