Predicting wealth score from remote sensing satellite images and household survey data using deep learning
The most exigent call of the United Nations’ 17 sustainable goals is to end poverty everywhere by 2030. Unlike in the past, when poverty was measured based on data collected through ground-level surveys, the new technology adopted by many developing and developed countries is to estimate the poverty...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Institute of Fundamental Technological Research PAS
2024
|
| Subjects: | |
| Online Access: | https://repository.londonmet.ac.uk/10037/1/SatteliteDeepLearning_CAMES_4.pdf |
| _version_ | 1824446524607692800 |
|---|---|
| author | Shekhar, Shashank Singh, Pratibha Mishra, Rashmi Kumar, Sunil |
| author_facet | Shekhar, Shashank Singh, Pratibha Mishra, Rashmi Kumar, Sunil |
| author_sort | Shekhar, Shashank |
| collection | LMU |
| description | The most exigent call of the United Nations’ 17 sustainable goals is to end poverty everywhere by 2030. Unlike in the past, when poverty was measured based on data collected through ground-level surveys, the new technology adopted by many developing and developed countries is to estimate the poverty index using remote sensing satellite images with the help of machine learning techniques. Our approach demonstrates the prediction of cluster wealth score and establishes the relationship between wealth score obtained from Demographic and Health Survey (DHS) data and remote sensing satellite images of India by calculating Pearson’s correlation coefficient (r2). The implementation results have been analyzed in four phases. Phase 1 comprises four regression models (RMs): Ridge, RANSAC, Lasso, and k-nearest neighbor for feature extraction from a pre-trained convolutional neural network model using daylight & nightlight images. Here, the Lasso RM outperforms the others and is best suited for predicting the wealth score. Phase 2 categorizes daylight images with DHS data, where the Lasso RM efficiently generates the cluster wealth score. Phase 3 focuses on images of specific regions of Delhi, Tamil Nadu, Maharashtra and Telangana, using the Lasso RM, as it emerged as the best predictor of cluster wealth score in the previous two phases. Phase 4 compares the results attained through our proposed model with existing results |
| first_indexed | 2025-02-19T01:16:32Z |
| format | Article |
| id | oai:repository.londonmet.ac.uk:10037 |
| institution | London Metropolitan University |
| language | English |
| last_indexed | 2025-02-19T01:16:32Z |
| publishDate | 2024 |
| publisher | Institute of Fundamental Technological Research PAS |
| record_format | eprints |
| spelling | oai:repository.londonmet.ac.uk:100372025-01-22T14:08:00Z https://repository.londonmet.ac.uk/10037/ Predicting wealth score from remote sensing satellite images and household survey data using deep learning Shekhar, Shashank Singh, Pratibha Mishra, Rashmi Kumar, Sunil 000 Computer science, information & general works 600 Technology The most exigent call of the United Nations’ 17 sustainable goals is to end poverty everywhere by 2030. Unlike in the past, when poverty was measured based on data collected through ground-level surveys, the new technology adopted by many developing and developed countries is to estimate the poverty index using remote sensing satellite images with the help of machine learning techniques. Our approach demonstrates the prediction of cluster wealth score and establishes the relationship between wealth score obtained from Demographic and Health Survey (DHS) data and remote sensing satellite images of India by calculating Pearson’s correlation coefficient (r2). The implementation results have been analyzed in four phases. Phase 1 comprises four regression models (RMs): Ridge, RANSAC, Lasso, and k-nearest neighbor for feature extraction from a pre-trained convolutional neural network model using daylight & nightlight images. Here, the Lasso RM outperforms the others and is best suited for predicting the wealth score. Phase 2 categorizes daylight images with DHS data, where the Lasso RM efficiently generates the cluster wealth score. Phase 3 focuses on images of specific regions of Delhi, Tamil Nadu, Maharashtra and Telangana, using the Lasso RM, as it emerged as the best predictor of cluster wealth score in the previous two phases. Phase 4 compares the results attained through our proposed model with existing results Institute of Fundamental Technological Research PAS 2024-06-24 Article PeerReviewed text en cc_by_4 https://repository.londonmet.ac.uk/10037/1/SatteliteDeepLearning_CAMES_4.pdf Shekhar, Shashank, Singh, Pratibha, Mishra, Rashmi and Kumar, Sunil (2024) Predicting wealth score from remote sensing satellite images and household survey data using deep learning. Computer Assisted Methods in Engineering and Science, 31 (3). pp. 351-387. ISSN 2299-3649 http://dx.doi.org/10.24423/cames.2024.722 10.24423/cames.2024.722 10.24423/cames.2024.722 |
| spellingShingle | 000 Computer science, information & general works 600 Technology Shekhar, Shashank Singh, Pratibha Mishra, Rashmi Kumar, Sunil Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title | Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title_full | Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title_fullStr | Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title_full_unstemmed | Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title_short | Predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| title_sort | predicting wealth score from remote sensing satellite images and household survey data using deep learning |
| topic | 000 Computer science, information & general works 600 Technology |
| url | https://repository.londonmet.ac.uk/10037/1/SatteliteDeepLearning_CAMES_4.pdf |
| work_keys_str_mv | AT shekharshashank predictingwealthscorefromremotesensingsatelliteimagesandhouseholdsurveydatausingdeeplearning AT singhpratibha predictingwealthscorefromremotesensingsatelliteimagesandhouseholdsurveydatausingdeeplearning AT mishrarashmi predictingwealthscorefromremotesensingsatelliteimagesandhouseholdsurveydatausingdeeplearning AT kumarsunil predictingwealthscorefromremotesensingsatelliteimagesandhouseholdsurveydatausingdeeplearning |