Welcome to my site.

I am currently an EPSRC Doctoral Prize Fellow at the University of Bristol. I specialise in machine learning techniques applied to astronomical data, with a focus on improving active learning performance and exploring the utility of weak supervision. My work has enabled me to be involved and consult in the morphology classification pipeline of the recently launched ESA telescope Euclid.

Current Research

I am based in the Data-Intensive Astronomical Analysis research group where I am working on:

  • Improving astronomical classification using Generative Models.
  • Parameter estimation of simulations using SBI.
  • Calibration of simulations within Digital Twins.

PhD Research

My PhD Improving The Practicality of Active Learning Pipelines in Real-World Problem Settings: A Case Study in The Classification of Astronomical Data explored the following topics:

  • Creating novel query strategies to improve accuracy and reduce labelling costs for active learning.
  • Combining the use of weak supervision methods with active learning to improve performance on datasets where labels are scarce, noisy, or difficult to obtain.
  • Using active learning for galaxy morphology classification with noisy image data and unreliable labels.
  • Source classification (star, galaxy, AGN, QSO separation) using Active Learning and Outlier Detection methods.
  • Creating interactive software for researchers to make use of cutting-edge machine learning techniques.

Supervisory Team

Sotiria Fotopoulou , Oliver Ray and Malcolm Bremer

Recent Publications

  • Euclid preparation - XLIII. Measuring detailed galaxy morphologies for Euclid with machine learning
    B. Aussel, S. Kruk, M. Walmsley, M. Huertas-Company, M. Castellano, C.J. Conselice, M. Delli Veneri, H. Domínguez-Sánchez, P.-A. Duc, U. Kuchner, A. La Marca, B. Margalef-Bentabol, F.R. Marleau, G. Stevens, Y. Toba, C. Tortora, L. Wang, Euclid Consortium
    Astronomy & Astrophysics
    PDF DOI
    The Euclid mission is expected to image millions of galaxies at high resolution, providing an extensive dataset with which to study galaxy evolution. Because galaxy morphology is both a fundamental parameter and one that is hard to determine for large samples, we investigate the application of deep learning in predicting the detailed morphologies of galaxies in Euclid using Zoobot, a convolutional neural network pretrained with 450 000 galaxies from the Galaxy Zoo project. We adapted Zoobot for use with emulated Euclid images generated based on Hubble Space Telescope COSMOS images and with labels provided by volunteers in the Galaxy Zoo: Hubble project. We experimented with different numbers of galaxies and various magnitude cuts during the training process. We demonstrate that the trained Zoobot model successfully measures detailed galaxy morphology in emulated Euclid images. It effectively predicts whether a galaxy has features and identifies and characterises various features, such as spiral arms, clumps, bars, discs, and central bulges. When compared to volunteer classifications, Zoobot achieves mean vote fraction deviations of less than 12% and an accuracy of above 91% for the confident volunteer classifications across most morphology types. However, the performance varies depending on the specific morphological class. For the global classes, such as disc or smooth galaxies, the mean deviations are less than 10%, with only 1000 training galaxies necessary to reach this performance. On the other hand, for more detailed structures and complex tasks, such as detecting and counting spiral arms or clumps, the deviations are slightly higher, of namely around 12% with 60 000 galaxies used for training. In order to enhance the performance on complex morphologies, we anticipate that a larger pool of labelled galaxies is needed, which could be obtained using crowd sourcing. We estimate that, with our model, the detailed morphology of approximately 800 million galaxies of the Euclid Wide Survey could be reliably measured and that approximately 230 million of these galaxies would display features. Finally, our findings imply that the model can be effectively adapted to new morphological labels. We demonstrate this adaptability by applying Zoobot to peculiar galaxies. In summary, our trained Zoobot CNN can readily predict morphological catalogues for Euclid images.
    @article{ Aussel2024euclid, author = {{Euclid Collaboration:} and {Aussel, B.} and {Kruk, S.} and {Walmsley, M.} and {Huertas-Company, M.} and {Castellano, M.} and {Conselice, C. J.} and {Veneri, M. Delli} and {Sánchez, H. Domínguez} and {Duc, P.-A.} and {Knapen, J. H.} and {Kuchner, U.} and {La Marca, A.} and {Margalef-Bentabol, B.} and {Marleau, F. R.} and {Stevens, G.} and {Toba, Y.} and {Tortora, C.} and {Wang, L.} and {Aghanim, N.} and {Altieri, B.} and {Amara, A.} and {Andreon, S.} and {Auricchio, N.} and {Baldi, M.} and {Bardelli, S.} and {Bender, R.} and {Bodendorf, C.} and {Bonino, D.} and {Branchini, E.} and {Brescia, M.} and {Brinchmann, J.} and {Camera, S.} and {Capobianco, V.} and {Carbone, C.} and {Carretero, J.} and {Casas, S.} and {Cavuoti, S.} and {Cimatti, A.} and {Congedo, G.} and {Conversi, L.} and {Copin, Y.} and {Courbin, F.} and {Courtois, H. M.} and {Cropper, M.} and {Da Silva, A.} and {Degaudenzi, H.} and {Di Giorgio, A. M.} and {Dinis, J.} and {Dubath, F.} and {Dupac, X.} and {Dusini, S.} and {Farina, M.} and {Farrens, S.} and {Ferriol, S.} and {Fotopoulou, S.} and {Frailis, M.} and {Franceschi, E.} and {Franzetti, P.} and {Fumana, M.} and {Galeotta, S.} and {Garilli, B.} and {Gillis, B.} and {Giocoli, C.} and {Grazian, A.} and {Grupp, F.} and {Haugan, S. V. H.} and {Holmes, W.} and {Hook, I.} and {Hormuth, F.} and {Hornstrup, A.} and {Hudelot, P.} and {Jahnke, K.} and {Keihänen, E.} and {Kermiche, S.} and {Kiessling, A.} and {Kilbinger, M.} and {Kubik, B.} and {Kümmel, M.} and {Kunz, M.} and {Kurki-Suonio, H.} and {Laureijs, R.} and {Ligori, S.} and {Lilje, P. B.} and {Lindholm, V.} and {Lloro, I.} and {Maiorano, E.} and {Mansutti, O.} and {Marggraf, O.} and {Markovic, K.} and {Martinet, N.} and {Marulli, F.} and {Massey, R.} and {Maurogordato, S.} and {Medinaceli, E.} and {Mei, S.} and {Mellier, Y.} and {Meneghetti, M.} and {Merlin, E.} and {Meylan, G.} and {Moresco, M.} and {Moscardini, L.} and {Munari, E.} and {Niemi, S.-M.} and {Padilla, C.} and {Paltani, S.} and {Pasian, F.} and {Pedersen, K.} and {Percival, W. J.} and {Pettorino, V.} and {Pires, S.} and {Polenta, G.} and {Poncet, M.} and {Popa, L. A.} and {Pozzetti, L.} and {Raison, F.} and {Rebolo, R.} and {Renzi, A.} and {Rhodes, J.} and {Riccio, G.} and {Romelli, E.} and {Roncarelli, M.} and {Rossetti, E.} and {Saglia, R.} and {Sapone, D.} and {Sartoris, B.} and {Schirmer, M.} and {Schneider, P.} and {Secroun, A.} and {Seidel, G.} and {Serrano, S.} and {Sirignano, C.} and {Sirri, G.} and {Stanco, L.} and {Starck, J.-L.} and {Tallada-Crespí, P.} and {Taylor, A. N.} and {Teplitz, H. I.} and {Tereno, I.} and {Toledo-Moreo, R.} and {Torradeflot, F.} and {Tutusaus, I.} and {Valentijn, E. A.} and {Valenziano, L.} and {Vassallo, T.} and {Veropalumbo, A.} and {Wang, Y.} and {Weller, J.} and {Zacchei, A.} and {Zamorani, G.} and {Zoubian, J.} and {Zucca, E.} and {Biviano, A.} and {Bolzonella, M.} and {Boucaud, A.} and {Bozzo, E.} and {Burigana, C.} and {Colodro-Conde, C.} and {Di Ferdinando, D.} and {Farinelli, R.} and {Graciá-Carpio, J.} and {Mainetti, G.} and {Marcin, S.} and {Mauri, N.} and {Neissner, C.} and {Nucita, A. A.} and {Sakr, Z.} and {Scottez, V.} and {Tenti, M.} and {Viel, M.} and {Wiesmann, M.} and {Akrami, Y.} and {Allevato, V.} and {Anselmi, S.} and {Baccigalupi, C.} and {Ballardini, M.} and {Borgani, S.} and {Borlaff, A. S.} and {Bretonnière, H.} and {Bruton, S.} and {Cabanac, R.} and {Calabro, A.} and {Cappi, A.} and {Carvalho, C. S.} and {Castignani, G.} and {Castro, T.} and {Cañas-Herrera, G.} and {Chambers, K. C.} and {Coupon, J.} and {Cucciati, O.} and {Davini, S.} and {De Lucia, G.} and {Desprez, G.} and {Di Domizio, S.} and {Dole, H.} and {Díaz-Sánchez, A.} and {Vigo, J. A. Escartin} and {Escoffier, S.} and {Ferrero, I.} and {Finelli, F.} and {Gabarra, L.} and {Ganga, K.} and {García-Bellido, J.} and {Gaztanaga, E.} and {George, K.} and {Giacomini, F.} and {Gozaliasl, G.} and {Gregorio, A.} and {Guinet, D.} and {Hall, A.} and {Hildebrandt, H.} and {Muñoz, A. Jimenez} and {Kajava, J. J. E.} and {Kansal, V.} and {Karagiannis, D.} and {Kirkpatrick, C. C.} and {Legrand, L.} and {Loureiro, A.} and {Macias-Perez, J.} and {Magliocchetti, M.} and {Maoli, R.} and {Martinelli, M.} and {Martins, C. J. A. P.} and {Matthew, S.} and {Maturi, M.} and {Maurin, L.} and {Metcalf, R. B.} and {Migliaccio, M.} and {Monaco, P.} and {Morgante, G.} and {Nadathur, S.} and {Walton, Nicholas A.} and {Peel, A.} and {Pezzotta, A.} and {Popa, V.} and {Porciani, C.} and {Potter, D.} and {Pöntinen, M.} and {Reimberg, P.} and {Rocci, P.-F.} and {Sánchez, A. G.} and {Schneider, A.} and {Sefusatti, E.} and {Sereno, M.} and {Simon, P.} and {Mancini, A. Spurio} and {Stanford, S. A.} and {Steinwagner, J.} and {Testera, G.} and {Tewes, M.} and {Teyssier, R.} and {Toft, S.} and {Tosi, S.} and {Troja, A.} and {Tucci, M.} and {Valieri, C.} and {Valiviita, J.} and {Vergani, D.} and {Zinchenko, I. A.}}, title = {Euclid preparation - XLIII. Measuring detailed galaxy morphologies for Euclid with machine learning}, DOI= "10.1051/0004-6361/202449609", url= "https://doi.org/10.1051/0004-6361/202449609", journal = {A\&A}, year = 2024, volume = 689, pages = "A274", }
  • Time-Series Classification for Dynamic Strategies in Multi-Step Forecasting
    R. Green, G. Stevens, T. de Menezes e Silva Filho, Z. Abdallah
    Arxiv Preprint
    PDF DOI
    Multi-step forecasting (MSF) in time-series, the ability to make predictions multiple time steps into the future, is fundamental to almost all temporal domains. To make such forecasts, one must assume the recursive complexity of the temporal dynamics. Such assumptions are referred to as the forecasting strategy used to train a predictive model. Previous work shows that it is not clear which forecasting strategy is optimal a priori to evaluating on unseen data. Furthermore, current approaches to MSF use a single (fixed) forecasting strategy. In this paper, we characterise the instance-level variance of optimal forecasting strategies and propose Dynamic Strategies (DyStrat) for MSF. We experiment using 10 datasets from different scales, domains, and lengths of multi-step horizons. When using a random-forest-based classifier, DyStrat outperforms the best fixed strategy, which is not knowable a priori, 94% of the time, with an average reduction in mean-squared error of 11%. Our approach typically triples the top-1 accuracy compared to current approaches. Notably, we show DyStrat generalises well for any MSF task.
    @misc{green2024timeseries, title={Time-Series Classification for Dynamic Strategies in Multi-Step Forecasting}, author={Riku Green and Grant Stevens and Telmo de Menezes e Silva Filho and Zahraa Abdallah}, year={2024}, eprint={2402.08373} }
  • Recent Posts

    Recent Talks

    The Hidden Difficulties of Machine Learning

    Presented at Access To Bristol, 2021

    On-campus presentation to 30 local sixth form students who intend to study Engineering at university. This presentation immediately followed the AI & ML:Cutting Through The Hype talk and was used to show how ML tasks are often not as straightforward as they may seem. This talk is very interactive with the aim that the students are able to discover the problems that appear themselves and see why certain solutions may not be sufficient for a problem. Read more

    AI & ML: Cutting Through The Hype

    Presented at Sutton Trust Summer School, 2021

    Webinar presented to 60 sixth form students who intend to study Engineering at university. The presentation starts with an introduction to what Computer Science is (and is not) like at university. Following this, the (very brief) foundations of what Machine Learning and AI really are. Unfortunately, the adoption of these tools has led to a large amount of over-exaggeration and overuse of certain buzzwords throughout the industry, making it seem like companies are doing super complicated and ground-breaking things when most of the time they’re doing nothing more than the Maths the students use in their A-Level studies. I also show the Dot-Com Boom and the AI Winter as examples for how overhyping can be damaging for research progress and the economy. Read more