Pub Date : 2023-02-24DOI: 10.48550/arXiv.2302.12591
V. Zahs, K. Anders, Julia Kohns, Alexander Stark, B. Höfle
Automatic damage assessment based on UAV-derived 3D point clouds can provide fast information on the damage situation after an earthquake. However, the assessment of multiple damage grades is challenging due to the variety in damage patterns and limited transferability of existing methods to other geographic regions or data sources. We present a novel approach to automatically assess multi-class building damage from real-world multi-temporal point clouds using a machine learning model trained on virtual laser scanning (VLS) data. We (1) identify object-specific change features, (2) separate changed and unchanged building parts, (3) train a random forest machine learning model with VLS data based on object-specific change features, and (4) use the classifier to assess building damage in real-world point clouds from photogrammetry-based dense image matching (DIM). We evaluate classifiers trained on different input data with respect to their capacity to classify three damage grades (heavy, extreme, destruction) in pre- and post-event DIM point clouds of a real earthquake event. Our approach is transferable with respect to multi-source input point clouds used for training (VLS) and application (DIM) of the model. We further achieve geographic transferability of the model by training it on simulated data of geometric change which characterises relevant damage grades across different geographic regions. The model yields high multi-target classification accuracies (overall accuracy: 92.0% - 95.1%). Its performance improves only slightly when using real-world region-specific training data (<3% higher overall accuracies) and when using real-world region-specific training data (<2% higher overall accuracies). We consider our approach relevant for applications where timely information on the damage situation is required and sufficient real-world training data is not available.
{"title":"Classification of structural building damage grades from multi-temporal photogrammetric point clouds using a machine learning model trained on virtual laser scanning data","authors":"V. Zahs, K. Anders, Julia Kohns, Alexander Stark, B. Höfle","doi":"10.48550/arXiv.2302.12591","DOIUrl":"https://doi.org/10.48550/arXiv.2302.12591","url":null,"abstract":"Automatic damage assessment based on UAV-derived 3D point clouds can provide fast information on the damage situation after an earthquake. However, the assessment of multiple damage grades is challenging due to the variety in damage patterns and limited transferability of existing methods to other geographic regions or data sources. We present a novel approach to automatically assess multi-class building damage from real-world multi-temporal point clouds using a machine learning model trained on virtual laser scanning (VLS) data. We (1) identify object-specific change features, (2) separate changed and unchanged building parts, (3) train a random forest machine learning model with VLS data based on object-specific change features, and (4) use the classifier to assess building damage in real-world point clouds from photogrammetry-based dense image matching (DIM). We evaluate classifiers trained on different input data with respect to their capacity to classify three damage grades (heavy, extreme, destruction) in pre- and post-event DIM point clouds of a real earthquake event. Our approach is transferable with respect to multi-source input point clouds used for training (VLS) and application (DIM) of the model. We further achieve geographic transferability of the model by training it on simulated data of geometric change which characterises relevant damage grades across different geographic regions. The model yields high multi-target classification accuracies (overall accuracy: 92.0% - 95.1%). Its performance improves only slightly when using real-world region-specific training data (<3% higher overall accuracies) and when using real-world region-specific training data (<2% higher overall accuracies). We consider our approach relevant for applications where timely information on the damage situation is required and sufficient real-world training data is not available.","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"79015399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2023-02-03DOI: 10.48550/arXiv.2302.01526
Shin-nosuke Ishikawa, Masato Todo, M. Taki, Y. Uchiyama, Kazunari Matsunaga, Pei-Ru Lin, Taiki Ogihara, Masao Yasui
We present a method of explainable artificial intelligence (XAI),"What I Know (WIK)", to provide additional information to verify the reliability of a deep learning model by showing an example of an instance in a training dataset that is similar to the input data to be inferred and demonstrate it in a remote sensing image classification task. One of the expected roles of XAI methods is verifying whether inferences of a trained machine learning model are valid for an application, and it is an important factor that what datasets are used for training the model as well as the model architecture. Our data-centric approach can help determine whether the training dataset is sufficient for each inference by checking the selected example data. If the selected example looks similar to the input data, we can confirm that the model was not trained on a dataset with a feature distribution far from the feature of the input data. With this method, the criteria for selecting an example are not merely data similarity with the input data but also data similarity in the context of the model task. Using a remote sensing image dataset from the Sentinel-2 satellite, the concept was successfully demonstrated with reasonably selected examples. This method can be applied to various machine-learning tasks, including classification and regression.
我们提出了一种可解释的人工智能(XAI)方法，“What I Know (WIK)”，通过展示训练数据集中的实例示例来提供额外的信息来验证深度学习模型的可靠性，该示例与要推断的输入数据相似，并在遥感图像分类任务中进行演示。XAI方法的预期角色之一是验证经过训练的机器学习模型的推断是否对应用程序有效，并且使用哪些数据集来训练模型以及模型体系结构是一个重要因素。我们以数据为中心的方法可以通过检查选定的示例数据来帮助确定训练数据集是否足以进行每个推理。如果选择的示例看起来与输入数据相似，我们可以确认模型不是在特征分布远离输入数据特征的数据集上训练的。使用这种方法，选择示例的标准不仅是与输入数据的数据相似度，还包括模型任务上下文中的数据相似度。利用Sentinel-2卫星的遥感图像数据集，通过合理选择的示例成功地演示了该概念。这种方法可以应用于各种机器学习任务，包括分类和回归。
{"title":"Example-Based Explainable AI and its Application for Remote Sensing Image Classification","authors":"Shin-nosuke Ishikawa, Masato Todo, M. Taki, Y. Uchiyama, Kazunari Matsunaga, Pei-Ru Lin, Taiki Ogihara, Masao Yasui","doi":"10.48550/arXiv.2302.01526","DOIUrl":"https://doi.org/10.48550/arXiv.2302.01526","url":null,"abstract":"We present a method of explainable artificial intelligence (XAI),\"What I Know (WIK)\", to provide additional information to verify the reliability of a deep learning model by showing an example of an instance in a training dataset that is similar to the input data to be inferred and demonstrate it in a remote sensing image classification task. One of the expected roles of XAI methods is verifying whether inferences of a trained machine learning model are valid for an application, and it is an important factor that what datasets are used for training the model as well as the model architecture. Our data-centric approach can help determine whether the training dataset is sufficient for each inference by checking the selected example data. If the selected example looks similar to the input data, we can confirm that the model was not trained on a dataset with a feature distribution far from the feature of the input data. With this method, the criteria for selecting an example are not merely data similarity with the input data but also data similarity in the context of the model task. Using a remote sensing image dataset from the Sentinel-2 satellite, the concept was successfully demonstrated with reasonably selected examples. This method can be applied to various machine-learning tasks, including classification and regression.","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-03","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76655502","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Yi Lian, Haixiao Li, Qianqian Renyang, Le Liu, Jiankang Dong, Xiaoning Liu, Zihan Qu, Lien-Chieh Lee, Lei Chen, Dongliang Wang, Hu Zhang
{"title":"Mapping the net ecosystem exchange of CO2 of global terrestrial systems","authors":"Yi Lian, Haixiao Li, Qianqian Renyang, Le Liu, Jiankang Dong, Xiaoning Liu, Zihan Qu, Lien-Chieh Lee, Lei Chen, Dongliang Wang, Hu Zhang","doi":"10.2139/ssrn.4058420","DOIUrl":"https://doi.org/10.2139/ssrn.4058420","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2023-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"76095879","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1016/j.jag.2022.103108
Yuri Shendryk
{"title":"Fusing GEDI with earth observation data for large area aboveground biomass mapping","authors":"Yuri Shendryk","doi":"10.1016/j.jag.2022.103108","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103108","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"74601415","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1016/j.jag.2022.103099
Ru Wang, Mengshi Yang, Jiefang Dong, M. Liao
{"title":"Investigating deformation along metro lines in coastal cities considering different structures with InSAR and SBM analyses","authors":"Ru Wang, Mengshi Yang, Jiefang Dong, M. Liao","doi":"10.1016/j.jag.2022.103099","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103099","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"91478636","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1016/j.jag.2022.103102
N. Málaga, S. Bruin, R. McRoberts, Alexs Arana Olivos, R. Paiva, Patricia Durán Montesinos, Daniela Requena Suarez, M. Herold
{"title":"Precision of subnational forest AGB estimates within the Peruvian Amazonia using a global biomass map","authors":"N. Málaga, S. Bruin, R. McRoberts, Alexs Arana Olivos, R. Paiva, Patricia Durán Montesinos, Daniela Requena Suarez, M. Herold","doi":"10.1016/j.jag.2022.103102","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103102","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81693375","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
{"title":"Extreme rainfall-related accelerations in landslides in Danba County, Sichuan Province, as detected by InSAR","authors":"Xuguo Shi, Jianing Wang, M. Jiang, Shaocheng Zhang, Yunlong Wu, Yulong Zhong","doi":"10.1016/j.jag.2022.103109","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103109","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"81532298","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1016/j.jag.2022.103101
Yanxi Li, R. Chen, Bin He, S. Veraverbeke
{"title":"Forest foliage fuel load estimation from multi-sensor spatiotemporal features","authors":"Yanxi Li, R. Chen, Bin He, S. Veraverbeke","doi":"10.1016/j.jag.2022.103101","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103101","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"78753265","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2022-12-01DOI: 10.1016/j.jag.2022.103104
Karel Kuželka, R. Marušák, P. Surový
{"title":"Inventory of close-to-nature forest stands using terrestrial mobile laser scanning","authors":"Karel Kuželka, R. Marušák, P. Surový","doi":"10.1016/j.jag.2022.103104","DOIUrl":"https://doi.org/10.1016/j.jag.2022.103104","url":null,"abstract":"","PeriodicalId":13664,"journal":{"name":"Int. J. Appl. Earth Obs. Geoinformation","volume":null,"pages":null},"PeriodicalIF":0.0,"publicationDate":"2022-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"80046935","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：