About Me

Ritesh Moon

I am a PhD researcher at the University of Birmingham working at the intersection of hydrological modelling, machine learning, and environmental data science. My research develops interpretable hybrid modelling frameworks that combine process-based hydrology with machine learning to improve streamflow prediction, reservoir-impacted catchment modelling, and river temperature forecasting.

I am particularly interested in building models that are not only accurate, but also physically meaningful, explainable, and useful for real-world water-resource and climate-adaptation challenges.

Research Vision

My research vision is to better understand and model hydrological systems by examining how process-based models, machine learning methods, and hybrid frameworks represent catchment behaviour under climate variability and human influence. My work focuses not only on improving prediction, but also on identifying which modelling approaches are most suitable for different catchment conditions, hydrological processes, and human-impacted systems. Through this, I aim to develop physically meaningful, interpretable, and robust modelling approaches that can support streamflow prediction, river temperature modelling, and wider water-resource decision-making.

Academic Background

PhD — Hydrological Modelling & Machine Learning

Oct 2023 – Present

University of Birmingham, United Kingdom

MTech — Water Resources & Ocean Engineering

2021

NIT Karnataka, India — First-Class Honours

BTech — Civil Engineering

2017

Sant Gadge Baba Amravati University, India — First-Class Honours

Academic & Research Experience

Doctoral Researcher — University of Birmingham

Oct 2023 – Present

Graduate Engineer — Arcadis Consulting India

Sep 2021 – Jan 2022
  • Built optimised hydraulic models for drainage networks using Micro Drainage, Civil Storm, and Open Roads (Drainage).
  • Coordinated with BIM modellers to ensure CAD QA-compliant drawings.

Awards & Grants

  • LES Travel Grant — £550 (March 2025)
  • University of Birmingham 125th Anniversary Grant — £745 (June 2025)

Workshops & Training

ELLIS Summer School on AI for Earth & Climate Sciences

Jena, Germany

Explored machine learning applications in Earth and climate systems, connecting directly with PhD research on physics-informed ML for streamflow prediction.

HBV Model Training

Cranfield University, 2024

Hydrological Modelling & Data Science Workshop

University of Birmingham, 2023

Teaching Experience

Teaching Support — Hydro-Climatology

University of Birmingham

Supported teaching in hydro-climatology, including explaining atmospheric circulation, pressure systems, wind movement, weather variability, and climate processes to undergraduate students.

Current Research Projects

Project 1 — Signature-Enhanced PIML for Streamflow Prediction

Physics-Informed ML HBV Model CAMELS-GB Hydrological Signatures EGU 2025

Developing physics-informed machine learning models that combine HBV-derived hydrological states with LSTM and catchment signatures to improve streamflow prediction across diverse UK catchments, with a focus on interpretability, robustness, and performance in heterogeneous and human-influenced catchments.

→ View EGU 2025 Abstract

Project 2 — Reservoir-Impacted Catchments & Hybrid Modelling

Reservoir Regulation Hybrid Modelling LSTM GRU Uncertainty Analysis

Investigating how reservoir regulation affects streamflow behaviour and developing hybrid modelling approaches to improve prediction in human-influenced catchments. Research focuses on identifying where process-based models fail and how machine learning can fill those gaps while preserving physical consistency.

Project 3 — River Temperature Hybrid Modelling

River Temperature Deep Learning Climate Adaptation Environment Agency

Developing hybrid models that combine process-based understanding and machine learning to improve river temperature prediction and assess climate-related impacts on freshwater systems. Produced practical recommendations for the Environment Agency on developing a pilot forecasting system to support ecological protection and river management.

Publications & Presentations

Conference Presentations

2025

Bridging Physics and Machine Learning: A Signature-Enhanced Hybrid Framework for Streamflow Prediction in Complex Catchments

Moon, R. — Oral Presentation, European Geosciences Union General Assembly (EGU 2025), Vienna, Austria.

Submitted Manuscripts

2025

Signature-Enhanced Physics-Informed Machine Learning for Streamflow Prediction Across UK Catchments.

Moon, R. et al. — Submitted to Water Resources Research.

Reports & Evidence Synthesis

2026

River Temperature Forecasting: Evidence Synthesis for Operational Applications

Google Scholar

→ View full profile on Google Scholar

Skills

Programming

Python R / RStudio Julia

Hydrological Modelling

HBV Model HEC-RAS Micro Drainage Civil Storm

Machine Learning

LSTM GRU Physics-Informed ML Hybrid Modelling Uncertainty Analysis

Methods & Frameworks

Hydrological Signatures Model Benchmarking Large-Sample Hydrology Catchment Classification

Datasets

CAMELS-GB UK River Flow Records Reservoir-Influenced Catchment Data River Temperature Observations Meteorological Forcing Data Remote-Sensing Products

Geospatial & Computing

QGIS BlueBEAR HPC (UoB) Remote Sensing

Research Interests

  • Hybrid & Physics-Informed Machine Learning
  • Flood Forecasting & Streamflow Prediction
  • River Temperature Modelling
  • Environmental Data Science & Climate Adaptation