A Hybrid State-Space Approach for Census-Tract Population Estimation

• URL: http://arxiv.org/abs/2608.30094v1
• Date: Sun, 30 Aug 2026 23:43:06 GMT
• Title: A Hybrid State-Space Approach for Census-Tract Population Estimation
• Abstract summary: MambaPop is a method to learn population directly from an administrative unit's own image.<n>It attains a mean absolute error (MAE) of $1141$ persons per tract, matching the strongest convolutional baseline.
• Score: 45.88028371034407
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: Sequence models---the architecture family behind large language models and, increasingly, state-of-the-art image recognition---have redefined how machines learn from high-dimensional data. Yet population estimation from satellite imagery, a task that underpins infrastructure planning, public health, and disaster response, has scarcely benefited: leading systems still bind population to a uniform raster, disaggregating census counts onto grid cells through weighting surfaces built from ancillary data (e.g., in WorldPop and LandScan), which can introduce systematic spatial bias, and predicting population per grid cell with convolutional neural networks. In this approach, the administrative-unit structure in which the census was actually collected is discarded. We close this gap with MambaPop, which renders each administrative unit as a single polygon-masked satellite image and treats tract-level population estimation as a sequence-modeling problem over its image patches, pairing each tract image directly with its population label and eliminating the disaggregation step entirely. Built on the hybrid state-space--attention MambaVision backbone, MambaPop is, to our knowledge, the first method to learn population directly from an administrative unit's own image as well as the first to apply a state-space based (Mamba) hybrid architecture to the population estimation task. Across all $\sim$84{,}000 contiguous-US census tracts of the 2020 census, MambaPop attains a mean absolute error (MAE) of $1{,}141$ persons per tract, matching the strongest convolutional baseline (YOLOv11, MAE $1{,}122$).

Related papers

• Spatial-Mamba: Effective Visual State Space Models via Structure-aware State Fusion [46.82975707531064]
  Selective state space models (SSMs) excel at capturing long-range dependencies in 1D sequential data.<n>We propose Spatial-Mamba, a novel approach that establishes neighborhood connectivity directly in the state space.<n>We show that Spatial-Mamba, even with a single scan, attains or surpasses the state-of-the-art SSM-based models in image classification, detection and segmentation.
  arXiv  Detail & Related papers  (2024-10-19T12:56:58Z)
• Granularity at Scale: Estimating Neighborhood Socioeconomic Indicators from High-Resolution Orthographic Imagery and Hybrid Learning [1.8369448205408005]
  Overhead images can help fill in the gaps where community information is sparse. Recent advancements in machine learning and computer vision have made it possible to quickly extract features from and detect patterns in image data. In this work, we explore how well two approaches, a supervised convolutional neural network and semi-supervised clustering can estimate population density, median household income, and educational attainment.
  arXiv  Detail & Related papers  (2023-09-28T19:30:26Z)
• Mesh-Wise Prediction of Demographic Composition from Satellite Images Using Multi-Head Convolutional Neural Network [0.0]
  This paper proposes a multi-head Convolutional Neural Network model with transfer learning from pre-trained ResNet50 for estimating mesh-wise demographics of Japan. Satellite images from Landsat-8/OLI and Suomi NPP/VIIRS-DNS as inputs and census demographics as labels. The trained model was performed on a testing dataset with a test score of at least 0.8914 in $textR2$ for all the demographic composition groups, and the estimated demographic composition was generated and visualised for 2022 as a non-census year.
  arXiv  Detail & Related papers  (2023-08-25T15:41:05Z)
• Fine-grained Population Mapping from Coarse Census Counts and Open Geodata [19.460864948909936]
  Fine-grained population maps are needed in several domains, like urban planning, environmental monitoring, public health, and humanitarian operations. We present POMELO, a deep learning model that employs coarse census counts and open geodata to estimate fine-grained population maps with 100m ground sampling distance. In a series of experiments for several countries in sub-Saharan Africa, the maps produced with POMELOare in good agreement with the most detailed available reference counts.
  arXiv  Detail & Related papers  (2022-11-08T06:43:52Z)
• ZoomNAS: Searching for Whole-body Human Pose Estimation in the Wild [97.0025378036642]
  We propose a single-network approach, termed ZoomNet, to take into account the hierarchical structure of the full human body. We also propose a neural architecture search framework, termed ZoomNAS, to promote both the accuracy and efficiency of whole-body pose estimation. To train and evaluate ZoomNAS, we introduce the first large-scale 2D human whole-body dataset, namely COCO-WholeBody V1.0.
  arXiv  Detail & Related papers  (2022-08-23T16:33:57Z)
• So2Sat POP -- A Curated Benchmark Data Set for Population Estimation from Space on a Continental Scale [11.38584315242023]
  We provide a comprehensive data set for population estimation in 98 European cities. The data set comprises a digital elevation model, local climate zone, land use proportions, nighttime lights in combination with multi-spectral Sentinel-2 imagery, and data from the Open Street Map initiative.
  arXiv  Detail & Related papers  (2022-04-07T07:30:43Z)
• BEV-Net: Assessing Social Distancing Compliance by Joint People Localization and Geometric Reasoning [77.08836528980248]
  Social distancing, an essential public health measure, has gained significant attention since the outbreak of the COVID-19 pandemic. In this work, the problem of visual social distancing compliance assessment in busy public areas with wide field-of-view cameras is considered. A dataset of crowd scenes with people annotations under a bird's eye view (BEV) and ground truth for metric distances is introduced. A multi-branch network, BEV-Net, is proposed to localize individuals in world coordinates and identify high-risk regions where social distancing is violated.
  arXiv  Detail & Related papers  (2021-10-10T23:56:37Z)
• Census-Independent Population Estimation using Representation Learning [0.5735035463793007]
  Census-independent population estimation approaches using alternative data sources have shown promise in providing frequent and reliable population estimates locally. We explore recent representation learning approaches, and assess the transferability of representations to population estimation in Mozambique. Using representation learning reduces required human supervision, since features are extracted automatically. We compare the resulting population estimates to existing population products from GRID3, Facebook (HRSL) and WorldPop.
  arXiv  Detail & Related papers  (2021-10-06T15:13:36Z)
• Sensing population distribution from satellite imagery via deep learning: model selection, neighboring effect, and systematic biases [16.82118960055405]
  This study marks the first attempt to cross-compare performances of popular state-of-the-art deep learning models in estimating population distribution from remote sensing images. DenseNet outperforms the other three models, while VGG has the worst performances in all evaluating metrics under all selected neighboring scenarios. There exists a notable, universal bias that all selected deep learning models tend to overestimate sparsely populated image patches and underestimate densely populated image patches, regardless of neighboring sizes.
  arXiv  Detail & Related papers  (2021-03-03T03:40:24Z)
• Completely Self-Supervised Crowd Counting via Distribution Matching [92.09218454377395]
  We propose a complete self-supervision approach to training models for dense crowd counting. The only input required to train, apart from a large set of unlabeled crowd images, is the approximate upper limit of the crowd count. Our method dwells on the idea that natural crowds follow a power law distribution, which could be leveraged to yield error signals for backpropagation.
  arXiv  Detail & Related papers  (2020-09-14T13:20:12Z)
• Magnify Your Population: Statistical Downscaling to Augment the Spatial Resolution of Socioeconomic Census Data [48.7576911714538]
  We present a new statistical downscaling approach to derive fine-scale estimates of key socioeconomic attributes. For each selected socioeconomic variable, a Random Forest model is trained on the source Census units and then used to generate fine-scale gridded predictions. As a case study, we apply this method to Census data in the United States, downscaling the selected socioeconomic variables available at the block group level, to a grid of 300 spatial resolution.
  arXiv  Detail & Related papers  (2020-06-23T16:52:18Z)

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.