Skip to main content
Profile

Sandhya Patidar

Associate Professor

Research Institute
Institute for Infrastructure and Environment
Accepting PhD Students
Yes
Research profile
Sandhya Patidar

Research
Research
Research

Research interests

My research focuses on the interdisciplinary applications of data science, integrating mathematical, statistical, and machine learning methods, to tackle complex real-world challenges in energy systems, water resources, climate change, extreme events, flood risk, and environmental impact assessment.

My work contributed to advancing intelligent systems through the integration of physics-informed AI models, hybrid statistical–machine learning frameworks, federated and edge learning, multi-objective safety-aware optimisation, and rigorous risk and uncertainty quantification. Rather than relying on black-box approaches, I develop interpretable, safety-aware, distributed AI architectures that could be embedded within operational digital twins. These platforms are designed with modular AI pipelines, seamless edge-to-cloud integration, privacy-preserving federated learning mechanisms, and standardised interoperability interfaces, enabling scalable, trustworthy, and real-world deployable AI solutions for complex systems such as energy, water, climate and infrastructure.

Over the years, I have built a strong research track record by leading and contributing to multidisciplinary projects that apply advanced Mathematical, Statistical, and AI techniques, including Hidden Markov Modelling, Stochastic Processes, Time Series Modelling, Uncertainty and Data Analysis, Complex Networks, Non-linear Dynamical Systems, Bifurcation Analysis, Chaos Theory, and Machine/Deep Learning (Ref: Keywords).

I have been involved (as Principal Investigator, Co-Investigator, and postdoctoral researcher) in several high-profile UKRI and EU-funded projects, such as EPSRC EP/F038240/1, EP/I03534X/1, EP/K013513/1, EP/L000180/1, EP/N030419/1, and Horizon Europe projects FEDECOM (101075660) and InterPED (101138047).

In addition, I have extensive experience in big data analytics and scientific programming (Python, R, MATLAB, C, C++, FORTRAN), supporting robust computational modelling and data-driven analysis. My work has resulted in over 100 peer-reviewed interdisciplinary publications and contributions.

My research excellence has been recognised through multiple awards, including Best Paper Awards at the World Renewable Energy Congress (WREC 2011), Best Presentation Awards (including the prestigious Sir David Wallace Prize, Loughborough University), the CESI Conference Award (Newcastle University), and the Alfred Carr Award from the Institution of Civil Engineers (ICE).

Keywords: Artificial Intelligence (AI), Physics-Informed AI, Hybrid AI–Statistical Modelling, Explainable AI (XAI), Trustworthy AI, Human-Centred AI, Distributed Intelligence, Edge AI, Federated Learning, AI for Safety-Critical Systems, Multi-Agent Systems, Adaptive Autonomous Systems, AI-Driven, Optimisation, Data-Driven Decision Support, AI for Engineering/Industrial Systems, AI-Enabled Digital Transformation, IoT-enabled distributed sensing, Spatio-temporal Analysis, etc.