Estimating the Impact of COVID-19 on Travel Demand in Houston Area Using Deep Learning and Satellite Imagery

Alekhya Pachika; Lu Gao; Lingguang Song; Pan Lu; Xingju Wang

cs.CVMar 29, 2026

Estimating the Impact of COVID-19 on Travel Demand in Houston Area Using Deep Learning and Satellite Imagery

Authors: Alekhya Pachika, Lu Gao, Lingguang Song, Pan Lu, Xingju Wang

Organizations: Civil and Environmental Engineering, University of Houston · Department of Transportation, Logistics and Finance, North Dakota State University · School of Traffic and Transportation, Shijiazhuang Tiedao University

Abstract

Considering recent advances in remote sensing satellite systems and computer vision algorithms, many satellite sensing platforms and sensors have been used to monitor the condition and usage of transportation infrastructure systems. The level of details that can be detected increases significantly with the increase of ground sample distance (GSD), which is around 15 cm - 30 cm for high-resolution satellite images. In this study, we analyzed data acquired from high-resolution satellite imagery to provide insights, predictive signals, and trend for travel demand estimation. More specifically, we estimate the impact of COVID-19 in the metropolitan area of Houston using satellite imagery from Google Earth Engine datasets. We developed a car-counting model through Detectron2 and Faster R-CNN to monitor the presence of cars within different locations (i.e., university, shopping mall, community plaza, restaurant, supermarket) before and during the COVID-19. The results show that the number of cars detected at these selected locations reduced on average 30% in 2020 compared with the previous year 2019. The results also show that satellite imagery provides rich information for travel demand and economic activity estimation. Together with advanced computer vision and deep learning algorithms, it can generate reliable and accurate information for transportation agency decision makers.

Figures & tables

Figure 1: Sixteen COWC images and bounding boxes.

No.	Place	Area (km 2 )
1	Evelyn Rubenstein Jewish Community Center (JCC) of Houston	0.04
2	University of Houston (UH) Parking Lot 16B, 16C, and 16F	0.04
3	Southwest corner of the intersection of Chimney Rock Rd and S Braeswood Blvd	0.02
4	Braeswood Square	0.06
5	South of the intersection of Hillcroft Ave and S Braeswood Blvd	0.07
6	Meyerland Plaza	0.21

Table 1: Data collected from 8 places in Houston.

Figure 2: Locations selected for this case study.

Figure 5: Parking located at Braeswood Square.

Figure 6: Parking located at Hillcroft and S Braeswood.

Figure 7: Parking located at Meyerland Plaza.

Figure 9: Parking located at Katy Mills.

Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models
Sep 1, 2026Ashiq Shukoor Iqbal, Wilson Wongso, Flora D. SalimVision Foundation Models Geospatial Foundation Models
The University of New South Wales, Sydney, NSW, Australia
Interpretable Machine Learning for Traffic Congestion Prediction: Unveiling the Impact of Different COVID-19 Periods
Aug 2, 2026Dan Zhu, Chi Sin Ng, Litian Xie +1Time Series Forecasting Recurrent Neural Networks
Department of Civil and Environmental Engineering, National University of Singapore, Singapore · Department of Industrial Systems Engineering and Management, National University of Singapore, Singapore
Real-Time Traffic Density Estimation: A Hybrid Computer Vision and Predictive Machine Learning Pipeline
Oct 9, 2026Prince Kwabena Appiah BoaduDensity Estimation Traffic Flow Estimation
Department of Computer Engineering, Kwame Nkrumah University of Science and Technology, Kumasi, Ghana

Sep 1, 2026J/K move · Enter open · S save

Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models

Ashiq Shukoor Iqbal, Wilson Wongso, Flora D. Salim

The University of New South Wales, Sydney, NSW, Australia

Vision Foundation Models Geospatial Foundation Models Remote Sensing Benchmarks

Open paper AskPDF arXiv

Satellite foundation models offer a globally available alternative to census data for commuting origin-destination (OD) generation, yet no study has systematically compared encoder paradigms within a single downstream pipeline. We ablate four satellite vision encoders: language-supervised (RemoteCLIP), self-supervised (DINOv3), and geographically grounded (SatCLIP, AlphaEarth) within an identical WeDAN graph diffusion framework across 1,925 US counties, 325 UK districts, and 14 global cities under five random seeds. Three main findings emerge. First, language-supervised features achieve the strongest in-distribution performance (RemoteCLIP CPC 0.602), while geographically grounded encoders transfer more reliably zero-shot: AlphaEarth improves CPC by 33% over RemoteCLIP on UK districts. Second, pretraining corpus scale alone is insufficient: DINOv3, trained on a substantially larger satellite corpus, underperforms RemoteCLIP by 0.091 CPC in-distribution and collapses to CPC 0.022 globally. Third, no encoder transfers usefully to global cities (best CPC 0.122 for RemoteCLIP, 0.022 for DINOv3), confirming cross-continental OD generation remains an open problem. We additionally clarify the semantics of the census noise parameter

η

, whose ordering reverses under cross-continental evaluation, a distinction critical to correctly interpreting prior results. Our code is available at: https://github.com/cruiseresearchgroup/satellites-see-commuters.

Abstract

Explore similar work

Do Satellites See Commuters? A Critical Benchmark of Vision Foundation Models

Interpretable Machine Learning for Traffic Congestion Prediction: Unveiling the Impact of Different COVID-19 Periods

Real-Time Traffic Density Estimation: A Hybrid Computer Vision and Predictive Machine Learning Pipeline