top of page
IMG_0146_edited.jpg

Hi my name is Dr Jonathan Smith and I am interested in machine learning and computational applications to real-world problems.

I have just accepted a Machine Learning Data Analyst position starting in January 2022 at the British Antarctic Survey. During this position I will help generate cutting edge data analytics techniques with an application to the Digital Twin of the RRS Sir David Attenborough.

I have just completed postdoctoral researcher position at California Institute of Technology investigating dynamics of earthquakes using cutting edge machine learning techniques. This work entailed computationally efficient research able to detect, associate and locate earthquake signals across 100's of TerraBytes of continuous realtime data. The work completed throughout this position combined a wide variety of machine learning and statistics based techniques, including but not limited to: Physics Informed neural networks, Neural Operators, Stein Variational Gradient Descent, Normalizing Flows, Recurrent Neural Networks, Convolutional Neural Networks, and conventional Deep Neural Networks. In addition, during this position I helped supervise students from the Computer Science and Earth Science for undergraduate, postgraduate and PhD projects.

I received my Doctorate of Philosophy in Geophysics from Hughes Hall, University of Cambridge, investigating 'Geomechanical properties of the Groningen gas reservoir'. This work combined extensive satellite and surface based remote sensing datasets (InSAR, cGPS and Optival Levelling), with regional earthquake catalogues, to better understand the surface and subsurface dynamics of active reservoirs, with the scope of forecasting the hazard of future production scenarios. During this position I also worked on volcanic hazard of central Iceland, providing infield knowledge of seismic network deployment, helping supervise masters student projects, and developing exhibits with demonstration for the 2016 Explosive Earth Royal Society Summer Student Exhibition.

Home: Bio
Home: Image

EMPLOYMENT & EDUCATION

Home: Education

2022 - 2023

MACHINE LEARNING DATA ANALYST


BRITISH ANTARCTIC SURVEY

Generating cutting edge machine learning applications for use with the Digital Twin of the RRS Sir David Attenborough.

2019 - 2021

POSTDOCTORAL RESEARCHER IN SEISMOLOGY


CALIFORNIA INSTITUTE OF TECHNOLOGY

I have just completed Postdoc under the supervision of Prof. Zachary Ross investigating the improvement of earthquake detection and location techniques to better reconcile earthquake dynamics. During this employment we applied and developed cutting edge machine learning techniques, with applications including: Physics Informed neural networks, Neural Operators, Stein Variational Gradient Descent, Normalizing Flows, Recurrent Neural Networks, Convolutional Neural Networks, and conventional Deep Neural Networks.

During my position I worked closely with members of the Caltech computer science department, helping supervisor research projects of undergraduate computer science students.

2015 - 2019

DOCTOR OF PHILOSOPHY IN GEOPHYSICS

UNIVERSITY OF CAMBRIDGE

I completed my PhD on 'Geomechanical properties of the Groningen gas reservoir' under the supervision of Prof Robert S. White and Prof Jean-Philippe Avouac.


This project was funded in collaboration with SHELL Global Solutions and entails a close working relationship with SHELL Netherlands, for the integration of: induced seismicity location analysis, surface subsidence monitoring, and seismic probabilistic forecasting.

This work has involved me in coding development, multithreaded computational modelling, Bayesian statistical modelling, principal component analyses and data storage/manipulation of large datasets (>32TB).

2011 - 2015

MASTER'S DEGREE IN EARTH SCIENCES - 2:I

UNIVERSITY OF OXFORD

Awarded a 2:1 honours degree in Earth Sciences from St Edmund Hall, Oxford.

MACHINE LEARNING PROJECTS

In this section I outline some of my key published machine learning projects that I have author throughout my research positions. All developed code can be found at my linked Github, with interactive Google Colab notebooks given for each project.

Home: Skills
Screenshot 2021-09-13 at 12.27.46.png

EIKONET

Jonathan D. Smith, Kamyar Azizzadenesheli and Zachary E. Ross


Solving the Eikonal equation with Physics Informed Deep Neural Networks

PUBLICATIONS

2021

Hadrien Meyer, Jonathan D. Smith and Jean-Philippe Avouac (in prep), Production optimisation to mitigate Induced Seismicity:  A probabilistic optimisation technique to minimise induced seismicity for reservoir production, Journal Geophysical Research

Thomas Winder, Conor Bacon, Jonathan D. Smith, Thomas S. Hudson, Julian Drew and Robert S. White (in prep), QuakeMigrate: A Modular, Open-Source Python Package for Earthquake Detection and Location, Seismological Research Letters - Electronic Seismologist

Jonathan D. Smith, Elías R. Heimisson, Stephen Bourne and Jean-Philippe Avouac (in review), Stress-based forecasting of induced seismicity with instantaneous earthquake failure functions: Applications to the Groningen Gas Reservoir, Earth and planetary science letters

Elías R. Heimisson, Jonathan D. Smith, Jean-Philippe Avouac and Stephen Bourne (in review), Coulomb Threshold Rate-and-State Model for Fault Reactivation: Application to induced seismicity at Groningen, Geophysical Journal International

Bing Q. Li, Jonathan D. Smith, and Zachary E. Ross (2021), Basal nucleation of ascending swarms in Long Valley Caldera, Science Advances

Jonathan D. Smith, Zachary E. Ross, Kamyar Azizzadenesheli and Jack Muir (2021), HypoSVI: Hypocentral inversion with stein variational inference and physics informed neural networks, Geophysical Journal International, doi:10.1093/gji/ggab309, https://arxiv.org/abs/2101.03271

2020

Jean-Philippe Avouac, Maxime Vrain, Taeho Kim, Jonathan D. Smith, Thomas Ader, Elías R. Heimisson, Zachary Ross, Tero Saarno (2020), A convolution model for earthquake forecasting derived from seismicity recorded during the  ST1 geothermal project  on Otaniemi campus, Finland, Proceedings World Geothermal Congress 2020

Jonathan D. Smith, Kamyar Azizzadenesheli and Zachary E. Ross (2020), EikoNet: Solving the Eikonal equation with Deep Neural Networks, IEEE Transactions on Geoscience and Remote Sensing, arxiv:https://arxiv.org/abs/2004.00361

Zachary E. Ross, Elizabeth S. Cochran, Daniel T. Trugman and Jonathan D. Smith (2020), 3D fault architecture controls the dynamism of earthquake swarms, Science, doi:0.1126/science.abb0779

Jonathan D. Smith, Robert S. White, Jean-Philippe Avouac, and Stephen Bourne (2020), Probabilistic earthquake locations for induced seismicity in the Groningen regionGeophysical Journal International, doi:10.1093/gji/ggaa179

2019

Jonathan D. Smith, Jean-Philippe Avouac, Robert S. White, Alex Copley, Adriano Gualandi and Stephen Bourne (2019), Reconciling reservoir compaction and compressibility in the Groningen region, Journal of Geophysical Research, doi: 10.1029/2018JB016801

Rebecca K. Pearce, Almudena Sánchez de la Muela, Max Moorkamp, James Hammond, Thomas M Mitchell, José Cembrano, Jaime Araya Vargas, Philip G Meredith, Pablo Iturrieta, Nicólas Pérez-Estay, Neill Marshall, Gonzalo Yañez, Ashley Griffith, Carlos Marquardt, \Jonathan D. Smith, Ashley Stanton-Yonge, Rocio Núñez (2019), Interaction between hydrothermal fluids and fault systems in the in the Southern Andes revealed by magnetotelluric and seismic data, Earth and Space Science Open Archive, doi: 10.1002/essoar.10501143.1

Keije Chen, Jonathan D. Smith, Jean-Philippe Avouac, Zhen Liu, Y. Tony Song and Adriano Gualandi (2019), Triggering of the Mw 7.2 Hawaii earthquake of May 4, 2018 by a dike intrusion, Geophysical Research Letters, doi:10.1029/2018GL081428

Thomas S. Hudson, Jonathan D. Smith, Alex M. Brisbourne and Robert S. White (2019), Automated detection of basal icequakes and discrimination from surface crevassing, Annals of Glaciology, doi:10.1017/aog.2019.18

Home: List
Organized Desk

CONTACT

Thank you for visiting my personal website.
If you have any questions or comments, please don't hesitate to get in touch :)

Mobile: +44 (0)7538563804

Thanks for submitting!

Home: Contact
bottom of page