Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data
The all-weather high-resolution air temperature data is crucial for understanding the urban thermal conditions with their spatio-temporal characteristics, driving factors, socio-economic and environmental consequences. In this study, we developed a novel 5-layer Deep Belief Network (DBN) deep learni...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3536 |
| _version_ | 1797412490869473280 |
|---|---|
| author | Xiang Zhang Tailai Huang Aminjon Gulakhmadov Yu Song Xihui Gu Jiangyuan Zeng Shuzhe Huang Won-Ho Nam Nengcheng Chen Dev Niyogi |
| author_facet | Xiang Zhang Tailai Huang Aminjon Gulakhmadov Yu Song Xihui Gu Jiangyuan Zeng Shuzhe Huang Won-Ho Nam Nengcheng Chen Dev Niyogi |
| author_sort | Xiang Zhang |
| collection | DOAJ |
| description | The all-weather high-resolution air temperature data is crucial for understanding the urban thermal conditions with their spatio-temporal characteristics, driving factors, socio-economic and environmental consequences. In this study, we developed a novel 5-layer Deep Belief Network (DBN) deep learning model to fuse multi-source data and then generated air temperature data with 3H characteristics: High resolution, High spatio-temporal continuity (spatially seamless and temporally continuous), and High accuracy simultaneously. The DBN model was developed and applied for two different urban regions: Wuhan Metropolitan Area (WMA) in China, and Austin, Texas, USA. The model has a excellent ability to fit the complex nonlinear relationship between temperature and different predictive variables. After various adjustments to the model structure and different combinations of input variables, the daily 500-m air temperature in Wuhan Metropolitan Area (WMA) was initially generated by fusing remote sensing, reanalysis and in situ measurement products. The ten-fold cross-validation results indicated that the DBN model achieved promising results with the RMSE of 1.086 °C, MAE of 0.839 °C, and R<sup>2</sup> of 0.986. Compared with conventional data fusion algorithms, the DBN model also exhibited better performance. In addition, the detailed evaluation of the model on spatial and temporal scales proved the advantages of using DBN model to generate 3H temperature data. The spatial transferability of the model was tested by conducting a validation experiment for Austin, USA. In general, the results and fine-scale analyses show that the employed framework is effective to generate 3H temperature, which is valuable for urban climate and urban heat island research. |
| first_indexed | 2024-03-09T05:03:24Z |
| format | Article |
| id | doaj.art-6c6a630f37dc40c6a2c91c9c05cd9aab |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:03:24Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6c6a630f37dc40c6a2c91c9c05cd9aab2023-12-03T12:57:36ZengMDPI AGRemote Sensing2072-42922022-07-011415353610.3390/rs14153536Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source DataXiang Zhang0Tailai Huang1Aminjon Gulakhmadov2Yu Song3Xihui Gu4Jiangyuan Zeng5Shuzhe Huang6Won-Ho Nam7Nengcheng Chen8Dev Niyogi9National Engineering Research Center of Geographic Information System, School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaNational Engineering Research Center of Geographic Information System, School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaResearch Center of Ecology and Environment in Central Asia, Xinjiang Institute of Ecology and Geography, Chinese Academy of Sciences, Urumqi 830011, ChinaNational Engineering Research Center of Geographic Information System, School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaDepartment of Atmospheric Science, School of Environmental Studies, China University of Geosciences, Wuhan 430074, ChinaState Key Laboratory of Remote Sensing Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Information Engineering in Surveying, Mapping, and Remote Sensing (LIESMARS), Wuhan University, Wuhan 430079, ChinaSchool of Social Safety and Systems Engineering, Institute of Agricultural Environmental Science, National Agricultural Water Research Center, Hankyong National University, 327 Jungang-ro, Anseong-si 17579, KoreaNational Engineering Research Center of Geographic Information System, School of Geography and Information Engineering, China University of Geosciences, Wuhan 430074, ChinaDepartment of Geological Sciences, Jackson School of Geosciences, University of Texas at Austin, Austin, TX 78712, USAThe all-weather high-resolution air temperature data is crucial for understanding the urban thermal conditions with their spatio-temporal characteristics, driving factors, socio-economic and environmental consequences. In this study, we developed a novel 5-layer Deep Belief Network (DBN) deep learning model to fuse multi-source data and then generated air temperature data with 3H characteristics: High resolution, High spatio-temporal continuity (spatially seamless and temporally continuous), and High accuracy simultaneously. The DBN model was developed and applied for two different urban regions: Wuhan Metropolitan Area (WMA) in China, and Austin, Texas, USA. The model has a excellent ability to fit the complex nonlinear relationship between temperature and different predictive variables. After various adjustments to the model structure and different combinations of input variables, the daily 500-m air temperature in Wuhan Metropolitan Area (WMA) was initially generated by fusing remote sensing, reanalysis and in situ measurement products. The ten-fold cross-validation results indicated that the DBN model achieved promising results with the RMSE of 1.086 °C, MAE of 0.839 °C, and R<sup>2</sup> of 0.986. Compared with conventional data fusion algorithms, the DBN model also exhibited better performance. In addition, the detailed evaluation of the model on spatial and temporal scales proved the advantages of using DBN model to generate 3H temperature data. The spatial transferability of the model was tested by conducting a validation experiment for Austin, USA. In general, the results and fine-scale analyses show that the employed framework is effective to generate 3H temperature, which is valuable for urban climate and urban heat island research.https://www.mdpi.com/2072-4292/14/15/3536air temperaturedata fusiondeep learningWuhan Metropolitan AreaAustin, Texas |
| spellingShingle | Xiang Zhang Tailai Huang Aminjon Gulakhmadov Yu Song Xihui Gu Jiangyuan Zeng Shuzhe Huang Won-Ho Nam Nengcheng Chen Dev Niyogi Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data Remote Sensing air temperature data fusion deep learning Wuhan Metropolitan Area Austin, Texas |
| title | Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data |
| title_full | Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data |
| title_fullStr | Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data |
| title_full_unstemmed | Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data |
| title_short | Deep Learning-Based 500 m Spatio-Temporally Continuous Air Temperature Generation by Fusing Multi-Source Data |
| title_sort | deep learning based 500 m spatio temporally continuous air temperature generation by fusing multi source data |
| topic | air temperature data fusion deep learning Wuhan Metropolitan Area Austin, Texas |
| url | https://www.mdpi.com/2072-4292/14/15/3536 |
| work_keys_str_mv | AT xiangzhang deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT tailaihuang deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT aminjongulakhmadov deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT yusong deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT xihuigu deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT jiangyuanzeng deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT shuzhehuang deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT wonhonam deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT nengchengchen deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata AT devniyogi deeplearningbased500mspatiotemporallycontinuousairtemperaturegenerationbyfusingmultisourcedata |