# US 2026/0087654 A1 · System and method for predicting census data using satellite images

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0087654 A1
- Document ID: US20260087654A1
- Status: Published application
- Kind: A1
- Application number: 18/897,114
- Filed: 2024-09-26
- Published: 2026-03-26
- Earliest claimed: 2024-09-26
- Assignees: College of William and Mary
- Applicants: College of William & Mary
- Inventors: Daniel Miller Runfola; Heather Baier; Anthony Stefanidis
- Web page: https://patentgrep.com/patent/US20260087654A1

## CPC

- G06T 7/33: using feature-based methods
- G06T 7/62: of area, perimeter, diameter or volume
- G06V 10/82: using neural networks
- G06V 20/13: Satellite images
- G06T 2207/10032: Satellite or aerial image; Remote sensing
- G06T 2207/20084: Artificial neural networks [ANN]
- G06T: IMAGE DATA PROCESSING OR GENERATION, IN GENERAL
- G06V: IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING

## Abstract

A satellite image of a geographic region is cropped. Each pixel of the cropped satellite image is brightened. A first portion of the brightened satellite image is sampled and has a centroid defined by a geographic location. A second portion of the brightened satellite image centered on the centroid is generated. The first and second portions have different resolutions. The first and second portions are processed to generate respective first and second outputs where each output is indicative of features therein. The first and second outputs are processed to generate an estimated census metric associated with the centroid. The estimated census metric is compared with a corresponding metric from collected census data to generate a difference therebetween. The location of the centroid is moved to a revised location and the process is repeated until the difference is less than a prescribed threshold.

## Claims

### Claim 1

A method, comprising:
by an interactive neural network inclusive of a first network trained with ImageNet, a second network comprising a recurrent neural network, and a third network trained with census data collected for a geographic region,
a) obtaining a satellite image of the geographic region;
b) cropping, by a processor coupled to the interactive neural network, the satellite image to define a cropped satellite image inclusive of a selected region of the geographic region wherein each pixel of the cropped satellite image has a brightness value;
c) increasing, by the processor, the brightness value for each pixel in the cropped satellite image to generate a brightened satellite image;
d) sampling, by the processor, a first portion of the brightened satellite image wherein the first portion has a centroid defined by a location in the selected region;
e) generating, by the processor, a second portion of the brightened satellite image centered on the centroid wherein the first portion and the second portion have different resolutions;
f) processing, by the first network, the first portion to generate a first output indicative of features in the first portion and the second portion to generate a second output indicative of features in the second portion;
g) processing, by the second network and the third network, the first output and the second output to generate an estimated census metric associated with the centroid;
h) comparing, by the second network, the estimated census metric with a corresponding metric from the census data to generate a difference there between; and
i) moving, by the second network, the location of the centroid to a revised location in the selected region and repeating steps d) through h) until the difference is less than a prescribed threshold.

### Claim 2 (depends on 1)

The method of claim 1, wherein the geographic region has a governing body associated therewith, and wherein the census data is collected by the governing body.

### Claim 3 (depends on 1)

The method of claim 1, wherein the selected region is selected from the group consisting of at least one of a state, a province, a city, a county, and a municipality.

### Claim 4 (depends on 1)

The method of claim 1, wherein the brightness value for each pixel is increased by a factor of at least 2.

### Claim 5 (depends on 1)

The method of claim 1, wherein the second portion is in a range of 50% to 80% smaller than the first portion.

### Claim 6 (depends on 1)

The method of claim 1, wherein the second portion is approximately 75% smaller than the first portion.

### Claim 7 (depends on 1)

The method of claim 1, wherein the centroid comprises a latitude and longitude in the selected region.

### Claim 8 (depends on 1)

The method of claim 1, wherein the step of moving includes applying a Gaussian distribution function to govern a distance between the location of the centroid and the revised location.

### Claim 9 (depends on 1)

The method of claim 1, wherein the first output and the second output comprise vector outputs.

### Claim 10 (depends on 1)

The method of claim 1, wherein the third network comprises a fully connected layer.

### Claim 11

A method, comprising:
by an interactive neural network inclusive of a first network trained with ImageNet and a second network comprising a recurrent neural network inclusive of a fully connected layer trained with census data collected for a geographic region,
a) obtaining a satellite image of the geographic region;
b) cropping, by a processor coupled to the interactive neural network, the satellite image to define a cropped satellite image inclusive of a selected region of the geographic region wherein each pixel of the cropped satellite image has a brightness value;
c) multiplying, by the processor, the brightness value for each pixel in the cropped satellite image by a factor of at least 2 to generate a brightened satellite image;
d) sampling, by the processor, a first portion of the brightened satellite image wherein the first portion has a centroid defined by a location in the selected region;
e) generating, by the processor, a second portion of the brightened satellite image centered on the centroid wherein the first portion and the second portion have different resolutions;
f) processing, by the first network, the first portion to generate a first output indicative of features in the first portion and the second portion to generate a second output indicative of features in the second portion;
g) processing, by the second network, the first output and the second output to generate an estimated census metric associated with the centroid;
h) comparing, by the second network, the estimated census metric with a corresponding metric from the census data to generate a difference there between; and
i) moving, by the second network, the location of the centroid to a revised location in the selected region and repeating steps d) through h) until the difference is less than a prescribed threshold.

### Claim 12 (depends on 11)

The method of claim 11, wherein the geographic region has a governing body associated therewith, and wherein the census data is collected by the governing body.

### Claim 13 (depends on 11)

The method of claim 11, wherein the selected region is selected from the group consisting of at least one of a state, a province, a city, a county, and a municipality.

### Claim 14 (depends on 11)

The method of claim 11, wherein the second portion is in a range of 50% to 80% smaller than the first portion.

### Claim 15 (depends on 11)

The method of claim 11, wherein the second portion is approximately 75% smaller than the first portion.

### Claim 16 (depends on 11)

The method of claim 11, wherein the centroid comprises a latitude and longitude in the selected region.

### Claim 17 (depends on 11)

The method of claim 11, wherein the step of moving includes applying a Gaussian distribution function to govern a distance between the location of the centroid and the revised location.

### Claim 18 (depends on 11)

The method of claim 11, wherein the first output and the second output comprise vector outputs.

### Claim 19

A method, comprising:
by an interactive neural network inclusive of a first network trained with ImageNet and a second network comprising a recurrent neural network inclusive of a fully connected layer trained with census data collected for a geographic region,
a) obtaining a satellite image of the geographic region;
b) cropping, by a processor coupled to the interactive neural network, the satellite image to define a cropped satellite image inclusive of a selected region of the geographic region, wherein the selected region comprises at least one of a state, a province, a city, a county, and a municipality of the geographic region, and wherein each pixel of the cropped satellite image has a brightness value;
c) multiplying, by the processor, the brightness value for each pixel in the cropped satellite image by a factor of at least 2 to generate a brightened satellite image;
d) sampling, by the processor, a first portion of the brightened satellite image wherein the first portion has a centroid defined by a location in the selected region;
e) generating, by the processor, a second portion of the brightened satellite image centered on the centroid wherein the first portion and the second portion have different resolutions;
f) processing, by the first network, the first portion to generate a first output indicative of features in the first portion and the second portion to generate a second output indicative of features in the second portion;
g) processing, by the second network, the first output and the second output to generate an estimated census metric associated with the centroid;
h) comparing, by the second network, the estimated census metric with a corresponding metric from the census data to generate a difference there between; and
i) moving, by the second network, the location of the centroid to a revised location in the selected region in accordance with a Gaussian distribution function and repeating steps d) through h) until the difference is less than a prescribed threshold.

### Claim 20 (depends on 19)

The method of claim 19, wherein the second portion is in a range of 50% to 80% smaller than the first portion.

### Claim 21 (depends on 19)

The method of claim 19, wherein the second portion is approximately 75% smaller than the first portion.

### Claim 22 (depends on 19)

The method of claim 19, wherein the centroid comprises a latitude and longitude in the selected region.

### Claim 23 (depends on 19)

The method of claim 19, wherein the first output and the second output comprise vector outputs.
