Skip to main content

Lund University Publications

LUND UNIVERSITY LIBRARIES

Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks

Sarmadi, Hamid ; Rognvaldsson, Thorsteinn ; Carlsson, Nils Roger LU ; Ohlsson, Mattias LU orcid ; Wahab, Ibrahim LU and Hall, Ola LU (2023) 10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023 In 2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings
Abstract

Deep convolutional neural networks (CNNs) have been shown to predict poverty and development indicators from satellite images with surprising accuracy. This paper presents a first attempt at analyzing the CNNs responses in detail and explaining the basis for the predictions. The CNN model, while trained on relatively low resolution day- and night-time satellite images, is able to outperform human subjects who look at high-resolution images in ranking the Wealth Index categories. Multiple explainability experiments performed on the model indicate the importance of the sizes of the objects, pixel colors in the image, and provide a visualization of the importance of different structures in input images. A visualization is also provided of... (More)

Deep convolutional neural networks (CNNs) have been shown to predict poverty and development indicators from satellite images with surprising accuracy. This paper presents a first attempt at analyzing the CNNs responses in detail and explaining the basis for the predictions. The CNN model, while trained on relatively low resolution day- and night-time satellite images, is able to outperform human subjects who look at high-resolution images in ranking the Wealth Index categories. Multiple explainability experiments performed on the model indicate the importance of the sizes of the objects, pixel colors in the image, and provide a visualization of the importance of different structures in input images. A visualization is also provided of type images that maximize the network prediction of Wealth Index, which provides clues on what the CNN prediction is based on.

(Less)
Please use this url to cite or link to this publication:
author
; ; ; ; and
organization
publishing date
type
Chapter in Book/Report/Conference proceeding
publication status
published
subject
keywords
Deep Convolutional Neural Networks, Explainable AI, Poverty prediction, Satellite Images
host publication
2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings
series title
2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings
editor
Manolopoulos, Yannis and Zhou, Zhi-Hua
publisher
IEEE - Institute of Electrical and Electronics Engineers Inc.
conference name
10th IEEE International Conference on Data Science and Advanced Analytics, DSAA 2023
conference location
Thessaloniki, Greece
conference dates
2023-10-09 - 2023-10-12
external identifiers
  • scopus:85179010090
ISBN
9798350345032
DOI
10.1109/DSAA60987.2023.10302541
language
English
LU publication?
yes
additional info
Publisher Copyright: © 2023 IEEE.
id
a2e6c515-5454-4f25-ae9f-fdc94fe009b7
date added to LUP
2023-12-18 08:07:37
date last changed
2023-12-18 11:34:51
@inproceedings{a2e6c515-5454-4f25-ae9f-fdc94fe009b7,
  abstract     = {{<p>Deep convolutional neural networks (CNNs) have been shown to predict poverty and development indicators from satellite images with surprising accuracy. This paper presents a first attempt at analyzing the CNNs responses in detail and explaining the basis for the predictions. The CNN model, while trained on relatively low resolution day- and night-time satellite images, is able to outperform human subjects who look at high-resolution images in ranking the Wealth Index categories. Multiple explainability experiments performed on the model indicate the importance of the sizes of the objects, pixel colors in the image, and provide a visualization of the importance of different structures in input images. A visualization is also provided of type images that maximize the network prediction of Wealth Index, which provides clues on what the CNN prediction is based on.</p>}},
  author       = {{Sarmadi, Hamid and Rognvaldsson, Thorsteinn and Carlsson, Nils Roger and Ohlsson, Mattias and Wahab, Ibrahim and Hall, Ola}},
  booktitle    = {{2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings}},
  editor       = {{Manolopoulos, Yannis and Zhou, Zhi-Hua}},
  isbn         = {{9798350345032}},
  keywords     = {{Deep Convolutional Neural Networks; Explainable AI; Poverty prediction; Satellite Images}},
  language     = {{eng}},
  publisher    = {{IEEE - Institute of Electrical and Electronics Engineers Inc.}},
  series       = {{2023 IEEE 10th International Conference on Data Science and Advanced Analytics, DSAA 2023 - Proceedings}},
  title        = {{Towards Explaining Satellite Based Poverty Predictions with Convolutional Neural Networks}},
  url          = {{http://dx.doi.org/10.1109/DSAA60987.2023.10302541}},
  doi          = {{10.1109/DSAA60987.2023.10302541}},
  year         = {{2023}},
}