Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing
The COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies and advanced pandemic control methodologies, to limit the wide...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-06-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/13/3074 |
| _version_ | 1797408221966630912 |
|---|---|
| author | Anastasios Temenos Ioannis N. Tzortzis Maria Kaselimi Ioannis Rallis Anastasios Doulamis Nikolaos Doulamis |
| author_facet | Anastasios Temenos Ioannis N. Tzortzis Maria Kaselimi Ioannis Rallis Anastasios Doulamis Nikolaos Doulamis |
| author_sort | Anastasios Temenos |
| collection | DOAJ |
| description | The COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies and advanced pandemic control methodologies, to limit the wide spreading of the virus in urban areas. However, techniques such as social isolation and lockdown are short-term solutions that minimize the spread of the pandemic in cities and do not invert long-term issues that derive from climate change, air pollution and urban planning challenges that enhance the spreading ability. Thus, it seems crucial to understand what kind of factors assist or prevent the wide spreading of the virus. Although AI frameworks have a very efficient predictive ability as data-driven procedures, they often struggle to identify strong correlations among multidimensional data and provide robust explanations. In this paper, we propose the fusion of a heterogeneous, spatio-temporal dataset that combine data from eight European cities spanning from 1 January 2020 to 31 December 2021 and describe atmospheric, socio-economic, health, mobility and environmental factors all related to potential links with COVID-19. Remote sensing data are the key solution to monitor the availability on public green spaces between cities in the study period. So, we evaluate the benefits of NIR and RED bands of satellite images to calculate the NDVI and locate the percentage in vegetation cover on each city for each week of our 2-year study. This novel dataset is evaluated by a tree-based machine learning algorithm that utilizes ensemble learning and is trained to make robust predictions on daily cases and deaths. Comparisons with other machine learning techniques justify its robustness on the regression metrics RMSE and MAE. Furthermore, the explainable frameworks SHAP and LIME are utilized to locate potential positive or negative influence of the factors on global and local level, with respect to our model’s predictive ability. A variation of SHAP, namely treeSHAP, is utilized for our tree-based algorithm to make fast and accurate explanations. |
| first_indexed | 2024-03-09T03:55:16Z |
| format | Article |
| id | doaj.art-1ac69ff9bd674c93aa3c653801f3590d |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T03:55:16Z |
| publishDate | 2022-06-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-1ac69ff9bd674c93aa3c653801f3590d2023-12-03T14:20:20ZengMDPI AGRemote Sensing2072-42922022-06-011413307410.3390/rs14133074Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote SensingAnastasios Temenos0Ioannis N. Tzortzis1Maria Kaselimi2Ioannis Rallis3Anastasios Doulamis4Nikolaos Doulamis5Department of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceDepartment of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceDepartment of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceDepartment of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceDepartment of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceDepartment of Rural Surveying Engineering and Geoinformatics Engineering, National Technical University of Athens, 157 80 Athens, GreeceThe COVID-19 pandemic has affected many aspects of human life around the world, due to its tremendous outcomes on public health and socio-economic activities. Policy makers have tried to develop efficient responses based on technologies and advanced pandemic control methodologies, to limit the wide spreading of the virus in urban areas. However, techniques such as social isolation and lockdown are short-term solutions that minimize the spread of the pandemic in cities and do not invert long-term issues that derive from climate change, air pollution and urban planning challenges that enhance the spreading ability. Thus, it seems crucial to understand what kind of factors assist or prevent the wide spreading of the virus. Although AI frameworks have a very efficient predictive ability as data-driven procedures, they often struggle to identify strong correlations among multidimensional data and provide robust explanations. In this paper, we propose the fusion of a heterogeneous, spatio-temporal dataset that combine data from eight European cities spanning from 1 January 2020 to 31 December 2021 and describe atmospheric, socio-economic, health, mobility and environmental factors all related to potential links with COVID-19. Remote sensing data are the key solution to monitor the availability on public green spaces between cities in the study period. So, we evaluate the benefits of NIR and RED bands of satellite images to calculate the NDVI and locate the percentage in vegetation cover on each city for each week of our 2-year study. This novel dataset is evaluated by a tree-based machine learning algorithm that utilizes ensemble learning and is trained to make robust predictions on daily cases and deaths. Comparisons with other machine learning techniques justify its robustness on the regression metrics RMSE and MAE. Furthermore, the explainable frameworks SHAP and LIME are utilized to locate potential positive or negative influence of the factors on global and local level, with respect to our model’s predictive ability. A variation of SHAP, namely treeSHAP, is utilized for our tree-based algorithm to make fast and accurate explanations.https://www.mdpi.com/2072-4292/14/13/3074XAICOVID-19pandemicbig dataremote sensingNDVI |
| spellingShingle | Anastasios Temenos Ioannis N. Tzortzis Maria Kaselimi Ioannis Rallis Anastasios Doulamis Nikolaos Doulamis Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing Remote Sensing XAI COVID-19 pandemic big data remote sensing NDVI |
| title | Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing |
| title_full | Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing |
| title_fullStr | Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing |
| title_full_unstemmed | Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing |
| title_short | Novel Insights in Spatial Epidemiology Utilizing Explainable AI (XAI) and Remote Sensing |
| title_sort | novel insights in spatial epidemiology utilizing explainable ai xai and remote sensing |
| topic | XAI COVID-19 pandemic big data remote sensing NDVI |
| url | https://www.mdpi.com/2072-4292/14/13/3074 |
| work_keys_str_mv | AT anastasiostemenos novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing AT ioannisntzortzis novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing AT mariakaselimi novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing AT ioannisrallis novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing AT anastasiosdoulamis novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing AT nikolaosdoulamis novelinsightsinspatialepidemiologyutilizingexplainableaixaiandremotesensing |