Predicting Poverty Using Geospatial Data in Thailand
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, th...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-04-01
|
| Series: | ISPRS International Journal of Geo-Information |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2220-9964/11/5/293 |
| _version_ | 1797499342782726144 |
|---|---|
| author | Nattapong Puttanapong Arturo Martinez Joseph Albert Nino Bulan Mildred Addawe Ron Lester Durante Marymell Martillan |
| author_facet | Nattapong Puttanapong Arturo Martinez Joseph Albert Nino Bulan Mildred Addawe Ron Lester Durante Marymell Martillan |
| author_sort | Nattapong Puttanapong |
| collection | DOAJ |
| description | 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. |
| first_indexed | 2024-03-10T03:46:03Z |
| format | Article |
| id | doaj.art-135c1f9b1f314bbabc8d5c1d034b104f |
| institution | Directory Open Access Journal |
| issn | 2220-9964 |
| language | English |
| last_indexed | 2024-03-10T03:46:03Z |
| publishDate | 2022-04-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | ISPRS International Journal of Geo-Information |
| spelling | doaj.art-135c1f9b1f314bbabc8d5c1d034b104f2023-11-23T11:19:46ZengMDPI AGISPRS International Journal of Geo-Information2220-99642022-04-0111529310.3390/ijgi11050293Predicting Poverty Using Geospatial Data in ThailandNattapong Puttanapong0Arturo Martinez1Joseph Albert Nino Bulan2Mildred Addawe3Ron Lester Durante4Marymell Martillan5Faculty of Economics, Thammasat University, Bangkok 10200, ThailandAsian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, PhilippinesAsian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, PhilippinesAsian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, PhilippinesAsian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, PhilippinesAsian Development Bank (ADB), Mandaluyong City 1550, Metro Manila, PhilippinesPoverty 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.https://www.mdpi.com/2220-9964/11/5/293povertyThailandgeospatialmachine learning |
| spellingShingle | Nattapong Puttanapong Arturo Martinez Joseph Albert Nino Bulan Mildred Addawe Ron Lester Durante Marymell Martillan Predicting Poverty Using Geospatial Data in Thailand ISPRS International Journal of Geo-Information poverty Thailand geospatial machine learning |
| title | Predicting Poverty Using Geospatial Data in Thailand |
| title_full | Predicting Poverty Using Geospatial Data in Thailand |
| title_fullStr | Predicting Poverty Using Geospatial Data in Thailand |
| title_full_unstemmed | Predicting Poverty Using Geospatial Data in Thailand |
| title_short | Predicting Poverty Using Geospatial Data in Thailand |
| title_sort | predicting poverty using geospatial data in thailand |
| topic | poverty Thailand geospatial machine learning |
| url | https://www.mdpi.com/2220-9964/11/5/293 |
| work_keys_str_mv | AT nattapongputtanapong predictingpovertyusinggeospatialdatainthailand AT arturomartinez predictingpovertyusinggeospatialdatainthailand AT josephalbertninobulan predictingpovertyusinggeospatialdatainthailand AT mildredaddawe predictingpovertyusinggeospatialdatainthailand AT ronlesterdurante predictingpovertyusinggeospatialdatainthailand AT marymellmartillan predictingpovertyusinggeospatialdatainthailand |