mlsanityData to 7 Oct 2026

Deep hybrid model with satellite imagery: how to combine demand modeling and computer vision for behavior analysis?

arXiv 2303.04204 ↗First posted 7 Mar 2023cs.LG cs.CV econ.GNcited by 8

Not on the map. Why?

Abstract (arXiv)

Classical demand modeling analyzes travel behavior using only low-dimensional numeric data (i.e. sociodemographics and travel attributes) but not high-dimensional urban imagery. However, travel behavior depends on the factors represented by both numeric data and urban imagery, thus necessitating a synergetic framework to combine them. This study creates a theoretical framework of deep hybrid models with a crossing structure consisting of a mixing operator and a behavioral predictor, thus integrating the numeric and imagery data into a latent space. Empirically, this framework is applied to analyze travel mode choice using the MyDailyTravel Survey from Chicago as the numeric inputs and the satellite images as the imagery inputs. We found that deep hybrid models outperform both the traditional demand models and the recent deep learning in predicting the aggregate and disaggregate travel behavior with our supervision-as-mixing design. The latent space in deep hybrid models can be interpreted, because it reveals meaningful spatial and social patterns. The deep hybrid models can also generate new urban images that do not exist in reality and interpret them with economic theory, such as computing substitution patterns and social welfare changes. Overall, the deep hybrid models demonstrate the complementarity between the low-dimensional numeric and high-dimensional imagery data and between the traditional demand modeling and recent deep learning. It generalizes the latent classes and variables in classical hybrid demand models to a latent space, and leverages the computational power of deep learning for imagery while retaining the economic interpretability on the microeconomics foundation.

Key facts. Cited by 8 papers in the map (data through 7 Oct 2026). Builds on 33 of its 96 references that are in the map. First posted on arXiv 7 Mar 2023.

Builds on

33 of 96 references.

References · 33

  1. 2015Deep Residual Learning for Image Recognitioncited by 51,809
  2. 2021High-Resolution Image Synthesis with Latent Diffusion Modelscited by 18,694
  3. 2018The Unreasonable Effectiveness of Deep Features as a Perceptual Metriccited by 11,029
  4. 2016Grad-CAM: Visual Explanations from Deep Networks via Gradient-based Localizationcited by 6,690
  5. 2020Taming Transformers for High-Resolution Image Synthesiscited by 3,229
  6. 2016Aggregated Residual Transformations for Deep Neural Networkscited by 2,540
  7. 2014Striving for Simplicity: The All Convolutional Netcited by 983
  8. 2015Autoencoding beyond pixels using a learned similarity metriccited by 407
  9. 2016Adversarial Feature Learningcited by 350
  10. 2017A Neural Representation of Sketch Drawingscited by 311
  11. 2016Adversarially Learned Inferencecited by 216
  12. 2015The Benefit of Multitask Representation Learningcited by 194
21 more
  1. 2020Human Trajectory Forecasting in Crowds: A Deep Learning Perspectivecited by 128
  2. 2020Inductive Graph Neural Networks for Spatiotemporal Krigingcited by 90
  3. 2018Understanding and Improving Interpolation in Autoencoders via an Adversarial Regularizercited by 87
  4. 2017Using Deep Learning and Google Street View to Estimate the Demographic Makeup of the UScited by 66
  5. 2016Deep Learning the City : Quantifying Urban Perception At A Global Scalecited by 65
  6. 2019Multi-level Convolutional Autoencoder Networks for Parametric Prediction of Spatio-temporal Dynamicscited by 45
  7. 2022Uncertainty Quantification of Sparse Travel Demand Prediction with Spatial-Temporal Graph Neural Networkscited by 29
  8. 2020Generating Interpretable Poverty Maps using Object Detection in Satellite Imagescited by 27
  9. 2021Spatial Aggregation and Temporal Convolution Networks for Real-time Krigingcited by 27
  10. 2021Choice modelling in the age of machine learning -- discussion papercited by 26
  11. 2017Using convolutional networks and satellite imagery to identify patterns in urban environments at a large scalecited by 23
  12. 2020Theory-based residual neural networks: A synergy of discrete choice models and deep neural networkscited by 15
  13. 2019Adversarially Approximated Autoencoder for Image Generation and Manipulationcited by 12
  14. 2021Equality of opportunity in travel behavior prediction with deep neural networks and discrete choice modelscited by 10
  15. 2017Autoencoder Regularized Network For Driving Style Representation Learningcited by 9
  16. 2021Combining Discrete Choice Models and Neural Networks through Embeddings: Formulation, Interpretability and Performancecited by 9
  17. 2019Ensemble Convolutional Neural Networks for Mode Inference in Smartphone Travel Surveycited by 6
  18. 2019Semi-supervised GANs to Infer Travel Modes in GPS Trajectoriescited by 3
  19. 2021A variational autoencoder approach for choice set generation and implicit perception of alternatives in choice modelingcited by 2
  20. 2018Modelling Latent Travel Behaviour Characteristics with Generative Machine Learningcited by 1
  21. 2021Data Fusion for Deep Learning on Transport Mode Detection: A Case Studycited by 1

Built on by

Cited by year

Citing papers per year: 2023: 1; 2024: 3; 2025: 4.

8 papers.

  1. 2025Aligning LLM with human travel choices: a persona-based embedding learning approachcited by 7
  2. 2024Vision Technologies with Applications in Traffic Surveillance Systems: A Holistic Surveycited by 4
  3. 2025Mitigating Spatial Disparity in Urban Prediction Using Residual-Aware Spatiotemporal Graph Neural Networks: A Chicago Case Studycited by 2
  4. 2023Images in Discrete Choice Modeling: Addressing Data Isomorphism in Multi-Modality Inputscited by 1
  5. 2025Demographics-Informed Neural Network for Multi-Modal Spatiotemporal forecasting of Urban Growth and Travel Patterns Using Satellite Imagerycited by 1
  6. 2024Advancing Transportation Mode Share Analysis with Built Environment: Deep Hybrid Models with Urban Road Networkcited by 0
  7. 2024A Unified Framework for Next-Gen Urban Forecasting via LLM-driven Dependency Retrieval and GeoTransformercited by 0
  8. 2025Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimationcited by 0