A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia
Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automa...
Main Authors: | , , , , , |
---|---|
Format: | Article |
Language: | English |
Published: |
MDPI AG
2019-11-01
|
Series: | Sensors |
Subjects: | |
Online Access: | https://www.mdpi.com/1424-8220/19/22/4893 |
_version_ | 1798003590142361600 |
---|---|
author | Hejar Shahabi Ben Jarihani Sepideh Tavakkoli Piralilou David Chittleborough Mohammadtaghi Avand Omid Ghorbanzadeh |
author_facet | Hejar Shahabi Ben Jarihani Sepideh Tavakkoli Piralilou David Chittleborough Mohammadtaghi Avand Omid Ghorbanzadeh |
author_sort | Hejar Shahabi |
collection | DOAJ |
description | Gully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks. |
first_indexed | 2024-04-11T12:10:08Z |
format | Article |
id | doaj.art-f3e8d196338f432ea576138e31904671 |
institution | Directory Open Access Journal |
issn | 1424-8220 |
language | English |
last_indexed | 2024-04-11T12:10:08Z |
publishDate | 2019-11-01 |
publisher | MDPI AG |
record_format | Article |
series | Sensors |
spelling | doaj.art-f3e8d196338f432ea576138e319046712022-12-22T04:24:38ZengMDPI AGSensors1424-82202019-11-011922489310.3390/s19224893s19224893A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, AustraliaHejar Shahabi0Ben Jarihani1Sepideh Tavakkoli Piralilou2David Chittleborough3Mohammadtaghi Avand4Omid Ghorbanzadeh5Department of Remote Sensing and GIS, University of Tabriz, Tabriz 5166616471, IranMountain Societies Research Institute, University of Central Asia, Khorog 736000, TajikistanDepartment of Geoinformatics-Z _GIS, University of Salzburg, 5020 Salzburg, AustriaMountain Societies Research Institute, University of Central Asia, Khorog 736000, TajikistanFaculty of Natural Resources and Marine Sciences, Tarbiat Modares Unviversity (TMU), Tehran 46414-356, IranDepartment of Geoinformatics-Z _GIS, University of Salzburg, 5020 Salzburg, AustriaGully erosion is a dominant source of sediment and particulates to the Great Barrier Reef (GBR) World Heritage area. We selected the Bowen catchment, a tributary of the Burdekin Basin, as our area of study; the region is associated with a high density of gully networks. We aimed to use a semi-automated object-based gully networks detection process using a combination of multi-source and multi-scale remote sensing and ground-based data. An advanced approach was employed by integrating geographic object-based image analysis (GEOBIA) with current machine learning (ML) models. These included artificial neural networks (ANN), support vector machines (SVM), and random forests (RF), and an ensemble ML model of stacking to deal with the spatial scaling problem in gully networks detection. Spectral indices such as the normalized difference vegetation index (NDVI) and topographic conditioning factors, such as elevation, slope, aspect, topographic wetness index (TWI), slope length (SL), and curvature, were generated from Sentinel 2A images and the ALOS 12-m digital elevation model (DEM), respectively. For image segmentation, the ESP2 tool was used to obtain three optimal scale factors. On using object pureness index (OPI), object matching index (OMI), and object fitness index (OFI), the accuracy of each scale in image segmentation was evaluated. The scale parameter of 45 with OFI of 0.94, which is a combination of OPI and OMI indices, proved to be the optimal scale parameter for image segmentation. Furthermore, segmented objects based on scale 45 were overlaid with 70% and 30% of a prepared gully inventory map to select the ML models’ training and testing objects, respectively. The quantitative accuracy assessment methods of Precision, Recall, and an F1 measure were used to evaluate the model’s performance. Integration of GEOBIA with the stacking model using a scale of 45 resulted in the highest accuracy in detection of gully networks with an F1 measure value of 0.89. Here, we conclude that the adoption of optimal scale object definition in the GEOBIA and application of the ensemble stacking of ML models resulted in higher accuracy in the detection of gully networks.https://www.mdpi.com/1424-8220/19/22/4893geographic object-based image analysis (geobia)gully erosionoptimal scale detectionstacking modelbowen catchment |
spellingShingle | Hejar Shahabi Ben Jarihani Sepideh Tavakkoli Piralilou David Chittleborough Mohammadtaghi Avand Omid Ghorbanzadeh A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia Sensors geographic object-based image analysis (geobia) gully erosion optimal scale detection stacking model bowen catchment |
title | A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia |
title_full | A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia |
title_fullStr | A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia |
title_full_unstemmed | A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia |
title_short | A Semi-Automated Object-Based Gully Networks Detection Using Different Machine Learning Models: A Case Study of Bowen Catchment, Queensland, Australia |
title_sort | semi automated object based gully networks detection using different machine learning models a case study of bowen catchment queensland australia |
topic | geographic object-based image analysis (geobia) gully erosion optimal scale detection stacking model bowen catchment |
url | https://www.mdpi.com/1424-8220/19/22/4893 |
work_keys_str_mv | AT hejarshahabi asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT benjarihani asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT sepidehtavakkolipiralilou asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT davidchittleborough asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT mohammadtaghiavand asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT omidghorbanzadeh asemiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT hejarshahabi semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT benjarihani semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT sepidehtavakkolipiralilou semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT davidchittleborough semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT mohammadtaghiavand semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia AT omidghorbanzadeh semiautomatedobjectbasedgullynetworksdetectionusingdifferentmachinelearningmodelsacasestudyofbowencatchmentqueenslandaustralia |