Adithya Ramachandran

Adithya Ramachandran, M. Sc.

Researcher

Department of Computer Science
Chair of Computer Science 5 (Pattern Recognition)

Room: Room 10.138
Martensstr. 3
91058 Erlangen

Office hours

Each week Fr, 09:00 - 17:00, Room 10.138,

My research focuses on modeling a digital twin and developing methods for water and district heating utility networks to enable ML, and DL solutions that aid in decarbonization. We take a synergistic approach to model consumer, and network behavior through the underlying time-series data and Geographic Information System (GIS) data. With an end-to-end data pipeline and state-of-the-art ML and DL techniques this research intends to place itself as a framework that facilitates efficient water and district heating networks. Key aspects of the utility pipe includes

  • Utility data processing
    • GIS data
    • Smart meter data
    • SCADA data
    • Cadastre maps
  • Machine Learning and Deep Learning
    • Forecasting
    • Anomaly detection
    • Event detection
    • Network optimization
    • Demand clustering
    • Document digitization
    • Establishing graph database
    • LLM agents

 

Student Supervision

Students looking for a thesis or project are requested to apply via e-mail with their CV, grades, and relevant projects/git. For an industrial thesis, enclose a detailed research proposal.

Academic CV

  • Since 10/2021:
    Ph.D. Student at the Pattern Recognition Lab, Diehl Metering GmbH
  • 10/2017 – 9/2021:
    M.Sc. in Computational Engineering
    Friedrich-Alexander University Erlangen-Nürnberg

Projects

Term: September 1, 2021 – June 30, 2025

Description: In the UtilityTwin research project, we focus on developing an intelligent digital twin for any energy or water supply network based on adaptive high-resolution sensor data (down to the sub-second range), GIS data, and machine learning techniques. We combine the concepts of BigData and AI in an innovative way in this research project to make positive contributions to the implementation of the energy transition and to counteract climate change.

2021

  • UtilityTwin

    (Third Party Funds Group – Overall project)

    Term: September 1, 2021 - August 31, 2024
    Funding source: Bayerisches Staatsministerium für Wirtschaft, Landesentwicklung und Energie (StMWi) (seit 2018)
    Abstract

    In the UtilityTwin research project, an intelligent digital twin for any energy or water supply network is to be researched and developed on the basis of adaptive high-resolution sensor data (down to the sub-second range) and machine learning techniques. Overall, the technology concepts BigData and AI are to be combined in an innovative way in this research project in order to make positive contributions to the implementation of the energy transition and to counteract climate change.

Publications

Accepted:
  • , , , Digitization Framework of Water Utility Documents for Digital Twins. In: 21st International Computing & Control in the Water Industry Conference, 2025
  • , , , , Link Prediction on Water Distribution Networks using Graph Neural Networks. In: 21st International Computing & Control in the Water Industry Conference, 2025

2025

Conference Contributions

2024

Journal Articles

Conference Contributions

2022

Conference Contributions

Research Groups

Thesis

Type Title Status
MA thesis Link Prediction on Utility Networks Using Graph Neural Networks running
MA thesis Deep Learning for Geo-Referencing Historical Utility Documents With Geographical Features finished
MA thesis Real-time Path Loss Prediction Using Deep Learning for Smart Meter Communication System finished
Project TSI Challenge Summer 2024: Heat & Water Demand Forecasting finished
MA thesis Explainable Predictive Maintenance: Forecasting and Anomaly Detection of Diagnostic Trouble Codes for Truck Fleet Management finished
MA thesis Leakage Detection and Modeling in Water Distribution Systems finished
MA thesis Adaptive Training for Heat Demand Prediction of District Heating Network finished
MA thesis Heat Demand Forecasting with Multi-Resolutional Representation of Heterogeneous Temporal Ensemble finished
MA thesis A hybrid approach forLeakage Localization in the Water Distribution Network finished
MA thesis Adaptive Training of Heat Demand Prediction using Continual Learning finished
Project Represent senor data of district heating network using contrastive learning finished
MA thesis Heat Demand Forecasting with Multi-Resolutional Representation of Heterogeneous Temporal Ensemble finished