publications

Submitted

InPrep

1. AppliedML

   Probabilistic climate model projections, using Gaussian Processes and Optimal Transport

   Amos*, M.,  and Pinder*, T.

   InPrep

   Code
2. AppliedML

   Street level air quality modelling using graph Gaussian processes: A demonstration for Lancaster, UK

   Young, P. J., Pinder, T., Booker, D.,  Amos, M. and 2 more authors

   InPrep

2023

1. AppliedML

   A continuous vertically resolved ozone dataset from the fusion of chemistry climate models with observations using a Bayesian neural network

   Amos, M., Sengupta, U., Young, P.,  and Hosking, J S

   2023

   Abs HTML PDF Code

   Continuous historic datasets of vertically resolved stratospheric ozone, support the case for ozone recovery, are necessary for the running of offline models and increase understanding of the impacts of ozone on the wider atmospheric system. Vertically resolved ozone datasets are typically constructed from multiple satellite, sonde and ground-based measurements that do not provide continuous coverage. As a result, several methods have been used to infill these gaps, most commonly relying on regression against observed time series. However, these existing methods either provide low accuracy infilling especially over polar regions, unphysical extrapolation, or an incomplete estimation of uncertainty. To address these methodological shortcomings we used and further developed an infilling framework that fuses observations with output from an ensemble of chemistry-climate models within a Bayesian neural network. We used this deep learning framework to produce a continuous record of vertically resolved ozone with uncertainty estimates. Under rigorous testing the infilling framework extrapolated and interpolated skillfully and maintained realistic interannual variability due to the inclusion of physically and chemically realistic models. This framework and the ozone dataset it produced, enables a more thorough investigation of vertically resolved trends throughout the atmosphere.

2022

1. AppliedML

   Identifying latent climate signals using sparse hierarchical Gaussian processes

   Amos*, M., Pinder*, T.,  and Young, P. J.

   Accepted at NeurIPS Workshops Tackling Climate Change with Machine Learning, and Gaussian Processes, Spatiotemporal Modeling, and Decision-making Systems 2022

   HTML PDF Code
2. Data

   LancasterAQ: A High Resolution Street Level Dataset of Ultrafine Particles

   Amos*, M., Booker*, D., Duncan*, R.,  Gouldsborough*, L. and 3 more authors

   2022

   HTML PDF Code
3. AtmosChem

   Update on Global Ozone: Past, Present, and Future, Chapter 3 in WMO Scientific Assessment of Ozone Depletion: 2022, GAW Report No. 278

   Hassler, B., Young, P. J.,  and others,

   2022

   HTML
4. Climate

   The Bristol CMIP6 data hackathon

   Mitchell, D. M., Stone, E. J., Andrews, O. D.,  Bamber, J .L. and 7 more authors

   Weather 2022

   Abs HTML PDF

   The Bristol CMIP6 Data Hackathon formed part of the Met Office Climate Data Challenge Hackathon series during 2021, bringing together around 100 UK early career researchers from a wide range of environmental disciplines. The purpose was to interrogate the under-utilised but currently most advanced climate model inter-comparison project datasets to develop new research ideas, create new networks and outreach opportunities in the lead up to COP26. Experts in different science fields, supported by a core team of scientists and data specialists at Bristol, had the unique opportunity to explore together interdisciplinary environmental topics summarised in this article.

5. Thesis

   Data-science techniques to improve the robustness, accuracy, and utility of chemistry-climate model ensembles

   Amos, M.

   2022

   Abs HTML PDF

   Ensembles of chemistry-climate models (CCMs) are fundamental for the exploration of the chemistry-climate system. A particular focus of chemistry-climate modelling is stratospheric ozone, whose concentrations have been decreased by anthropogenic releases of ozone depleting substances. In conjunction with observational data, CCM ensembles have been relied upon to simulate historic effects of ozone depletion and to project future ozone recovery. However, many widely used ensemble analysis methods are simplistic and are based upon incorrect assumptions about the design of the ensemble. Multi-model means used to construct future ozone projections do not account for variable model performance or similarity and therefore give biased and inaccurate projections. Similarly, simplistic linear regression methods used to infill historic ozone records underestimate interannual variability and are inaccurate in regions of sparse data coverage. Moreover, given advances in machine learning and data science and their increased use in environmental science, it is timely to apply more advanced tools to CCM ensembles. To address this methodological deficit, this thesis presents a set of novel tools to improve the predictions and projections from CCM ensembles of stratospheric ozone. A process-based weighted mean is developed which accounts for model performance and similarity in CCM ensembles. This improvement over pre-existing methods was used to generate accurate ozone hole recovery projections. This thesis also developed a Bayesian neural network (BNN) which fuses together CCMs with observational data to produce accurate and uncertainty-aware predictions. The BNN framework was used to produce historic continuous datasets of total ozone column and vertically resolved ozone, and represents a significant improvement in methods used to ensemble models. Though designed for CCM ensembles these flexible tools have the potential to be applied to other environmental modelling disciplines to improve the accuracy of projections, better understand uncertainty and to make better use of historic observations.

2021

1. Ecology

   Flyway-scale analysis reveals that the timing of migration in wading birds is becoming later

   Mondain-Monval, T., Amos, M., Chapman, J.-L.,  MacColl, A. and 1 more author

   Ecology and Evolution 2021

   Abs HTML PDF

   Understanding the implications of climate change for migratory animals is paramount for establishing how best to conserve them. A large body of evidence suggests that birds are migrating earlier in response to rising temperatures, but many studies focus on single populations of model species. Migratory patterns at large spatial scales may differ from those occurring in single populations, for example because of individuals dispersing outside of study areas. Furthermore, understanding phenological trends across species is vital because we need a holistic understanding of how climate change affects wildlife, especially as rates of temperature change vary globally. The life cycles of migratory wading birds cover vast latitudinal gradients, making them particularly susceptible to climate change and, therefore, ideal model organisms for understanding its effects. Here, we implement a novel application of changepoint detection analysis to investigate changes in the timing of migration in waders at a flyway scale using a thirteen-year citizen science dataset (eBird) and determine the influence of changes in weather conditions on large-scale migratory patterns. In contrast to most previous research, our results suggest that migration is getting later in both spring and autumn. We show that rates of change were faster in spring than autumn in both the Afro-Palearctic and Nearctic flyways, but that weather conditions in autumn, not in spring, predicted temporal changes in the corresponding season. Birds migrated earlier in autumn when temperatures increased rapidly, and later with increasing headwinds. One possible explanation for our results is that migration is becoming later due to northward range shifts, which means that a higher proportion of birds travel greater distances and therefore take longer to reach their destinations. Our findings underline the importance of considering spatial scale when investigating changes in the phenology of migratory bird species.

2020

1. AtmosChem

   Projecting ozone hole recovery using an ensemble of chemistry–climate models weighted by model performance and independence

   Amos, M., Young, P. J., Hosking, J. S.,  Lamarque, J.-F. and 14 more authors

   Atmospheric Chemistry and Physics 2020

   Abs HTML PDF Code

   Calculating a multi-model mean, a commonly used method for ensemble averaging, assumes model independence and equal model skill. Sharing of model components amongst families of models and research centres, conflated by growing ensemble size, means model independence cannot be assumed and is hard to quantify. We present a methodology to produce a weighted-model ensemble projection, accounting for model performance and model independence. Model weights are calculated by comparing model hindcasts to a selection of metrics chosen for their physical relevance to the process or phenomena of interest. This weighting methodology is applied to the Chemistry–Climate Model Initiative (CCMI) ensemble to investigate Antarctic ozone depletion and subsequent recovery. The weighted mean projects an ozone recovery to 1980 levels, by 2056 with a 95 % confidence interval (2052–2060), 4 years earlier than the most recent study. Perfect-model testing and out-of-sample testing validate the results and show a greater projective skill than a standard multi-model mean. Interestingly, the construction of a weighted mean also provides insight into model performance and dependence between the models. This weighting methodology is robust to both model and metric choices and therefore has potential applications throughout the climate and chemistry–climate modelling communities.

2. ML

   Ensembling geophysical models with Bayesian neural networks

   Sengupta*, U., Amos*, M., Hosking, J. S.,  Rasmussen, C. and 2 more authors

   Advances in Neural Information Processing Systems 2020

   Abs HTML PDF Code

   Ensembles of geophysical models improve projection accuracy and express uncertainties. We develop a novel data-driven ensembling strategy for combining geophysical models using Bayesian Neural Networks, which infers spatiotemporally varying model weights and bias while accounting for heteroscedastic uncertainties in the observations. This produces more accurate and uncertainty-aware projections without sacrificing interpretability. Applied to the prediction of total column ozone from an ensemble of 15 chemistry-climate models, we find that the Bayesian neural network ensemble (BayNNE) outperforms existing ensembling methods, achieving a 49.4% reduction in RMSE for temporal extrapolation, and a 67.4% reduction in RMSE for polar data voids, compared to a weighted mean. Uncertainty is also well-characterized, with 90.6% of the data points in our extrapolation validation dataset lying within 2 standard deviations and 98.5% within 3 standard deviations.