Matin Mahmood

Machine Learning × Energy Systems

About

I'm an ML researcher and engineer working at the intersection of machine learning and energy systems. I'm currently based in Berlin at the Merantix AI Campus Hacker Room, building open-source tools for embedding visualization and representation learning.

Previously, I was an ML Scientist at GE Vernova (2022–2025), where I was the sole ML engineer on the Constellation project (£17.8M, UK Power Networks) — developing power flow prediction and anomaly detection models for smart substations. Before that, I was a first engineer at PyPSA meets Earth, contributing to the world's first open-source global energy system model.

I hold a BSc (Hons) in Artificial Intelligence and Mathematics from the University of Edinburgh. My research interests span time-series forecasting for power grids, representation learning, AI safety, and computer vision for energy infrastructure.

News

Publications

Publication list aligned with Google Scholar (117 citations).

PyPSA-Earth. A New Global Open Energy System Optimization Model Demonstrated in Africa

M. Parzen, H. Abdel-Khalek, E. Fedorova, M. Mahmood, M.M. Frysztacki, J. Hampp, L. Franken, et al.

Applied Energy 341, 121096 — 2023

PyPSA meets Africa: Developing an Open Source Electricity Network Model of the African Continent

D. Kirli, J. Hampp, K. van Greevenboek, R. Grant, M. Mahmood, M. Parzen, A. Kiprakis

2021 IEEE AFRICON, 1–6 — 2021

Remote power flow prediction using PMU data and machine learning for enhanced DER resilience in communication loss scenarios

M. Mahmood, V. Jayakrishnan, A. Glatz, Y. Fei, I. Martin, M.A. Khan, R. Davey, et al.

IET Conference Proceedings CP922 2025 (14), 2707–2711 — 2025

Selected Open-Source Projects

HyperView Hyper3Labs · 2025–present · 16★

Open-source embedding visualization toolkit with Euclidean and non-Euclidean views for analyzing learned representations. CLIP-based image embeddings and HuggingFace Spaces deployment. [demo] [code]

earth-osm PyPSA meets Earth · 2022–present · 47★

Python package for global power infrastructure data extraction from OpenStreetMap. Used by the Polish TSO and energy non-profits. Presented at Stanford and Princeton. [PyPI] [code] [talk]

Alignment Graph Apart Research · 2024–present · 18★

Interactive knowledge graph of 5000+ AI alignment papers using LLM-based clustering and graph visualization for literature exploration. [site] [code] [blog]

PyPSA-Earth Open Energy Transition · 2021–2024 · 322★

Core contributor to the first open-source global energy system optimization model, including major performance improvements to network build pipelines. [code] [docs]

detect-energy PyPSA meets Earth · 2022–2023 · 25★

Satellite imagery detection of power infrastructure (transmission towers) using R-CNN and CycleGANs for domain adaptation across landcover types. [code]

Unified web and code search MCP server with weighted provider routing and automatic failover across multiple search backends. [code]

Low-Dimensional GANs BSc Thesis · University of Edinburgh

Undergraduate thesis on GAN training instability in low-dimensional settings. Novel mode collapse mitigation via hyperspherical projection sampling. Supervised by Prof. Desmond Higham. [report] [code]

Experience

AI Researcher & Builder Sep 2025 – present

Merantix AI Campus, Berlin — Hacker Room Residency

ML Scientist Jun 2022 – Sep 2025

GE Vernova — Remote (Edinburgh / London / Berlin)

First Engineer / Core Developer Feb 2021 – Feb 2024

PyPSA meets Earth — Remote (Edinburgh)

Teaching Assistant — Applied Machine Learning Sep 2020 – May 2022

University of Edinburgh, School of Informatics

President — EDIntelligence (AI & Data Science Society) Sep 2019 – Jun 2020

University of Edinburgh

Awards & Community