Predicting road quality using high resolution satellite imagery: A transfer learning approach.
Recognizing the importance of road infrastructure to promote human health and economic development, actors around the globe are regularly investing in both new roads and road improvements. However, in many contexts there is a sparsity-or complete lack-of accurate information regarding existing road...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Public Library of Science (PLoS)
2021-01-01
|
| Series: | PLoS ONE |
| Online Access: | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0253370&type=printable |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1850239661687963648 |
|---|---|
| author | Ethan Brewer Jason Lin Peter Kemper John Hennin Dan Runfola |
| author_facet | Ethan Brewer Jason Lin Peter Kemper John Hennin Dan Runfola |
| author_sort | Ethan Brewer |
| collection | DOAJ |
| description | Recognizing the importance of road infrastructure to promote human health and economic development, actors around the globe are regularly investing in both new roads and road improvements. However, in many contexts there is a sparsity-or complete lack-of accurate information regarding existing road infrastructure, challenging the effective identification of where investments should be made. Previous literature has focused on overcoming this gap through the use of satellite imagery to detect and map roads. In this piece, we extend this literature by leveraging satellite imagery to estimate road quality and concomitant information about travel speed. We adopt a transfer learning approach in which a convolutional neural network architecture is first trained on data collected in the United States (where data is readily available), and then "fine-tuned" on an independent, smaller dataset collected from Nigeria. We test and compare eight different convolutional neural network architectures using a dataset of 53,686 images of 2,400 kilometers of roads in the United States, in which each road segment is measured as "low", "middle", or "high" quality using an open, cellphone-based measuring platform. Using satellite imagery to estimate these classes, we achieve an accuracy of 80.0%, with 99.4% of predictions falling within the actual or an adjacent class. The highest performing base model was applied to a preliminary case study in Nigeria, using a dataset of 1,000 images of paved and unpaved roads. By tailoring our US-model on the basis of this Nigeria-specific data, we were able to achieve an accuracy of 94.0% in predicting the quality of Nigerian roads. A continuous case estimate also showed the ability, on average, to predict road quality to within 0.32 on a 0 to 3 scale (with higher values indicating higher levels of quality). |
| format | Article |
| id | doaj-art-3049a5bdc60d4bcda31227041cbc08dd |
| institution | OA Journals |
| issn | 1932-6203 |
| language | English |
| publishDate | 2021-01-01 |
| publisher | Public Library of Science (PLoS) |
| record_format | Article |
| series | PLoS ONE |
| spelling | doaj-art-3049a5bdc60d4bcda31227041cbc08dd2025-08-20T02:01:05ZengPublic Library of Science (PLoS)PLoS ONE1932-62032021-01-01167e025337010.1371/journal.pone.0253370Predicting road quality using high resolution satellite imagery: A transfer learning approach.Ethan BrewerJason LinPeter KemperJohn HenninDan RunfolaRecognizing the importance of road infrastructure to promote human health and economic development, actors around the globe are regularly investing in both new roads and road improvements. However, in many contexts there is a sparsity-or complete lack-of accurate information regarding existing road infrastructure, challenging the effective identification of where investments should be made. Previous literature has focused on overcoming this gap through the use of satellite imagery to detect and map roads. In this piece, we extend this literature by leveraging satellite imagery to estimate road quality and concomitant information about travel speed. We adopt a transfer learning approach in which a convolutional neural network architecture is first trained on data collected in the United States (where data is readily available), and then "fine-tuned" on an independent, smaller dataset collected from Nigeria. We test and compare eight different convolutional neural network architectures using a dataset of 53,686 images of 2,400 kilometers of roads in the United States, in which each road segment is measured as "low", "middle", or "high" quality using an open, cellphone-based measuring platform. Using satellite imagery to estimate these classes, we achieve an accuracy of 80.0%, with 99.4% of predictions falling within the actual or an adjacent class. The highest performing base model was applied to a preliminary case study in Nigeria, using a dataset of 1,000 images of paved and unpaved roads. By tailoring our US-model on the basis of this Nigeria-specific data, we were able to achieve an accuracy of 94.0% in predicting the quality of Nigerian roads. A continuous case estimate also showed the ability, on average, to predict road quality to within 0.32 on a 0 to 3 scale (with higher values indicating higher levels of quality).https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0253370&type=printable |
| spellingShingle | Ethan Brewer Jason Lin Peter Kemper John Hennin Dan Runfola Predicting road quality using high resolution satellite imagery: A transfer learning approach. PLoS ONE |
| title | Predicting road quality using high resolution satellite imagery: A transfer learning approach. |
| title_full | Predicting road quality using high resolution satellite imagery: A transfer learning approach. |
| title_fullStr | Predicting road quality using high resolution satellite imagery: A transfer learning approach. |
| title_full_unstemmed | Predicting road quality using high resolution satellite imagery: A transfer learning approach. |
| title_short | Predicting road quality using high resolution satellite imagery: A transfer learning approach. |
| title_sort | predicting road quality using high resolution satellite imagery a transfer learning approach |
| url | https://journals.plos.org/plosone/article/file?id=10.1371/journal.pone.0253370&type=printable |
| work_keys_str_mv | AT ethanbrewer predictingroadqualityusinghighresolutionsatelliteimageryatransferlearningapproach AT jasonlin predictingroadqualityusinghighresolutionsatelliteimageryatransferlearningapproach AT peterkemper predictingroadqualityusinghighresolutionsatelliteimageryatransferlearningapproach AT johnhennin predictingroadqualityusinghighresolutionsatelliteimageryatransferlearningapproach AT danrunfola predictingroadqualityusinghighresolutionsatelliteimageryatransferlearningapproach |