Weathering assessment approach for building sandstone using hyperspectral imaging technique
Abstract Weathering is one of the most common causes of building sandstone damage. The evolution of building sandstone in various weathering behaviors is critical for research. An intelligent assessment approach for classifying weathering degree of building sandstone in a humid environment is presen...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
SpringerOpen
2023-04-01
|
| Series: | Heritage Science |
| Subjects: | |
| Online Access: | https://doi.org/10.1186/s40494-023-00914-7 |
| _version_ | 1797849934944272384 |
|---|---|
| author | Haiqing Yang Jianghua Ni Chiwei Chen Ying Chen |
| author_facet | Haiqing Yang Jianghua Ni Chiwei Chen Ying Chen |
| author_sort | Haiqing Yang |
| collection | DOAJ |
| description | Abstract Weathering is one of the most common causes of building sandstone damage. The evolution of building sandstone in various weathering behaviors is critical for research. An intelligent assessment approach for classifying weathering degree of building sandstone in a humid environment is presented in this study. This synthesis method relates to three parts: microscopic observation of weathering characteristics, hyperspectral acquisition of weathered samples, and machine learning technology for a classification model. At first, weathering process is divided into initial weathered stage, accelerated weathered stage, and stable weathered stage according to the causes and mechanisms of weathering. Secondly, a novel classification method of weathering degree is proposed based on the weathering stage. Then, the mapping relationship between microscopic characteristics and hyperspectral image of shedding samples can be established in the visible and near-infrared spectral ranges (400–1000 nm) according to the change law of spectral absorption feature. Next, the spectral data of building sandstone with different weathering degrees are classified using Random Forest model. Furthermore, the hyperparameters of Random Forest model are optimized by Gray Wolf Optimizer algorithm for better performance. The trained model is finally applied to evaluate the weathering degree of large-scale sandstone walls quantitatively. The whole weathering assessment process is worth recommending for diagnosing and monitoring the building sandstone. |
| first_indexed | 2024-04-09T18:53:19Z |
| format | Article |
| id | doaj.art-e8b208fe457b42779207dac8095cc8df |
| institution | Directory Open Access Journal |
| issn | 2050-7445 |
| language | English |
| last_indexed | 2024-04-09T18:53:19Z |
| publishDate | 2023-04-01 |
| publisher | SpringerOpen |
| record_format | Article |
| series | Heritage Science |
| spelling | doaj.art-e8b208fe457b42779207dac8095cc8df2023-04-09T11:24:01ZengSpringerOpenHeritage Science2050-74452023-04-0111111810.1186/s40494-023-00914-7Weathering assessment approach for building sandstone using hyperspectral imaging techniqueHaiqing Yang0Jianghua Ni1Chiwei Chen2Ying Chen3State Key Laboratory of Coal Mine Disaster Dynamics and Control, School of Civil Engineering, Chongqing UniversityState Key Laboratory of Coal Mine Disaster Dynamics and Control, School of Civil Engineering, Chongqing UniversityState Key Laboratory of Coal Mine Disaster Dynamics and Control, School of Civil Engineering, Chongqing UniversityChongqing Academy of GovernanceAbstract Weathering is one of the most common causes of building sandstone damage. The evolution of building sandstone in various weathering behaviors is critical for research. An intelligent assessment approach for classifying weathering degree of building sandstone in a humid environment is presented in this study. This synthesis method relates to three parts: microscopic observation of weathering characteristics, hyperspectral acquisition of weathered samples, and machine learning technology for a classification model. At first, weathering process is divided into initial weathered stage, accelerated weathered stage, and stable weathered stage according to the causes and mechanisms of weathering. Secondly, a novel classification method of weathering degree is proposed based on the weathering stage. Then, the mapping relationship between microscopic characteristics and hyperspectral image of shedding samples can be established in the visible and near-infrared spectral ranges (400–1000 nm) according to the change law of spectral absorption feature. Next, the spectral data of building sandstone with different weathering degrees are classified using Random Forest model. Furthermore, the hyperparameters of Random Forest model are optimized by Gray Wolf Optimizer algorithm for better performance. The trained model is finally applied to evaluate the weathering degree of large-scale sandstone walls quantitatively. The whole weathering assessment process is worth recommending for diagnosing and monitoring the building sandstone.https://doi.org/10.1186/s40494-023-00914-7Building sandstoneWeathering assessment modelHyperspectral imagingMicroscopic observationMachine learning |
| spellingShingle | Haiqing Yang Jianghua Ni Chiwei Chen Ying Chen Weathering assessment approach for building sandstone using hyperspectral imaging technique Heritage Science Building sandstone Weathering assessment model Hyperspectral imaging Microscopic observation Machine learning |
| title | Weathering assessment approach for building sandstone using hyperspectral imaging technique |
| title_full | Weathering assessment approach for building sandstone using hyperspectral imaging technique |
| title_fullStr | Weathering assessment approach for building sandstone using hyperspectral imaging technique |
| title_full_unstemmed | Weathering assessment approach for building sandstone using hyperspectral imaging technique |
| title_short | Weathering assessment approach for building sandstone using hyperspectral imaging technique |
| title_sort | weathering assessment approach for building sandstone using hyperspectral imaging technique |
| topic | Building sandstone Weathering assessment model Hyperspectral imaging Microscopic observation Machine learning |
| url | https://doi.org/10.1186/s40494-023-00914-7 |
| work_keys_str_mv | AT haiqingyang weatheringassessmentapproachforbuildingsandstoneusinghyperspectralimagingtechnique AT jianghuani weatheringassessmentapproachforbuildingsandstoneusinghyperspectralimagingtechnique AT chiweichen weatheringassessmentapproachforbuildingsandstoneusinghyperspectralimagingtechnique AT yingchen weatheringassessmentapproachforbuildingsandstoneusinghyperspectralimagingtechnique |