Mostafa Mahdavi̇fard, Sara KAVİANİ AHANGAR, B. Feizizadeh, Khalil Valizadeh Kamran, S. Karimzadeh
{"title":"基于谷歌地球引擎SAR和光学图像分类的Qeshm红树林时空监测","authors":"Mostafa Mahdavi̇fard, Sara KAVİANİ AHANGAR, B. Feizizadeh, Khalil Valizadeh Kamran, S. Karimzadeh","doi":"10.26833/ijeg.1118542","DOIUrl":null,"url":null,"abstract":"Mangrove forests are considered one of the most complex and dynamic ecosystems facing various challenges due to anthropogenic disturbance and climate change. The excessive harvesting and land-use change in areas covered by mangrove ecosystems are critical threats for these forests. Therefore, the continuous and regular monitoring of these forests is essential. Fortunately, remote sensing data has made it possible to regularly and frequently monitor this type of forest. This study has two goals. Firstly, it combines optical data of Landsat- 8 and Sentinel-2 with Sentinel-1 radar data to improve land cover mapping accuracy. Secondly, it aims to evaluate the SVM machine learning algorithms and random forest to detection and differentiate forest cover from other land types in the Google Earth Engine system. The results show that the support vector machine (SVM) algorithm in the S2 + S1 dataset with a kappa coefficient of 0.94 performs significantly better than when used in the L8 + S1 combination dataset with a kappa coefficient of 0.88. On the other hand, the kappa coefficients of 0.89 and 0.85 were estimated for the random forest algorithm in S2 + S1 and L8 + S1 datasets. This again indicates the superiority of Sentinel-2 and Sentinel-1 datasets over Landsat- 8 and Sentinel-1 datasets. In general, the support vector machine (SVM) algorithm yielded better results than the RF random forest algorithm in optical and radar datasets. The results showed that the use of the Google Earth engine system and machine learning algorithms accelerates the process of mapping mangrove forests and even change detection.","PeriodicalId":42633,"journal":{"name":"International Journal of Engineering and Geosciences","volume":null,"pages":null},"PeriodicalIF":3.1000,"publicationDate":"2023-04-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Spatio-Temporal monitoring of Qeshm mangrove forests through machine learning classification of SAR and Optical images on Google Earth Engine\",\"authors\":\"Mostafa Mahdavi̇fard, Sara KAVİANİ AHANGAR, B. Feizizadeh, Khalil Valizadeh Kamran, S. Karimzadeh\",\"doi\":\"10.26833/ijeg.1118542\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"Mangrove forests are considered one of the most complex and dynamic ecosystems facing various challenges due to anthropogenic disturbance and climate change. The excessive harvesting and land-use change in areas covered by mangrove ecosystems are critical threats for these forests. Therefore, the continuous and regular monitoring of these forests is essential. Fortunately, remote sensing data has made it possible to regularly and frequently monitor this type of forest. This study has two goals. Firstly, it combines optical data of Landsat- 8 and Sentinel-2 with Sentinel-1 radar data to improve land cover mapping accuracy. Secondly, it aims to evaluate the SVM machine learning algorithms and random forest to detection and differentiate forest cover from other land types in the Google Earth Engine system. The results show that the support vector machine (SVM) algorithm in the S2 + S1 dataset with a kappa coefficient of 0.94 performs significantly better than when used in the L8 + S1 combination dataset with a kappa coefficient of 0.88. On the other hand, the kappa coefficients of 0.89 and 0.85 were estimated for the random forest algorithm in S2 + S1 and L8 + S1 datasets. This again indicates the superiority of Sentinel-2 and Sentinel-1 datasets over Landsat- 8 and Sentinel-1 datasets. In general, the support vector machine (SVM) algorithm yielded better results than the RF random forest algorithm in optical and radar datasets. The results showed that the use of the Google Earth engine system and machine learning algorithms accelerates the process of mapping mangrove forests and even change detection.\",\"PeriodicalId\":42633,\"journal\":{\"name\":\"International Journal of Engineering and Geosciences\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":3.1000,\"publicationDate\":\"2023-04-19\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"International Journal of Engineering and Geosciences\",\"FirstCategoryId\":\"1085\",\"ListUrlMain\":\"https://doi.org/10.26833/ijeg.1118542\",\"RegionNum\":0,\"RegionCategory\":null,\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q2\",\"JCRName\":\"ENGINEERING, GEOLOGICAL\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"International Journal of Engineering and Geosciences","FirstCategoryId":"1085","ListUrlMain":"https://doi.org/10.26833/ijeg.1118542","RegionNum":0,"RegionCategory":null,"ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q2","JCRName":"ENGINEERING, GEOLOGICAL","Score":null,"Total":0}
Spatio-Temporal monitoring of Qeshm mangrove forests through machine learning classification of SAR and Optical images on Google Earth Engine
Mangrove forests are considered one of the most complex and dynamic ecosystems facing various challenges due to anthropogenic disturbance and climate change. The excessive harvesting and land-use change in areas covered by mangrove ecosystems are critical threats for these forests. Therefore, the continuous and regular monitoring of these forests is essential. Fortunately, remote sensing data has made it possible to regularly and frequently monitor this type of forest. This study has two goals. Firstly, it combines optical data of Landsat- 8 and Sentinel-2 with Sentinel-1 radar data to improve land cover mapping accuracy. Secondly, it aims to evaluate the SVM machine learning algorithms and random forest to detection and differentiate forest cover from other land types in the Google Earth Engine system. The results show that the support vector machine (SVM) algorithm in the S2 + S1 dataset with a kappa coefficient of 0.94 performs significantly better than when used in the L8 + S1 combination dataset with a kappa coefficient of 0.88. On the other hand, the kappa coefficients of 0.89 and 0.85 were estimated for the random forest algorithm in S2 + S1 and L8 + S1 datasets. This again indicates the superiority of Sentinel-2 and Sentinel-1 datasets over Landsat- 8 and Sentinel-1 datasets. In general, the support vector machine (SVM) algorithm yielded better results than the RF random forest algorithm in optical and radar datasets. The results showed that the use of the Google Earth engine system and machine learning algorithms accelerates the process of mapping mangrove forests and even change detection.