Physics-Informed Graph Neural Networks for Water Distribution Systems

1 code implementation • 27 Mar 2024 • Inaam Ashraf, Janine Strotherm, Luca Hermes, Barbara Hammer

In this realm, we propose a novel and efficient machine learning emulator, more precisely, a physics-informed deep learning (DL) model, for hydraulic state estimation in WDS.

Targeted Visualization of the Backbone of Encoder LLMs

1 code implementation • 26 Mar 2024 • Isaac Roberts, Alexander Schulz, Luca Hermes, Barbara Hammer

Attention based Large Language Models (LLMs) are the state-of-the-art in natural language processing (NLP).

Dimensionality Reduction Image Classification

Adversarial Attacks on Leakage Detectors in Water Distribution Networks

1 code implementation • 25 May 2023 • Paul Stahlhofen, André Artelt, Luca Hermes, Barbara Hammer

Many Machine Learning models are vulnerable to adversarial attacks: There exist methodologies that add a small (imperceptible) perturbation to an input such that the model comes up with a wrong prediction.

Metropolitan Segment Traffic Speeds from Massive Floating Car Data in 10 Cities

1 code implementation • 17 Feb 2023 • Moritz Neun, Christian Eichenberger, Yanan Xin, Cheng Fu, Nina Wiedemann, Henry Martin, Martin Tomko, Lukas Ambühl, Luca Hermes, Michael Kopp

Traffic analysis is crucial for urban operations and planning, while the availability of dense urban traffic data beyond loop detectors is still scarce.

Privacy Preserving

Spatial Graph Convolution Neural Networks for Water Distribution Systems

1 code implementation • 17 Nov 2022 • Inaam Ashraf, Luca Hermes, André Artelt, Barbara Hammer

We investigate the task of missing value estimation in graphs as given by water distribution systems (WDS) based on sparse signals as a representative machine learning challenge in the domain of critical infrastructure.

Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes

1 code implementation • 31 Mar 2022 • Christian Eichenberger, Moritz Neun, Henry Martin, Pedro Herruzo, Markus Spanring, Yichao Lu, Sungbin Choi, Vsevolod Konyakhin, Nina Lukashina, Aleksei Shpilman, Nina Wiedemann, Martin Raubal, Bo wang, Hai L. Vu, Reza Mohajerpoor, Chen Cai, Inhi Kim, Luca Hermes, Andrew Melnik, Riza Velioglu, Markus Vieth, Malte Schilling, Alabi Bojesomo, Hasan Al Marzouqi, Panos Liatsis, Jay Santokhi, Dylan Hillier, Yiming Yang, Joned Sarwar, Anna Jordan, Emil Hewage, David Jonietz, Fei Tang, Aleksandra Gruca, Michael Kopp, David Kreil, Sepp Hochreiter

The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future on simply aggregated GPS probe data in time and space bins.

Transfer Learning

A Graph-based U-Net Model for Predicting Traffic in unseen Cities

1 code implementation • 11 Feb 2022 • Luca Hermes, Barbara Hammer, Andrew Melnik, Riza Velioglu, Markus Vieth, Malte Schilling

Accurate traffic prediction is a key ingredient to enable traffic management like rerouting cars to reduce road congestion or regulating traffic via dynamic speed limits to maintain a steady flow.

Management Traffic Prediction

Application of Graph Convolutions in a Lightweight Model for Skeletal Human Motion Forecasting

1 code implementation • 10 Oct 2021 • Luca Hermes, Barbara Hammer, Malte Schilling

Prediction of movements is essential for successful cooperation with intelligent systems.

Motion Forecasting