Saiful Khan
AboutSoftwareProjectsPublications
Senior Scientist · UK Research and Innovation (UKRI)

Saiful Khan

B.E., M.S., D.Phil. (Oxford)

Saiful Khan

I build data-driven software systems that support complex, end-to-end workflows, spanning AI/ML and digital-twin pipelines through to interactive visualisation. By integrating data, models and visualisation into practical software platforms, I help scientists and engineers tackle complex problems and make better-informed decisions. I work at the Rutherford Appleton Laboratory (RAL), part of the Science and Technology Facilities Council (STFC), which is part of UK Research and Innovation (UKRI).

I began my career in industry, developing engineering database software at Oracle and real-time industrial automation systems at ABB. I then moved into academic research at the University of Oxford, where I completed my DPhil and subsequently undertook postdoctoral research with Professor Min Chen. Since then, I have contributed to the design and development of software systems across a diverse range of domains, including enterprise search, seismology, radio astronomy, global health emergencies, nuclear fusion and urban environments. Many of these systems are now in active real-world use.

Research Interests

  • Service Computing
  • Applied AI/ML
  • Semantic Search
  • Data Virtualization
  • Human-centred AI
  • Visual Analytics

Major Awards

  • RAMP Early Career Investigator Award, Royal Society

Professional Service

  • Programme Committee, Services Computing Conference (SCC), 2026
  • Guest Editor, Reliable Scientific Machine Learning for PDE Solution and Discovery, Frontiers in Applied Mathematics and Statistics
Portfolio

Software & Systems

A selection of projects with openly available code.

Meta-StoryBoard (MSB) screenshot

Meta-StoryBoard (MSB)

Meta-StoryBoard is a JavaScript and TypeScript library designed for creating storytelling visualizations using the feature-action design pattern. It is scalable, supports large-scale dynamic time-series data, and can be applied across various domains.

Video source: vis4pandemres.github.io
EPSRC
University of Oxford
STFC

Propagation

Propagation is a novel approach for efficiently propagating visual designs across multiple plots and dashboards, enabling their reuse for new datasets. It was developed during the RAMPVIS project (below).

EPSRC
University of Oxford

Rapid Assistance in Modelling the Pandemic Visualization (RAMPVIS)

A visualization and visual analytics infrastructure developed to support the modelling scientists and epidemiologists of the Scottish COVID Response Consortium (SCRC) during the COVID-19 pandemic.

Received a RAMP Early Career Investigator Award from the Royal Society for my contributions to the RAMP programme.

EPSRC
University of Oxford

Visual Bulletin Analytics System (VBAS)

This project represents a fundamental evolution of data analysis at the International Seismological Centre (ISC) in the UK. The manual paper-based analysis workflow on the left illustrates the inefficient 30-year-old process, where analysts used barcode scanners, rulers, and pencils to manually review diverse seismic data across physical printouts and archived files. This has been replaced by the new VBAS (Visual Bulletin Analytics System), seen on the right. This interactive, unified software integrates all diverse seismological data types into a single interface. On a modern workstation, analysts can now digitally review hypocentres, magnitudes, phase arrivals, seismicity maps, and more. VBAS enables the team to detect patterns, identify anomalies, and perform operational quality assurance far more efficiently and accurately.

Innovate UK
University of Oxford
International Seismological Centre

Visualization Assisted Enterprise Search Engine

Laing O'Rourke, an international engineering and construction company, holds a vast archive of project knowledge whose reuse and monetization depend on searching it quickly and reliably—beyond what standard enterprise search could provide. Developed a proof-of-concept visualization-assisted search engine to address this challenge: a focus+context visualization for rapid observation of false positives and false negatives in search results, a Search Provenance Graph with visual representations of search collaboration, and a special-purpose enterprise search engine with machine learning of ontologies to improve search precision and recall.

My D.Phil. (Ph.D.) project at the University of Oxford was funded by Laing O'Rourke (www.laingorourke.com).

Laing O'Rourke
University of Oxford
Work

Grants & Projects

Funded research programmes and engineering projects I lead and contribute to.

All
Software Engineering · 11
Machine Learning · 6
Visualization · 6
Large Language Model · 2
Grants

2


  1. 1.
    A Long-term VIS-enabled Infrastructure for Supporting ML-assisted Human Decision-making
    Active

    Machine learning (ML) developers often train many models for a task, keep the best one and discard the rest. Yet imperfect models with different strengths can work well together, like people in a team. This EPSRC-funded project uses visualization, which lets people take in the profiles of these models at a glance. It builds tools to catalogue and test large pools of ML models and combine them into effective teams (ensembles). The tools also help decision-makers spot unusual or conflicting predictions. I lead the development of the ensemble models, the overall system and the data virtualization services. These services bring scattered data sources together for large-scale ML. My work also uses large language models (LLMs) to automatically generate metadata for datasets and help AI agents find the right services.

    Role
    Co-PI
    Organisation
    STFC, University of Oxford
    Funding
    EPSRC (£584k)
  2. 2.
    Tokamak Fusion Data Management, Active Learning, and Visualization

    Nuclear fusion experiments generate massive datasets that remain inaccessible to modern data science methods. In collaboration with the UK Atomic Energy Authority (UKAEA), supervised the development of FAIR-MAST for the Mega Ampere Spherical Tokamak (MAST). It makes fusion data FAIR (findable, accessible, interoperable and reusable) and opens it up for visual analytics and AI/ML. It is the first comprehensive data management system of its kind in fusion research. Following this success, built a prototype showing how active learning and visualization can help experts annotate fusion diagnostic data.

    Role
    PI
    Organisation
    STFC
    Funding
    UKAEA (£64k)
Projects

11


  1. 1.
    UrbanAIR: Digital Twin as a Service (DTaaS) for Urban Air Quality
    Active

    Cities need street-level, real-time environmental intelligence to protect public health and plan for climate resilience. Leading the development of the EU-funded UrbanAIR Digital Twin as a Service (DTaaS) platform, delivering real-time, street-level air quality and heat resilience forecasts across three European cities, in collaboration with international partners including VITO (Belgium) and Antwerp City Council.

    Role
    Technical Lead
    Organisation
    STFC
    Funding
    EU
  2. 2.
    DAFNI Data Bridge
    Active

    UK infrastructure research increasingly depends on modelling and analysis at unprecedented scale. The Data & Analytics Facility for National Infrastructure (DAFNI) is a national computing platform that enables researchers to run advanced simulations across transport, water, energy, and city-scale systems. Led the development of a cross-platform data bridge connecting DAFNI and CEDA (Centre for Environmental Data Analysis) services to accelerate environmental modelling and streamline researcher access to national data resources.

    Role
    Technical Lead, User Liaison
    Organisation
    STFC
  3. 3.
    LLM for Semantic Search & Information Retrieval

    Led development of LLM-based semantic search, information retrieval, and automated metadata generation at STFC, including (a) grant proposal search and (b) semantic search, clustering, and topic modelling of scientific data from STFC's DataGateway.

    Role
    Data Scientist
    Organisation
    STFC, UKRI
  4. 4.
    HyperCrop

    Applied machine learning to hyperspectral imaging for crop disease prediction, in collaboration with RAL Space.

    Role
    Researcher
    Organisation
    STFC
  5. 5.
    Rapid Assistance in Modelling the Pandemic Visualization (RAMPVIS)

    During COVID-19, epidemiologists needed to make high-stakes decisions from tens of thousands of rapidly evolving datasets, with no existing infrastructure to visualize or search them at that scale. Initially volunteered as a software architect for the Royal Society's RAMP initiative, where a working system was needed within three months. To meet this deadline, ran an agile process built on continuous, direct stakeholder engagement instead of fixed sprints. Later, funded by EPSRC, led development of RAMPVIS, a visual analytics infrastructure, in collaboration with the UK visualization research community and the Scottish COVID Response Consortium (SCRC). Designed and implemented infrastructure for rapidly deploying visualizations, dashboards, and search capabilities across tens of thousands of heterogeneous, continuously evolving datasets, and developed novel methods for semi-automated visualization generation.

    Role
    Software Architect (Volunteer), Postdoctoral Researcher
    Organisation
    University of Oxford
    Funding
    EPSRC
  6. 6.
    Square Kilometre Array (SKA): Streaming and Visualization

    The SKA is the world's largest radio telescope, generating astronomical data at a volume and rate where real-time streaming and visualization are essential to monitor and act on data as it arrives. Led the design and development of a scalable, real-time streaming and visualization infrastructure to meet this need, with a low-latency data streaming architecture and web-based rendering pipelines for high-volume data streams.

    Role
    Postdoctoral Researcher
    Organisation
    University of Oxford, SKA
    Funding
    STFC
  7. 7.
    Data, Workflow, and Provenance Management

    Horus Security Consultancy's intelligence services depend on large-scale open-source data, but manual workflows could no longer keep pace with the growing volume of online sources. In this Innovate UK-funded university-industry collaboration, led development of a prototype system for scalable, automated open-source intelligence gathering: worked with analysts to capture operational workflows and translate domain requirements into system architecture, and designed and implemented an end-to-end platform for data ingestion, management, search, and provenance, providing analysts with efficient access to information. Later joined Horus as Lead Data Scientist to lead the transition of the prototype from proof-of-concept to commercial software, building and leading a team of software engineers to deliver multiple customer-facing products.

    Role
    Postdoctoral Researcher, Lead Data Scientist
    Organisation
    University of Oxford, Horus
    Funding
    Innovate UK
  8. 8.
    Visual Bulletin Analytics System (VBAS)

    Seismologists at the International Seismological Centre (ISC) previously relied on inefficient, paper-based workflows to review complex seismic events across multiple data types. Developed VBAS—an interactive visualization system that integrates diverse seismological data, including hypocentres, magnitudes, phase arrivals, travel-time curves, seismicity maps, station geometry, and more. VBAS provides a unified interface that helps ISC analysts detect patterns, identify anomalies, and perform data analysis far more efficiently. The system replaced the ISC's 30-year-old paper-based process.

    Role
    Postdoctoral Researcher
    Organisation
    University of Oxford, ISC
    Funding
    Innovate UK
  9. 9.
    Visualization Assisted Enterprise Search Engine

    Laing O'Rourke, an international engineering and construction company, holds a vast archive of project knowledge whose reuse and monetization depend on searching it quickly and reliably—beyond what standard enterprise search could provide. Developed a proof-of-concept visualization-assisted search engine to address this challenge: a focus+context visualization for rapid observation of false positives and false negatives in search results, a Search Provenance Graph with visual representations of search collaboration, and a special-purpose enterprise search engine with machine learning of ontologies to improve search precision and recall.

    Role
    D.Phil. (Ph.D.) Research
    Organisation
    University of Oxford
    Funding
    Laing O'Rourke
  10. 10.
    Oracle Database

    Oracle's database runs mission-critical operations for customers worldwide, where defects or missing features can disrupt business operations—making reliable engineering essential. Developed and debugged Oracle database service features, and independently identified the need for, designed, and built automation tools that improved efficiency and reduced cost across the patch build, test, and delivery pipeline.

    Role
    Software Engineer
    Organisation
    Oracle
  11. 11.
    AC800 Web

    Commercial real-time operating systems (RTOS) added significant licensing cost to industrial automation controllers, motivating ABB's investigation of Linux as a free, real-time-capable alternative for these time-critical embedded systems. Developed Linux system software for ABB's industrial automation controllers and conducted performance benchmarks across various Linux RTOS flavours to assess real-time suitability.

    Role
    Software Engineer
    Organisation
    ABB
Research

Publications

All
Software Engineering
Machine Learning
Visualization
Large Language Model

Preprints

  • 1.

    S. Khan, Y. Xing, J. Chakraborty, A. Farea, P. Beaucamp, S. Jackson, and M. Chen. Automated Keyword Generation Using LLMs in a High-Volume Data Virtualization Service. arXiv:2610.41893, 2026.

  • 2.

    S. Khan and A. Farea. Grounding LLM Agents in Business Processes: Process-Aware Knowledge Graphs for Reliable Multi-Step Service Invocation. arXiv:2610.37242, 2026.

  • 3.

    S. Khan and A. Farea. eIRWR: Enhanced Iterative Random Walk with Restart for Scalable Root Cause Analysis in Microservices. arXiv:2608.08073, 2026.

  • 4.

    Y. Xing, P. Beaucamp, J. Chakraborty, A. Farea, Y. Jin, S. Khan, G. Andrienko, N. Andrienko, and M. Chen. Understanding How Humans Inject Knowledge into Machine Learning Workflows through Visual Analytics. arXiv:2607.00969, 2026.

  • 5.

    P. Beaucamp, A. Abdul-Rahman, R. Borgo, W. Jentner, S. Khan, Y. Xing, D. Ebert, and M. Chen. Optimizing Visual Analytics Workflows: From Theory to Practice. arXiv:2606.24454, 2026.

  • 6.

    Y. Xing, A. Farea, S. Khan, and M. Chen. A Multiplexing Design Space: Theory, Method, and Application. arXiv:2606.12719, 2026.

  • 7.

    A. Farea, S. Khan, R. Daryani, E. C. Ersan, and M. S. Celebi. Learning Fluid-Structure Interaction with Physics-Informed Machine Learning and Immersed Boundary Methods. arXiv:2505.18565, 2025.

2026

  • 8.

    S. Khan, S. Jones, B. Bach, J. Cha, M. Chen, J. Meikle, J. C. Roberts, J. Thiyagalingam, J. Wood, and P. D. Ritsos. Meta-Storyboard Using Feature-Action Patterns: Concept, Techniques, and Case Studies. Computer Graphics Forum, 2026.

  • 9.

    A. Farea, Y. Xing, S. Khan, and M. Chen. Visualization Support for Training PINNs as PDE Solvers. Proc. 1st Engineering CCP Conference, 2026. (Presented at Oxford.)

  • 10.

    Y. Xing, A. Farea, S. Khan, and M. Chen. From Visual Multiplexing to Zebra Maps. IEEE VIS 2026, 2026. (Poster, presented in Paris.)

2025

  • 11.

    S. Khan, J. Chakraborty, P. Beaucamp, N. Bhujel, and M. Chen. Data Virtualization for Machine Learning. Proc. 22nd Int. Conf. on Services Computing (SCC 2025), Hong Kong, pp. 69–84, 2025.

  • 12.

    A. Farea, S. Khan, and M. S. Celebi. QCPINN: Quantum-Classical Physics-Informed Neural Networks for Solving PDEs. Machine Learning: Science and Technology, 6(4):045053, 2025.

  • 13.

    A. Farea, S. Khan, and M. S. Celebi. Multi-Objective Loss Balancing in Physics-Informed Neural Networks for Fluid Flow Applications. Proc. 32nd IEEE Int. Conf. on High Performance Computing, Data, and Analytics (HiPC 2025), Hyderabad, pp. 108–118, 2025.

  • 14.

    S. Jackson, S. Khan, N. Cummings, J. Hodson, S. de Witt, S. Pamela, R. Akers, J. Thiyagalingam, and MAST Team. An Open Data Service for Supporting Research in Machine Learning on Tokamak Data. IEEE Transactions on Plasma Science, 53(9):2440–2449, 2025.

2024

  • 15.

    S. Jackson, S. Khan, N. Cummings, J. Hodson, S. de Witt, S. Pamela, R. Akers, J. Thiyagalingam, and MAST Team. FAIR-MAST: A Fusion Device Data Management System. SoftwareX, 27:101869, 2024.

  • 16.

    S. Jackson, N. Cummings, and S. Khan. Streaming Technologies and Serialization Protocols: Empirical Performance Analysis. IEEE Access, 12:158025–158039, 2024.

2023

  • 17.

    S. Khan, E. Rydow, S. Etemaditajbakhsh, K. Adamek, and W. Armour. Web Performance Evaluation of High Volume Streaming Data Visualization. IEEE Access, 11:15623–15636, 2023.

  • 18.

    B. Bach, E. Freeman, A. Abdul-Rahman, C. Turkay, S. Khan, Y. Fan, and M. Chen. Dashboard Design Patterns. IEEE Transactions on Visualization and Computer Graphics, 29(1):342–352, 2023. (Presented at IEEE VIS 2022, Honorable Mention.)

  • 19.

    P. D. Ritsos, S. Khan, S. Jones, B. Bach, J. Meikle, J. C. Roberts, J. Wood, and M. Chen. Creating Storytelling Visualizations for the COVID-19 Pandemic Using Feature-Action Design Patterns. IEEE VIS Workshop on Visualization for Pandemic and Emergency Responses (Vis4PandEmRes), Melbourne, 2023.

2022

  • 20.

    S. Khan, P. H. Nguyen, A. Abdul-Rahman, E. Freeman, C. Turkay, and M. Chen. Rapid Development of a Data Visualization Service in an Emergency Response. IEEE Transactions on Services Computing, 15(3):1251–1264, 2022.

  • 21.

    S. Khan and D. Wallom. A System for Organizing, Collecting, and Presenting Open-Source Intelligence. Journal of Data, Information and Management, 4(2):107–117, 2022.

  • 22.

    J. Dykes, A. Abdul-Rahman, D. Archambault, B. Bach, R. Borgo, M. Chen, J. Enright, H. Fang, E. E. Firat, E. Freeman, T. Gönen, C. Harris, R. Jianu, N. W. John, S. Khan, A. Lahiff, R. S. Laramee, L. Matthews, S. Mohr, P. H. Nguyen, A. A. M. Rahat, R. Reeve, P. D. Ritsos, J. C. Roberts, A. Slingsby, B. Swallow, T. Torsney-Weir, C. Turkay, R. Turner, F. P. Vidal, Q. Wang, J. Wood, and K. Xu. Visualization for Epidemiological Modelling: Challenges, Solutions, Reflections and Recommendations. Philosophical Transactions of the Royal Society A, 380(2233):20210299, 2022.

  • 23.

    M. Chen, A. Abdul-Rahman, D. Archambault, J. Dykes, P. D. Ritsos, A. Slingsby, T. Torsney-Weir, C. Turkay, B. Bach, R. Borgo, A. Brett, H. Fang, R. Jianu, S. Khan, R. S. Laramee, L. Matthews, P. H. Nguyen, R. Reeve, J. C. Roberts, F. P. Vidal, Q. Wang, J. Wood, and K. Xu. RAMPVIS: Answering the Challenges of Building Visualisation Capabilities for Large-scale Emergency Responses. Epidemics, 39:100569, 2022. (Early version: arXiv:2012.04757, 2020.)

2021

  • 24.

    S. Khan, P. H. Nguyen, A. Abdul-Rahman, B. Bach, M. Chen, E. Freeman, and C. Turkay. Propagating Visual Designs to Numerous Plots and Dashboards. IEEE Transactions on Visualization and Computer Graphics, 28(1):86–95, 2021. (Presented at IEEE VIS 2021.)

2019

  • 25.

    C. Madsen, M. Hurst, S. McLeish, I. Emsley, R. Stacey, M. Garibyan, A. Abdul-Rahman, S. Khan, and M. Chen. Resource Discovery @ the University of Oxford. Technical Report, University of Oxford, 2019.

2016

  • 26.

    S. Khan, U. Kanturska, T. Waters, J. Eaton, R. Bañares-Alcántara, and M. Chen. Ontology-assisted Provenance Visualization for Supporting Enterprise Search of Engineering and Business Files. Advanced Engineering Informatics, 30(2):244–257, 2016.

2015

  • 27.

    S. Khan. Visualization Assisted Enterprise Search Engine. DPhil Thesis, University of Oxford, 2015.

2014

  • 28.

    S. Khan, K. J. Proctor, S. J. Walton, R. Bañares-Alcántara, and M. Chen. A Study on Glyph-based Visualisation with Dense Visual Context. Proc. Computer Graphics & Visual Computing (CGVC 2014), pp. 73–80, 2014.