A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions
The effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-01-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/3/672 |
| _version_ | 1797485031064600576 |
|---|---|
| author | Sepideh Tavakkoli Piralilou Golzar Einali Omid Ghorbanzadeh Thimmaiah Gudiyangada Nachappa Khalil Gholamnia Thomas Blaschke Pedram Ghamisi |
| author_facet | Sepideh Tavakkoli Piralilou Golzar Einali Omid Ghorbanzadeh Thimmaiah Gudiyangada Nachappa Khalil Gholamnia Thomas Blaschke Pedram Ghamisi |
| author_sort | Sepideh Tavakkoli Piralilou |
| collection | DOAJ |
| description | The effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using random forest (RF) and support vector machine (SVM) models. In addition, we investigate the fusion of the predictions from the different spatial resolutions using the Dempster–Shafer theory (DST) and 14 wildfire conditioning factors. Seven factors are derived separately from the coarse and medium spatial resolution datasets for the whole forest area of the Guilan Province, Iran. All conditional factors are used to train and test the SVM and RF models in the Google Earth Engine (GEE) software environment, along with an inventory dataset from comprehensive global positioning system (GPS)-based field survey points of wildfire locations. These locations are evaluated and combined with coarse resolution satellite data, namely the thermal anomalies product of the moderate resolution imaging spectroradiometer (MODIS) for the period 2009 to 2019. We assess the performance of the models using four-fold cross-validation by the receiver operating characteristic (ROC) curve method. The area under the curve (AUC) achieved from the ROC curve yields 92.15% and 91.98% accuracy for the respective SVM and RF models for the coarse RS data. In comparison, the AUC for the medium RS data is 92.5% and 93.37%, respectively. Remarkably, the highest AUC value of 94.71% is achieved for the RF model where coarse and medium resolution datasets are combined through DST. |
| first_indexed | 2024-03-09T23:12:59Z |
| format | Article |
| id | doaj.art-aec96c1c877045b480f73142152e8e23 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T23:12:59Z |
| publishDate | 2022-01-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-aec96c1c877045b480f73142152e8e232023-11-23T17:41:36ZengMDPI AGRemote Sensing2072-42922022-01-0114367210.3390/rs14030672A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial ResolutionsSepideh Tavakkoli Piralilou0Golzar Einali1Omid Ghorbanzadeh2Thimmaiah Gudiyangada Nachappa3Khalil Gholamnia4Thomas Blaschke5Pedram Ghamisi6Department of Geoinformatics—Z_GIS, University of Salzburg, 5020 Salzburg, AustriaDepartment of Remote Sensing and GIS, University of Tabriz, Tabriz 5166616471, IranInstitute of Advanced Research in Artificial Intelligence (IARAI), Landstraßer Hauptstraße 5, 1030 Vienna, AustriaGroup Digital Transformation—New Propositions Swiss Re Europe S.A., Niederlassung Deutschland, Arabellastrasse 30, 81925 Munich, GermanyDepartment of Remote Sensing and GIS, University of Tabriz, Tabriz 5166616471, IranDepartment of Geoinformatics—Z_GIS, University of Salzburg, 5020 Salzburg, AustriaInstitute of Advanced Research in Artificial Intelligence (IARAI), Landstraßer Hauptstraße 5, 1030 Vienna, AustriaThe effects of the spatial resolution of remote sensing (RS) data on wildfire susceptibility prediction are not fully understood. In this study, we evaluate the effects of coarse (Landsat 8 and SRTM) and medium (Sentinel-2 and ALOS) spatial resolution data on wildfire susceptibility prediction using random forest (RF) and support vector machine (SVM) models. In addition, we investigate the fusion of the predictions from the different spatial resolutions using the Dempster–Shafer theory (DST) and 14 wildfire conditioning factors. Seven factors are derived separately from the coarse and medium spatial resolution datasets for the whole forest area of the Guilan Province, Iran. All conditional factors are used to train and test the SVM and RF models in the Google Earth Engine (GEE) software environment, along with an inventory dataset from comprehensive global positioning system (GPS)-based field survey points of wildfire locations. These locations are evaluated and combined with coarse resolution satellite data, namely the thermal anomalies product of the moderate resolution imaging spectroradiometer (MODIS) for the period 2009 to 2019. We assess the performance of the models using four-fold cross-validation by the receiver operating characteristic (ROC) curve method. The area under the curve (AUC) achieved from the ROC curve yields 92.15% and 91.98% accuracy for the respective SVM and RF models for the coarse RS data. In comparison, the AUC for the medium RS data is 92.5% and 93.37%, respectively. Remarkably, the highest AUC value of 94.71% is achieved for the RF model where coarse and medium resolution datasets are combined through DST.https://www.mdpi.com/2072-4292/14/3/672Sentinel-2Landsat 8SRTMALOSheterogeneous dataforest fire |
| spellingShingle | Sepideh Tavakkoli Piralilou Golzar Einali Omid Ghorbanzadeh Thimmaiah Gudiyangada Nachappa Khalil Gholamnia Thomas Blaschke Pedram Ghamisi A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions Remote Sensing Sentinel-2 Landsat 8 SRTM ALOS heterogeneous data forest fire |
| title | A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions |
| title_full | A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions |
| title_fullStr | A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions |
| title_full_unstemmed | A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions |
| title_short | A Google Earth Engine Approach for Wildfire Susceptibility Prediction Fusion with Remote Sensing Data of Different Spatial Resolutions |
| title_sort | google earth engine approach for wildfire susceptibility prediction fusion with remote sensing data of different spatial resolutions |
| topic | Sentinel-2 Landsat 8 SRTM ALOS heterogeneous data forest fire |
| url | https://www.mdpi.com/2072-4292/14/3/672 |
| work_keys_str_mv | AT sepidehtavakkolipiralilou agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT golzareinali agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT omidghorbanzadeh agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT thimmaiahgudiyangadanachappa agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT khalilgholamnia agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT thomasblaschke agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT pedramghamisi agoogleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT sepidehtavakkolipiralilou googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT golzareinali googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT omidghorbanzadeh googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT thimmaiahgudiyangadanachappa googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT khalilgholamnia googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT thomasblaschke googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions AT pedramghamisi googleearthengineapproachforwildfiresusceptibilitypredictionfusionwithremotesensingdataofdifferentspatialresolutions |