Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand
This study introduced a new approach for monitoring regional development by applying satellite data with machine learning algorithms. Satellite data that represent physical features and environmental factors were obtained by developing a web-based application on the Google Earth Engine platform. Fou...
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
World Scientific Publishing
2023-09-01
|
| Series: | Asian Development Review |
| Subjects: | |
| Online Access: | https://www.worldscientific.com/doi/10.1142/S0116110523400024 |
| _version_ | 1797655878720028672 |
|---|---|
| author | NATTAPONG PUTTANAPONG NUTCHAPON PRASERTSOONG WICHAYA PEECHAPAT |
| author_facet | NATTAPONG PUTTANAPONG NUTCHAPON PRASERTSOONG WICHAYA PEECHAPAT |
| author_sort | NATTAPONG PUTTANAPONG |
| collection | DOAJ |
| description | This study introduced a new approach for monitoring regional development by applying satellite data with machine learning algorithms. Satellite data that represent physical features and environmental factors were obtained by developing a web-based application on the Google Earth Engine platform. Four machine learning methods were applied to the obtained geospatial data to predict provincial gross domestic product. The random forest method achieved the highest predictive performance, with 97.7% accuracy. The constructed random forest model was extended to conduct variable importance and minimal depth analyses, enabling the quantification of a factor’s influence on the prediction outcome. Variable importance and minimal depth analyses generated similar results, indicating that urban area and population are the most influential factors. Moreover, environmental and climate indicators exert medium-level effects. This study showed that integrating available satellite data and machine learning methods could be an alternative framework for facilitating a timely and costless monitoring system of regional development. |
| first_indexed | 2024-03-11T17:21:01Z |
| format | Article |
| id | doaj.art-e100bb6b1a494a7a96b9900fe44dfc49 |
| institution | Directory Open Access Journal |
| issn | 0116-1105 1996-7241 |
| language | English |
| last_indexed | 2024-03-11T17:21:01Z |
| publishDate | 2023-09-01 |
| publisher | World Scientific Publishing |
| record_format | Article |
| series | Asian Development Review |
| spelling | doaj.art-e100bb6b1a494a7a96b9900fe44dfc492023-10-19T12:43:52ZengWorld Scientific PublishingAsian Development Review0116-11051996-72412023-09-014002398510.1142/S0116110523400024Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of ThailandNATTAPONG PUTTANAPONG0NUTCHAPON PRASERTSOONG1WICHAYA PEECHAPAT2Faculty of Economics, Thammasat University, ThailandFaculty of Economics, Thammasat University, ThailandFaculty of Economics, Thammasat University, ThailandThis study introduced a new approach for monitoring regional development by applying satellite data with machine learning algorithms. Satellite data that represent physical features and environmental factors were obtained by developing a web-based application on the Google Earth Engine platform. Four machine learning methods were applied to the obtained geospatial data to predict provincial gross domestic product. The random forest method achieved the highest predictive performance, with 97.7% accuracy. The constructed random forest model was extended to conduct variable importance and minimal depth analyses, enabling the quantification of a factor’s influence on the prediction outcome. Variable importance and minimal depth analyses generated similar results, indicating that urban area and population are the most influential factors. Moreover, environmental and climate indicators exert medium-level effects. This study showed that integrating available satellite data and machine learning methods could be an alternative framework for facilitating a timely and costless monitoring system of regional development.https://www.worldscientific.com/doi/10.1142/S0116110523400024Google Earth Enginemachine learningregional developmentsatellite dataThailand |
| spellingShingle | NATTAPONG PUTTANAPONG NUTCHAPON PRASERTSOONG WICHAYA PEECHAPAT Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand Asian Development Review Google Earth Engine machine learning regional development satellite data Thailand |
| title | Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand |
| title_full | Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand |
| title_fullStr | Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand |
| title_full_unstemmed | Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand |
| title_short | Predicting Provincial Gross Domestic Product Using Satellite Data and Machine Learning Methods: A Case Study of Thailand |
| title_sort | predicting provincial gross domestic product using satellite data and machine learning methods a case study of thailand |
| topic | Google Earth Engine machine learning regional development satellite data Thailand |
| url | https://www.worldscientific.com/doi/10.1142/S0116110523400024 |
| work_keys_str_mv | AT nattapongputtanapong predictingprovincialgrossdomesticproductusingsatellitedataandmachinelearningmethodsacasestudyofthailand AT nutchaponprasertsoong predictingprovincialgrossdomesticproductusingsatellitedataandmachinelearningmethodsacasestudyofthailand AT wichayapeechapat predictingprovincialgrossdomesticproductusingsatellitedataandmachinelearningmethodsacasestudyofthailand |