analiza aiqbench
Puffin introduces a probabilistic framework that leverages satellite imagery embeddings to disaggregate coarse socioeconomic data into high-resolution estimates while maintaining aggregate consistency. By modeling uncertainty distributions rather than single point predictions, the method addresses critical gaps in urban planning and public health where fine-grained census data is unavailable. This work advances machine learning applications for statistical inference in spatial domains without relying on expensive fine-resolution training labels.
Puffin: Probabilistic Learning of Spatial Detail From Coarse Observations
arXiv:2610.11914v1 Announce Type: new Abstract: High-resolution socioeconomic variables are important for applications such as urban planning, public health, disaster response, and resource allocation. In practice, however, these variables are often observed only at a coarse spatial resolution. We introduce Puffin, a probabilistic framework for statistical disaggregation that raises the resolution of coarse totals using high-resolution satellite embeddings as covariates. Instead of predicting a single value for each fine-resolution subregion, Puffin learns a probability distribution and is trained through an aggregation-aware likelihood. At inference, Puffin conditions these predictions on the observed regional total and splits it among the subregions. The resulting fine-scale estimates are consistent with the observed aggregate and come with calibrated uncertainty, without requiring fine-resolution labels for training. We evaluate Puffin on German and US census, employment, and election data across population, jobs, and other count variables, and study when statistical disaggregation succeeds or fails across regions, countries, and targets.
Abstract:High-resolution socioeconomic variables are important for applications such as urban planning, public health, disaster response, and resource allocation. In practice, however, these variables are often observed only at a coarse spatial resolution. We introduce Puffin, a probabilistic framework for statistical disaggregation that raises the resolution of coarse totals using high-resolution satellite embeddings as covariates. Instead of predicting a single value for each fine-resolution subregion, Puffin learns a probability distribution and is trained through an aggregation-aware likelihood. At inference, Puffin conditions these predictions on the observed regional total and splits it among the subregions. The resulting fine-scale estimates are consistent with the observed aggregate and come with calibrated uncertainty, without requiring fine-resolution labels for training. We evaluate Puffin on German and US census, employment, and election data across population, jobs, and other count variables, and study when statistical disaggregation succeeds or fails across regions, countries, and targets.
Machine Learning (cs.LG)
arXiv:2610.11914 [cs.LG]
(or arXiv:2610.11914v1 [cs.LG] for this version)
https://doi.org/10.48550/arXiv.2610.11914 Focus to learn more arXiv-issued DOI via DataCite (pending registration)
arXivLabs is a framework that allows collaborators to develop and share new arXiv features directly on our website.
Both individuals and organizations that work with arXivLabs have embraced and accepted our values of openness, community, excellence, and user data privacy. arXiv is committed to these values and only works with partners that adhere to them.
Have an idea for a project that will add value for arXiv's community? Learn more about arXivLabs.
Text integral sub licența deschisă a publicației · 240 cuvinte
Subiecte conexe
The Entangled Dimensions of Decision Theory
LessWrong · 30 iul. 2026
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland
arXiv · 9 iun. 2026
FACET: Factorized Asymmetric Conditioning for Efficient Transport in High-Fidelity Fluorescence Microscopy Synthesis
arXiv · 6 oct. 2026
Exponential Reduction of Mesh Dependence in Quantum Estimation of Parabolic PDE Observables
arXiv · 21 iul. 2026