Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI)
Urban vegetation mapping is critical in many applications, i.e., preserving biodiversity, maintaining ecological balance, and minimizing the urban heat island effect. It is still challenging to extract accurate vegetation covers from aerial imagery using traditional classification approaches, becaus...
Saved in:
| Main Authors: | , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-07-01
|
| Series: | Sensors |
| Subjects: | |
| Online Access: | https://www.mdpi.com/1424-8220/21/14/4738 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1832575955414024192 |
|---|---|
| author | Arnick Abdollahi Biswajeet Pradhan |
| author_facet | Arnick Abdollahi Biswajeet Pradhan |
| author_sort | Arnick Abdollahi |
| collection | DOAJ |
| description | Urban vegetation mapping is critical in many applications, i.e., preserving biodiversity, maintaining ecological balance, and minimizing the urban heat island effect. It is still challenging to extract accurate vegetation covers from aerial imagery using traditional classification approaches, because urban vegetation categories have complex spatial structures and similar spectral properties. Deep neural networks (DNNs) have shown a significant improvement in remote sensing image classification outcomes during the last few years. These methods are promising in this domain, yet unreliable for various reasons, such as the use of irrelevant descriptor features in the building of the models and lack of quality in the labeled image. Explainable AI (XAI) can help us gain insight into these limits and, as a result, adjust the training dataset and model as needed. Thus, in this work, we explain how an explanation model called Shapley additive explanations (SHAP) can be utilized for interpreting the output of the DNN model that is designed for classifying vegetation covers. We want to not only produce high-quality vegetation maps, but also rank the input parameters and select appropriate features for classification. Therefore, we test our method on vegetation mapping from aerial imagery based on spectral and textural features. Texture features can help overcome the limitations of poor spectral resolution in aerial imagery for vegetation mapping. The model was capable of obtaining an overall accuracy (OA) of 94.44% for vegetation cover mapping. The conclusions derived from SHAP plots demonstrate the high contribution of features, such as Hue, Brightness, GLCM_Dissimilarity, GLCM_Homogeneity, and GLCM_Mean to the output of the proposed model for vegetation mapping. Therefore, the study indicates that existing vegetation mapping strategies based only on spectral characteristics are insufficient to appropriately classify vegetation covers. |
| format | Article |
| id | doaj-art-4ac5a76dd06944218d414b750af4c9d5 |
| institution | Kabale University |
| issn | 1424-8220 |
| language | English |
| publishDate | 2021-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Sensors |
| spelling | doaj-art-4ac5a76dd06944218d414b750af4c9d52025-01-31T16:01:01ZengMDPI AGSensors1424-82202021-07-012114473810.3390/s21144738Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI)Arnick Abdollahi0Biswajeet Pradhan1Centre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW 2007, AustraliaCentre for Advanced Modelling and Geospatial Information Systems (CAMGIS), Faculty of Engineering and IT, University of Technology Sydney, Ultimo, NSW 2007, AustraliaUrban vegetation mapping is critical in many applications, i.e., preserving biodiversity, maintaining ecological balance, and minimizing the urban heat island effect. It is still challenging to extract accurate vegetation covers from aerial imagery using traditional classification approaches, because urban vegetation categories have complex spatial structures and similar spectral properties. Deep neural networks (DNNs) have shown a significant improvement in remote sensing image classification outcomes during the last few years. These methods are promising in this domain, yet unreliable for various reasons, such as the use of irrelevant descriptor features in the building of the models and lack of quality in the labeled image. Explainable AI (XAI) can help us gain insight into these limits and, as a result, adjust the training dataset and model as needed. Thus, in this work, we explain how an explanation model called Shapley additive explanations (SHAP) can be utilized for interpreting the output of the DNN model that is designed for classifying vegetation covers. We want to not only produce high-quality vegetation maps, but also rank the input parameters and select appropriate features for classification. Therefore, we test our method on vegetation mapping from aerial imagery based on spectral and textural features. Texture features can help overcome the limitations of poor spectral resolution in aerial imagery for vegetation mapping. The model was capable of obtaining an overall accuracy (OA) of 94.44% for vegetation cover mapping. The conclusions derived from SHAP plots demonstrate the high contribution of features, such as Hue, Brightness, GLCM_Dissimilarity, GLCM_Homogeneity, and GLCM_Mean to the output of the proposed model for vegetation mapping. Therefore, the study indicates that existing vegetation mapping strategies based only on spectral characteristics are insufficient to appropriately classify vegetation covers.https://www.mdpi.com/1424-8220/21/14/4738XAIdeep neural networkremote sensingSHAPvegetation mapping |
| spellingShingle | Arnick Abdollahi Biswajeet Pradhan Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) Sensors XAI deep neural network remote sensing SHAP vegetation mapping |
| title | Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) |
| title_full | Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) |
| title_fullStr | Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) |
| title_full_unstemmed | Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) |
| title_short | Urban Vegetation Mapping from Aerial Imagery Using Explainable AI (XAI) |
| title_sort | urban vegetation mapping from aerial imagery using explainable ai xai |
| topic | XAI deep neural network remote sensing SHAP vegetation mapping |
| url | https://www.mdpi.com/1424-8220/21/14/4738 |
| work_keys_str_mv | AT arnickabdollahi urbanvegetationmappingfromaerialimageryusingexplainableaixai AT biswajeetpradhan urbanvegetationmappingfromaerialimageryusingexplainableaixai |