AidroLab
AI research into resilient and sustainable water management
Urban water systems face growing pressure from climate change and demographics. As a result, water managers count increasingly on digitalization to ensure safe drinking water, adequate sanitation, and effective flood control.
Fast and accurate AI-tools are needed to model the physical processes within water networks and during flooding events. AidroLab believes that the most promising techniques to develop such tools are Graph Neural Networks or GNNs – an extension of deep learning to graph data structures. We are also exploring other AI-applications that can complement our GNN models and provide a thorough AI-based digital twin of (urban) water systems. By bringing together fundamental and applied AI, AidroLab is pushing the boundaries of science, enabling resilient and sustainable urban water systems.
AidroLab is part of the TU Delft AI Labs programme.
The team
Education
Courses
2023-2024
- Machine Learning for Graph Data | CS4350
- Signal Processing | CSE2220
- Modelling, Uncertainty and Data for Engineers | CEGM1000
- Data Science and Artificial Intelligence for Engineers | CEGM2003
2022-2023
- Machine Learning for Graph Data | CS4350
- Signal Processing | CSE2220
- Modelling, Uncertainty and Data for Engineers | CEGM1000
2021-2022
Master Projects
MSc Thesis for CEG (Environmental Engineering)
For more proposals, please check your BrightSpace page and the Google Sheet link of the Dispuut Water & Environment (dispuut-we-citg@tudelft.nl | +31(0)15-2784284 | www.dispuutwaterandenvironment.com) or contact us.
Ongoing
- Optimizing the pump schedule of water distribution systems using a deep learning metamodel (Nikolaos Mertzanis)
- Modelling dike-breach floods in Dutch dike rings (Sergio Bulte)
- Hybrid Modelling in Hydrology Using a Neural Ordinary Differential Equations Approach (Jonathan Schieren)
- Small Deep Learning Models for Sewer Defect Detection (Brendan Determan)
- Improving PIV-based streamflow estimation with Deep Learning (Max Helmich)
- GAN-based rainfall nowcasting (Sven van Os)
Finished
- Assessment of Pump Failures in Rotterdam: A Five-Year Study (2016-2020): A Failure Analysis based on statistical modelling 2024 (Qiwen Zhang)
- Diverse Explorations of Rainfall Nowcasting with TrajGRU: Mitigating Smoothness and Fading Out Challenges for Longer Lead Times 2024 (Yanghuan Zou)
- Towards a fully distributed multivariable hydrological deep learning model with graph neural networks 2024 (Peter Nelemans)
- Characterization of plastic transport in the Saigon River: An analysis of the river stretch that crosses Ho Chi Minh City conducted in the rainy season 2024 (Francesca Lena, Edoarto Forte & Agatha Zamuner)
- Prediction of Discharges from Polders to ‘Boezem’ Canals with a Random Forest and an LSTM Model: Improving Inputs of the Decision Support System of the Hoogheemraadschap van Delfland 2024 (Josine van Marrewijk)
- Deep Learning for Geotechnical Engineering: The Effectiveness of Generative Adversarial Networks in Subsoil Schematization 2023 (Fabian Campos Montero
- A LSTM-based Generative Adversarial Network for End-use Water Modelling 2023 (Yukun Xie)
- Operational Streamflow Drought Forecasting for the Rhine River at Lobith Using the LSTM Deep Learning Approach 2023 (Jing Deng)
- cGANs for multispectral snow extent analysis in the Alps 2023 (Adriaan Keurhorst)
- The Effect of Climate Variability on the Root Zone Storage Capacity 2023 (Nienke Tempel)
- GNNs and Beam Dynamics: Investigation into the application of Graph Neural Networks to predict the dynamic behaviour of lattice beams 2023 (Lex Niessen)
- The impact of an additional phenology model on the performance of conceptual hydrological models 2023 (Casper Pierik)
- Leak Localization in Water Distribution Networks 2023 (Zixi Meng)
- Macrolitter in Groyne Fields: Short term variability & the influence of natural processes 2023 (Jakob Grosfeld)
- Water balance-based approach to improve understanding of Drought Development: by calculating the root storage deficit 2023 (Piet Storm)
- Can fourier neural operators replicate the intrinsic predictability of spatiotemporal chaos?: for the Kuramoto-Sivashinsky system 2023 (Kevin Schuurman)
- Do multi-year droughts increase floods? 2022 (Yang Zhao)
- GGANet: Algorithm Unrolling for Water Distribution Networks Metamodelling 2023 (Albert Solà Roca)
- Transformer-based rainfall-runoff predictions 2023 (Kangmin Mao)
- Perceptual losses in precipitation nowcasting: Exploring limits and potential 2022 (Diewertje Dekker)
- Development of an LSTM-based methodology for burst detection in water distribution systems 2022 (Konstantinos Glynis)
- The role of water vapor observations in satellite-based rainfall information highlighted by a Deep Learning approach 2022 (Fabio Curzi)
- Predicting fluvial flood arrival times by making use of a deep learning model 2022 (Ron Bruijns)
- Using YOLOv5 for the Detection of Icebergs in SAR Imagery 2022 (Daan Hulskemper)
- Parametric design of a grid shell roof over existing buildings, with a focus on connection design 2022 (Fiori Isufi)
- Matching streamflow river gauges with hydrologic models 2021 (Mizzi van der Ven)
- Integrated Neural Network and Finite Element Analysis for constitutive modelling of soil 2021 (Keshav Kashichenula)
- 3D Road Boundary Mapping of MLS Point Clouds 2021 (Qian Bai)
- Shallow Cumulus Clouds as Complex Networks 2021 (Pouriya Alinaghi)
- The variability of the rootzone storage capacity in Austria: An exploration of its controls 2021 (Bart Veenings)
- Relating groundwater heads to stream discharge by using machine learning techniques: A case study in subcatchment Chaamse Beken 2021 (Valerie Demetriades)
- Estimating new reservoir locations with the use of a hydrological model for small holder cotton farmers in Maharashtra, India 2021 (Jente Janssen)
- Assessing Global Applicability of a Long Short-Term Memory (LSTM) Neural Network for Rainfall-Runoff Modelling 2021 (Katharina Wilbrand)
- Short-Term Water Demand Forecasting at District Level Using Deep Learning Methods 2021 (Diego Mauricio Corredor Mora)
- Applying deep learning vs machine learning models to reproduce dry spells at point scale from satellite information in a data-scarce region: the case of northern Ghana, 2021 (Panagiotis Mavritsakis)
- Exploration of Deep Learning-based Computer Vision for the Detection of Floating Plastic Debris in Waterways, 2021 (André J. Vallendar)
- Nowcasting heavy precipitation in the Netherlands: a deep learning approach, 2021 (Eva van der Kooij)
- Creation of new Extra-Tropical Cyclone fields in the North Atlantic with Generative Adversarial Networks, 2020 (Filippo Dainelli)
MSc Thesis for EEMCS (Intelligent Systems)
For more proposals, please check MSc thesis projects.
Ongoing
- Adaptive Learning on graphs (Alex Jeleniewski)
- Graph Learning for Multi-Sensor Radar (Radu Gaghi)
- Graph Neural Networks for Renewable Energy (Rodrigo Revilla Llaca)
Finished
- An Experimental Assessment of the Stability of Graph Contrastive Learning 2024 (Siert Sebus)
- The Hierarchical Subspace Iteration Method for Computing Vibration Modes of Elastic Objects 2024 (Julian van Dijk)
- A System for Model Diagnosis centered around Human Computation 2024 (Ziad Ahmad Saad Soliman Nawar)
- From Clicks to Conscious Choices: Investigating the Effects of Carbon Footprint Data in E-Commerce Recommender Systems 2023 (Sneha Lodha)
- Pure Cold Start Recommendation by Learning on Stochastically Expanded Graphs 2023 (Simon Dahrs)
- Nudging Towards Sustainable Choices via Recommender Systems 2023 (Raoul Kalisvaart)
- Self-Supervised Few Shot Learning: Prototypical Contrastive Learning with Graphs 2023 (Ojas Shirekar)
- Hardware-based implementations in Side-Channel Analysis: A comparison study of DL SCA attacks against HW and SW AES and a novel methodology 2023 (Wolf Bubberman)
- Simplicial Unrolling ElasticNet for Edge Flow Signal Reconstruction 2023 (Chengen Liu)
- Sparse & Interpretable Graph Attention Networks 2023 (Titus Naber)
- Bayesian Contrastive Learning on Topological Structures 2023 (Alex Möllers)
- GGANet: Algorithm Unrolling for Water Distribution Networks Metamodelling 2023 (Albert Solà Roca)
- Deep Statistical Solver for Distribution System State Estimation 2022 (Benjamin Habib)
- Short-term Earthquake Prediction with Deep Neural Networks: Finding the optimal time prior to earthquake strikes to use in predictions 2022 (Glenn van den Belt)
- Improving cell type matching across species in scRNA-seq data using protein embeddings and transfer learning 2022 (Kirti Biharie)
- Accelerating Axial-Symmetrical Nebulae Visualization and Reconstruction 2021 (Nouri Khalass)
- Side-Channel Analysis with Graph Neural Networks, M. Sc. thesis, TU Delft, 2021 (V. de Bruijn)
- Accuracy-Diversity Trade-off in Recommender Systems Via Graph Convolutions, M. Sc. thesis, TU Delft, 2020 (M. Pocchiari)
- Identifying Author Fingerprints in Texts via Graph Neural Networks, M. Sc. thesis, TU Delft, 2020 (T. Sipko)
- Advances in Graph Signal Processing: Fast graph construction & Node-adaptive graph signal reconstruction, M. Sc. thesis, TU Delft, 2020 (M. Yang)
- Graph-Adaptive Activation Functions for Graph Neural Networks, M. Sc. thesis, TU Delft, 2020 (B. Iancu)
- Graph-Time Convolutional Neural Network: Learning from Time-Varying Signals Defined on Graphs, M. Sc. thesis, TU Delft, 2020 (G. Mazzola)
- Automatic Depth Matching for Petrophysical Borehole Logs 2020 (A. Garcia Manso)
- Visually grounded fine-grained speech representations learning 2020 (Tian Tian)
- Applying Machine Learning to Learn System Dynamics Models for Urban Systems 2020 (Rukai Yin)
- Active Semi-Supervised Learning For Diffusions on Graphs 2020 (Biswadeep Das)
- Interpreting Information of Deep Neural Networks for Profiled Side Channel Analysis 2020 (Marius Pop)
- Blind Graph Topology Change Detection: A Graph Signal Processing approach 2020 (Ashvant Mahabir)