the Creative Commons Attribution 4.0 License.
the Creative Commons Attribution 4.0 License.
Comparison of machine learning classification algorithms for land cover change in a coastal area affected by the 2010 Earthquake and Tsunami in Chile
Abstract. Earthquakes and tsunamis are the natural events that generate subsequent geomorphological land cover changes. The damage is usually of such importance and of such a diverse nature that it is imperative to have tools that allow quick and precise monitoring. Thus, know which classification methods have the best potential to obtain greater precision will improve natural disaster management. We analyze Tubul locality (37.21º S; 73.43º O) in Biobío region, Chile, in which greatest geomorphological changes were documented after the earthquake and tsunami occurred 27/February/2010. These changes can be analyzed using different machine learning methods. We investigate the Support Vector Machine
(SVM) and Random Forest
(RF), versus the Maximum Likelihood
(ML) classification method of Landsat TM and ASTER satellite images. The comparison of the performance of the classifiers and certifying accuracy improvement shows that machine learning algorithms are superior to traditional classification methods in terms of overall accuracy and robustness. The general classification accuracy was approximately 97 %. We also visualize the land cover transformations, showing that 26 % of the region was altered. The results of performance testing of machine learning methodologies was consistent with other studies and presents a valid application in the visualization of land cover changes in areas of natural disasters.
- Preprint
(1084 KB) - Metadata XML
- BibTeX
- EndNote
-
RC1: 'comments to the authors', Anonymous Referee #1, 24 Apr 2020
- AC1: 'considerations about training samples and classifiers', matias volke, 19 May 2020
- AC3: 'the novelty of the work is limited or unclear.', matias volke, 02 Jul 2020
- AC4: 'Page 8, Figure 3: 1- I do not understand the reason for using both Landsat and ASTER images? Does it add any further information?', matias volke, 02 Jul 2020
- AC5: '2- Considering that the time difference between the Landsat and ASTER images is one-two weeks, please explain the reason for the differences between the thematic maps (I-A with II-A and I-B with II-B).', matias volke, 02 Jul 2020
- AC6: '3- As the title of the manuscript is a comparison of the machine learning methods, I suggest adding the thematic maps created by applying the RF method. And compare the results in more detail.', matias volke, 02 Jul 2020
-
RC2: 'Comparison of machine learning classification algorithms for land cover change in a coastal area affected by the 2010 Earthquake and Tsunami in Chile.', Anonymous Referee #2, 28 Apr 2020
- AC1: 'considerations about training samples and classifiers', matias volke, 19 May 2020
- AC8: 'The authors could investigate many more classifiers to make more comprehensive conclusions', matias volke, 03 Jul 2020
- AC9: 'it is necessary to iterate the classifiers at least 10 times and report the mean and standard deviation values to avoid any biases induced in the training data.', matias volke, 03 Jul 2020
-
RC3: 'nhess-2020-41', Anonymous Referee #3, 10 May 2020
- AC2: 'considerations about classifiers', matias volke, 19 May 2020
- AC10: 'The research question in this manuscript is not much meaningful.', matias volke, 03 Jul 2020
- AC11: 'would suggest comparing the performance of RF and SVM with the more recently proposed approaches, including XGBosst and CNN algorithms.', matias volke, 03 Jul 2020
- AC7: '4- Please add some signs or vectors in the map, so that the interpretation provided in page 9 becomes more understandable.', matias volke, 02 Jul 2020
-
RC1: 'comments to the authors', Anonymous Referee #1, 24 Apr 2020
- AC1: 'considerations about training samples and classifiers', matias volke, 19 May 2020
- AC3: 'the novelty of the work is limited or unclear.', matias volke, 02 Jul 2020
- AC4: 'Page 8, Figure 3: 1- I do not understand the reason for using both Landsat and ASTER images? Does it add any further information?', matias volke, 02 Jul 2020
- AC5: '2- Considering that the time difference between the Landsat and ASTER images is one-two weeks, please explain the reason for the differences between the thematic maps (I-A with II-A and I-B with II-B).', matias volke, 02 Jul 2020
- AC6: '3- As the title of the manuscript is a comparison of the machine learning methods, I suggest adding the thematic maps created by applying the RF method. And compare the results in more detail.', matias volke, 02 Jul 2020
-
RC2: 'Comparison of machine learning classification algorithms for land cover change in a coastal area affected by the 2010 Earthquake and Tsunami in Chile.', Anonymous Referee #2, 28 Apr 2020
- AC1: 'considerations about training samples and classifiers', matias volke, 19 May 2020
- AC8: 'The authors could investigate many more classifiers to make more comprehensive conclusions', matias volke, 03 Jul 2020
- AC9: 'it is necessary to iterate the classifiers at least 10 times and report the mean and standard deviation values to avoid any biases induced in the training data.', matias volke, 03 Jul 2020
-
RC3: 'nhess-2020-41', Anonymous Referee #3, 10 May 2020
- AC2: 'considerations about classifiers', matias volke, 19 May 2020
- AC10: 'The research question in this manuscript is not much meaningful.', matias volke, 03 Jul 2020
- AC11: 'would suggest comparing the performance of RF and SVM with the more recently proposed approaches, including XGBosst and CNN algorithms.', matias volke, 03 Jul 2020
- AC7: '4- Please add some signs or vectors in the map, so that the interpretation provided in page 9 becomes more understandable.', matias volke, 02 Jul 2020
Viewed
HTML | XML | Total | BibTeX | EndNote | |
---|---|---|---|---|---|
922 | 499 | 71 | 1,492 | 76 | 99 |
- HTML: 922
- PDF: 499
- XML: 71
- Total: 1,492
- BibTeX: 76
- EndNote: 99
Viewed (geographical distribution)
Country | # | Views | % |
---|
Total: | 0 |
HTML: | 0 |
PDF: | 0 |
XML: | 0 |
- 1
Cited
3 citations as recorded by crossref.
- Comparative analysis of the performance of selected machine learning algorithms depending on the size of the training sample P. Kupidura et al. 10.2478/rgg-2024-0015
- Classification of the Land Cover of a Megacity in ASEAN Using Two Band Combinations and Three Machine Learning Algorithms: A Case Study in Ho Chi Minh City C. Huang et al. 10.3390/su15086798
- Land cover object change monitoring and environmental suitability confirmation in Cat Ba Biosphere Reserve of Vietnam L. Hue et al. 10.1080/14888386.2024.2385975