Cargando…

A review of explainable AI in the satellite data, deep machine learning, and human poverty domain

Recent advances in artificial intelligence and deep machine learning have created a step change in how to measure human development indicators, in particular asset-based poverty. The combination of satellite imagery and deep machine learning now has the capability to estimate some types of poverty a...

Descripción completa

Detalles Bibliográficos
Autores principales: Hall, Ola, Ohlsson, Mattias, Rögnvaldsson, Thorsteinn
Formato: Online Artículo Texto
Lenguaje:English
Publicado: Elsevier 2022
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9583173/
https://www.ncbi.nlm.nih.gov/pubmed/36277818
http://dx.doi.org/10.1016/j.patter.2022.100600
_version_ 1784813011961118720
author Hall, Ola
Ohlsson, Mattias
Rögnvaldsson, Thorsteinn
author_facet Hall, Ola
Ohlsson, Mattias
Rögnvaldsson, Thorsteinn
author_sort Hall, Ola
collection PubMed
description Recent advances in artificial intelligence and deep machine learning have created a step change in how to measure human development indicators, in particular asset-based poverty. The combination of satellite imagery and deep machine learning now has the capability to estimate some types of poverty at a level close to what is achieved with traditional household surveys. An increasingly important issue beyond static estimations is whether this technology can contribute to scientific discovery and, consequently, new knowledge in the poverty and welfare domain. A foundation for achieving scientific insights is domain knowledge, which in turn translates into explainability and scientific consistency. We perform an integrative literature review focusing on three core elements relevant in this context—transparency, interpretability, and explainability—and investigate how they relate to the poverty, machine learning, and satellite imagery nexus. Our inclusion criteria for papers are that they cover poverty/wealth prediction, using survey data as the basis for the ground truth poverty/wealth estimates, be applicable to both urban and rural settings, use satellite images as the basis for at least some of the inputs (features), and the method should include deep neural networks. Our review of 32 papers shows that the status of the three core elements of explainable machine learning (transparency, interpretability, and domain knowledge) is varied and does not completely fulfill the requirements set up for scientific insights and discoveries. We argue that explainability is essential to support wider dissemination and acceptance of this research in the development community and that explainability means more than just interpretability.
format Online
Article
Text
id pubmed-9583173
institution National Center for Biotechnology Information
language English
publishDate 2022
publisher Elsevier
record_format MEDLINE/PubMed
spelling pubmed-95831732022-10-21 A review of explainable AI in the satellite data, deep machine learning, and human poverty domain Hall, Ola Ohlsson, Mattias Rögnvaldsson, Thorsteinn Patterns (N Y) Review Recent advances in artificial intelligence and deep machine learning have created a step change in how to measure human development indicators, in particular asset-based poverty. The combination of satellite imagery and deep machine learning now has the capability to estimate some types of poverty at a level close to what is achieved with traditional household surveys. An increasingly important issue beyond static estimations is whether this technology can contribute to scientific discovery and, consequently, new knowledge in the poverty and welfare domain. A foundation for achieving scientific insights is domain knowledge, which in turn translates into explainability and scientific consistency. We perform an integrative literature review focusing on three core elements relevant in this context—transparency, interpretability, and explainability—and investigate how they relate to the poverty, machine learning, and satellite imagery nexus. Our inclusion criteria for papers are that they cover poverty/wealth prediction, using survey data as the basis for the ground truth poverty/wealth estimates, be applicable to both urban and rural settings, use satellite images as the basis for at least some of the inputs (features), and the method should include deep neural networks. Our review of 32 papers shows that the status of the three core elements of explainable machine learning (transparency, interpretability, and domain knowledge) is varied and does not completely fulfill the requirements set up for scientific insights and discoveries. We argue that explainability is essential to support wider dissemination and acceptance of this research in the development community and that explainability means more than just interpretability. Elsevier 2022-10-14 /pmc/articles/PMC9583173/ /pubmed/36277818 http://dx.doi.org/10.1016/j.patter.2022.100600 Text en © 2022 The Author(s) https://creativecommons.org/licenses/by-nc-nd/4.0/This is an open access article under the CC BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/).
spellingShingle Review
Hall, Ola
Ohlsson, Mattias
Rögnvaldsson, Thorsteinn
A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title_full A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title_fullStr A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title_full_unstemmed A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title_short A review of explainable AI in the satellite data, deep machine learning, and human poverty domain
title_sort review of explainable ai in the satellite data, deep machine learning, and human poverty domain
topic Review
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC9583173/
https://www.ncbi.nlm.nih.gov/pubmed/36277818
http://dx.doi.org/10.1016/j.patter.2022.100600
work_keys_str_mv AT hallola areviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain
AT ohlssonmattias areviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain
AT rognvaldssonthorsteinn areviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain
AT hallola reviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain
AT ohlssonmattias reviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain
AT rognvaldssonthorsteinn reviewofexplainableaiinthesatellitedatadeepmachinelearningandhumanpovertydomain