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

• URL: http://arxiv.org/abs/2203.17070v2
• Date: Fri, 1 Apr 2022 10:06:33 GMT
• Title: Traffic4cast at NeurIPS 2021 -- Temporal and Spatial Few-Shot Transfer Learning in Gridded Geo-Spatial Processes
• Authors: 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 and Sepp Hochreiter
• Abstract summary: The IARAI Traffic4cast competitions at NeurIPS 2019 and 2020 showed that neural networks can successfully predict future traffic conditions 1 hour into the future. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. The competition now covers ten cities over 2 years, providing data compiled from over 1012 GPS probe data.
• Score: 61.16854022482186
• License: http://creativecommons.org/licenses/by-nc-sa/4.0/
• Abstract: 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. We thus reinterpreted the challenge of forecasting traffic conditions as a movie completion task. U-Nets proved to be the winning architecture, demonstrating an ability to extract relevant features in this complex real-world geo-spatial process. Building on the previous competitions, Traffic4cast 2021 now focuses on the question of model robustness and generalizability across time and space. Moving from one city to an entirely different city, or moving from pre-COVID times to times after COVID hit the world thus introduces a clear domain shift. We thus, for the first time, release data featuring such domain shifts. The competition now covers ten cities over 2 years, providing data compiled from over 10^12 GPS probe data. Winning solutions captured traffic dynamics sufficiently well to even cope with these complex domain shifts. Surprisingly, this seemed to require only the previous 1h traffic dynamic history and static road graph as input.

Related papers

• Rethinking Urban Mobility Prediction: A Super-Multivariate Time Series Forecasting Approach [71.67506068703314]
  Long-term urban mobility predictions play a crucial role in the effective management of urban facilities and services. Traditionally, urban mobility data has been structured as videos, treating longitude and latitude as fundamental pixels. In our research, we introduce a fresh perspective on urban mobility prediction. Instead of oversimplifying urban mobility data as traditional video data, we regard it as a complex time series.
  arXiv  Detail & Related papers  (2023-12-04T07:39:05Z)
• Traffic4cast at NeurIPS 2022 -- Predict Dynamics along Graph Edges from Sparse Node Data: Whole City Traffic and ETA from Stationary Vehicle Detectors [25.857884532427292]
  Traffic4cast is a competition series that advances machine learning for modeling complex spatial systems over time. Our dynamic road graph data combine information from road maps, $1012$ probe data points, and stationary vehicle detectors in three cities over the span of two years. In the core challenge, participants are invited to predict the likelihoods of three congestion classes derived from the speed levels in the GPS data for the entire road graph in three cities 15 min into the future. For the extended challenge, participants are tasked to predict the average travel times on super-segments 15 min into the future.
  arXiv  Detail & Related papers  (2023-03-14T10:03:37Z)
• Multi-task Learning for Sparse Traffic Forecasting [13.359590890052454]
  We propose a multi-task learning network that can simultaneously predict the congestion classes and the speed of each road segment. Our method achieved excellent results on the dataset provided by the Traffic4cast Competition 2022, source code is available at https://github.com/OctopusLi/NeurIPS2022-traffic4cast.
  arXiv  Detail & Related papers  (2022-11-18T02:10:40Z)
• Predicting Future Occupancy Grids in Dynamic Environment with Spatio-Temporal Learning [63.25627328308978]
  We propose a-temporal prediction network pipeline to generate future occupancy predictions. Compared to current SOTA, our approach predicts occupancy for a longer horizon of 3 seconds. We publicly release our grid occupancy dataset based on nulis to support further research.
  arXiv  Detail & Related papers  (2022-05-06T13:45:32Z)
• Solving Traffic4Cast Competition with U-Net and Temporal Domain Adaptation [0.0]
  We present our solution to the Traffic4Cast 2021 Core Challenge. The challenge focuses on the temporal domain shift in traffic due to the COVID-19 pandemic. Our solution has ranked third in the final competition.
  arXiv  Detail & Related papers  (2021-11-05T11:49:52Z)
• Traffic Forecasting on Traffic Moving Snippets [5.614519484892094]
  In the traffic4cast competition, short-term traffic prediction is tackled in unprecedented detail. We propose to predict small quadratic city sections, rather than processing a full-city-raster at once. With the performance on the traffic4cast test data and further experiments on a validation set it is shown that patch-wise prediction indeed improves accuracy.
  arXiv  Detail & Related papers  (2021-10-27T12:36:58Z)
• The 5th AI City Challenge [51.83023045451549]
  The fifth AI City Challenge attracted 305 participating teams across 38 countries. The evaluation was conducted on both algorithmic effectiveness and computational efficiency. Results show the promise of AI in Smarter Transportation.
  arXiv  Detail & Related papers  (2021-04-25T19:15:27Z)
• TLab: Traffic Map Movie Forecasting Based on HR-NET [23.40323690536007]
  In our solution, hand-crafted features are input into the model in a form of channels. In terms of prediction accuracy, our solution has won 2nd place in NeurIPS 2020, Traffic4cast Challenge.
  arXiv  Detail & Related papers  (2020-11-13T18:48:13Z)
• Constructing Geographic and Long-term Temporal Graph for Traffic Forecasting [88.5550074808201]
  We propose Geographic and Long term Temporal Graph Convolutional Recurrent Neural Network (GLT-GCRNN) for traffic forecasting. In this work, we propose a novel framework for traffic forecasting that learns the rich interactions between roads sharing similar geographic or longterm temporal patterns.
  arXiv  Detail & Related papers  (2020-04-23T03:50:46Z)
• Physical-Virtual Collaboration Modeling for Intra-and Inter-Station Metro Ridership Prediction [116.66657468425645]
  We propose a unified Physical-Virtual Collaboration Graph Network (PVCGN), which can effectively learn the complex ridership patterns from the tailor-designed graphs. Specifically, a physical graph is directly built based on the realistic topology of the studied metro system. A similarity graph and a correlation graph are built with virtual topologies under the guidance of the inter-station passenger flow similarity and correlation.
  arXiv  Detail & Related papers  (2020-01-14T16:47:54Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.