Predicting Poverty Using Geospatial Data in Thailand
Bibliographic Data
| ID | 22033482 |
|---|---|
| Authors | Nattapong Puttanapong (0000-0002-5643-7979, Thammasat University, corresponding author), Arturo Martinez (0000-0002-3384-4061, Asian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, Philippines), A J Martínez (0000-0002-1822-5078, Asian Development Bank), Joseph Albert Nino Bulan (Asian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, Philippines), Joseph Bulan (0009-0009-8964-5828, Asian Development Bank), Mildred Addawe (0009-0002-9481-4365, Asian Development Bank), Ron Lester Durante (0000-0001-7555-4436, Asian Development Bank), Marymell Martillan (0000-0002-1500-9548, Asian Development Bank) |
| Year | 2022 |
| Volume | 11 |
| Issue | 5 |
| Pages | 293 |
| Publication date | 2022-04-30 |
| Peer Reviewed | Yes |
| Open Access | Yes |
| Type | ARTICLE |
| Venue | ISPRS International Journal of Geo-Information (JOURNAL) |
| Journal identifiers | ISSN: 2220-9964 • E-ISSN: 2220-9964 |
| Publisher | MDPI AG (PUBLISHER • IT) |
| DOI | 10.3390/ijgi11050293 |
| OpenAlex | W4225257363 |
| Language | EN |
| Citations received | 13 |
| References cited | 84 |
Poverty statistics are conventionally compiled using data from socioeconomic surveys. This study examines an alternative approach to estimating poverty by investigating whether readily available geospatial data can accurately predict the spatial distribution of poverty in Thailand. In particular, the geospatial data examined in this study include the intensity of night-time light (NTL), land cover, vegetation index, land surface temperature, built-up areas, and points of interest. The study also compares the predictive performance of various econometric and machine-learning methods such as generalized least squares, neural network, random forest, and support-vector regression. Results suggest that the intensity of NTL and other variables that approximate population density are highly associated with the proportion of an area’s population that are living in poverty. The random forest technique yielded the highest level of prediction accuracy among the methods considered in this study, primarily due to its capability to fit complex association structures even with small-to-medium-sized datasets. This obtained result suggests the potential applications of using publicly accessible geospatial data and machine-learning methods for timely monitoring of the poverty distribution. Moving forward, additional studies are needed to improve the predictive power and investigate the temporal stability of the relationships observed
Cartography · Econometrics · Geography · Geospatial analysis · Land cover · Land use · Machine learning · Population · Poverty · Predictive power · Random forest · Regression · Socioeconomic status · Statistics · Computer Science · Demography · Impact of Light on Environment and Health · Land Use and Ecosystem Services · Mathematics · Remote Sensing in Agriculture · Ecology
Factors influencing housing rental decisions across major cities in Thailand
Exploring the Relationship between Melioidosis Morbidity Rate and Local Environmental Indicators Using Remotely Sensed Data
How accurate is a poverty map based on remote sensing data? An application to Malawi
The Spatial Effects of Regional Poverty
Determinants of Multidimensional Poverty in Rural Ethiopia
A review of machine learning and satellite imagery for poverty prediction
Nighttime light satellite images reveal uneven socioeconomic development along China's land border
Mapping the Dimensions of Poverty Through Big Data, Socioeconomic Surveys and Machine Learning in Cambodia
Determination of households benefits from subsidies by using data mining approaches
Economic Experimentation under Authoritarian Closure
Urban poverty patterns in Pyongyang (North Korea)
Evaluating area-level features for proxy means test models
Predicting Multidimensional Poverty with Machine Learning Algorithms
Retooling Poverty Targeting Using Out-of-Sample Validation and Machine Learning
Urban heat islands and landscape heterogeneity
Relation between satellite observed visible-near infrared emissions, population, economic activity and electric power consumption
Under the Weather
Potential of NPP-Viirs Nighttime Light Imagery for Modeling the Regional Economy of China
Extracting urban functional regions from points of interest and human activities on location‐based social networks
Using publicly available satellite imagery and deep learning to understand economic well-being in Africa
Mapping poverty using mobile phone and satellite data
Spatial determinants of poverty in rural Kenya
Measuring Economic Growth from Outer Space
Combining satellite imagery and machine learning to predict poverty
Bias in random forest variable importance measures
Improved population mapping for China using remotely sensed and points-of-interest data within a random forests model
Google Earth Engine
Random Forests
Sustainable Development Report 2021
Global Inequality
Mapping regional economic activity from night-time light satellite imagery
Is Random Forest a Superior Methodology for Predicting Poverty? An Empirical Assessment
Analysis of the relationship between rainfall and economic growth in Indian states
Livelihood mapping and poverty correlates at a meso-level in Kenya
Understanding the Evidence Base for Poverty–Environment Relationships using Remotely Sensed Satellite Data
Rainfall Shocks and Within-Community Wealth Inequality
Who are the world’s poor? A new profile of global multidimensional poverty
Rainfall and conflict
China's poverty alleviation resettlement
Night-time Imagery as a Tool for Global Mapping of Socioeconomic Parameters and Greenhouse Gas Emissions
Ethnic Inequality
How much did droughts matter? Linking rainfall and GDP growth in Zimbabwe
The Poverty-Growth-Inequality Triangle
| Unique citing works | 13 |
|---|---|
| Citations per year | 3,25 |
| Citation span | 2022 - 2026 (5) |
| Citation velocity | current |
| Highly cited | No |
| Citation types | Neutral: 10 |