Predicting poverty with vegetation index

Accurate and timely predictions of the poverty status of communities in developing countries are critical to policymakers. Previous work has applied convolutional neural networks (CNNs) to high‐resolution satellite imagery to perform community‐level poverty prediction. Although promising, such image...

Full description

Bibliographic Details
Main Authors: Tang, Binh, Liu, Yanyan, Matteson, David S.
Format: Journal Article
Language:Inglés
Published: Wiley 2022
Subjects:
Online Access:https://hdl.handle.net/10568/141232
_version_ 1855526915519021056
author Tang, Binh
Liu, Yanyan
Matteson, David S.
author_browse Liu, Yanyan
Matteson, David S.
Tang, Binh
author_facet Tang, Binh
Liu, Yanyan
Matteson, David S.
author_sort Tang, Binh
collection Repository of Agricultural Research Outputs (CGSpace)
description Accurate and timely predictions of the poverty status of communities in developing countries are critical to policymakers. Previous work has applied convolutional neural networks (CNNs) to high‐resolution satellite imagery to perform community‐level poverty prediction. Although promising, such imagery has limitations in predicting poverty among poor communities. We provide the first evidence that a publicly available, moderate‐resolution vegetation index (the normalized difference vegetation index [NDVI]), can be used with CNNs to produce accurate poverty predictions contemporaneously among poor communities heavily dependent on agriculture. We also show that the NDVI can effectively detect consumption variation over time. To our knowledge, this is the first attempt to use remote sensing data to predict future‐period consumption expenditure at the community level.
format Journal Article
id CGSpace141232
institution CGIAR Consortium
language Inglés
publishDate 2022
publishDateRange 2022
publishDateSort 2022
publisher Wiley
publisherStr Wiley
record_format dspace
spelling CGSpace1412322025-12-08T10:11:39Z Predicting poverty with vegetation index Tang, Binh Liu, Yanyan Matteson, David S. news machine learning poverty Accurate and timely predictions of the poverty status of communities in developing countries are critical to policymakers. Previous work has applied convolutional neural networks (CNNs) to high‐resolution satellite imagery to perform community‐level poverty prediction. Although promising, such imagery has limitations in predicting poverty among poor communities. We provide the first evidence that a publicly available, moderate‐resolution vegetation index (the normalized difference vegetation index [NDVI]), can be used with CNNs to produce accurate poverty predictions contemporaneously among poor communities heavily dependent on agriculture. We also show that the NDVI can effectively detect consumption variation over time. To our knowledge, this is the first attempt to use remote sensing data to predict future‐period consumption expenditure at the community level. 2022-06 2024-04-12T13:37:30Z 2024-04-12T13:37:30Z Journal Article https://hdl.handle.net/10568/141232 en https://doi.org/10.1002/aepp.13175 https://doi.org/10.1371/journal.pone.0255519 Limited Access Wiley Tang, Binh; Liu, Yanyan; and Matteson, David S. 2022. Predicting poverty with vegetation index. Applied Economic Perspectives and Policy 44(2): 930-945. https://doi.org/10.1002/aepp.13221
spellingShingle news
machine learning
poverty
Tang, Binh
Liu, Yanyan
Matteson, David S.
Predicting poverty with vegetation index
title Predicting poverty with vegetation index
title_full Predicting poverty with vegetation index
title_fullStr Predicting poverty with vegetation index
title_full_unstemmed Predicting poverty with vegetation index
title_short Predicting poverty with vegetation index
title_sort predicting poverty with vegetation index
topic news
machine learning
poverty
url https://hdl.handle.net/10568/141232
work_keys_str_mv AT tangbinh predictingpovertywithvegetationindex
AT liuyanyan predictingpovertywithvegetationindex
AT mattesondavids predictingpovertywithvegetationindex