Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine
Accurate mapping of built-up land is essential for urbanization monitoring and ecosystem research. At present, remote sensing is one of the primary means used for real-time and accurate surveying and mapping of built-up land, due to the long time series and multi-information advantages of existing r...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/15/3562 |
| _version_ | 1827601758674747392 |
|---|---|
| author | Han Xu Xiangming Xiao Yuanwei Qin Zhi Qiao Shaoqiu Long Xianzhe Tang Luo Liu |
| author_facet | Han Xu Xiangming Xiao Yuanwei Qin Zhi Qiao Shaoqiu Long Xianzhe Tang Luo Liu |
| author_sort | Han Xu |
| collection | DOAJ |
| description | Accurate mapping of built-up land is essential for urbanization monitoring and ecosystem research. At present, remote sensing is one of the primary means used for real-time and accurate surveying and mapping of built-up land, due to the long time series and multi-information advantages of existing remote sensing images and the ability to obtain highly precise year-by-year built-up land maps. In this study, we obtained feature-enhanced data regarding built-up land from Landsat images and phenology-based algorithms and proposed a method that combines the use of the Google Earth Engine (GEE) and deep learning approaches. The Res-UNet++ structural model was improved for built-up land mapping in Guangdong from 1991 to 2020. Experiments show that overall accuracy of built-up land map in the study area in 2020 was 0.99, the kappa coefficient was 0.96, user accuracy of built-up land was 0.98, and producer accuracy was 0.901. The trained model can be applied to other years with good results. The overall accuracy (OA) of the assessment results every five years was above 0.97, and the kappa coefficient was above 0.90. From 1991 to 2020, built-up land in Guangdong has expanded significantly, the area of built-up land has increased by 71%, and the proportion of built-up land has increased by 3.91%. Our findings indicate that the combined approach of GEE and deep learning algorithms can be developed into a large-scale, long time-series of remote sensing classification techniques framework that can be useful for future land-use mapping research. |
| first_indexed | 2024-03-09T05:02:54Z |
| format | Article |
| id | doaj.art-6218c2997d3e4dc282f02e4ab257a5a9 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T05:02:54Z |
| publishDate | 2022-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-6218c2997d3e4dc282f02e4ab257a5a92023-12-03T12:57:47ZengMDPI AGRemote Sensing2072-42922022-07-011415356210.3390/rs14153562Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth EngineHan Xu0Xiangming Xiao1Yuanwei Qin2Zhi Qiao3Shaoqiu Long4Xianzhe Tang5Luo Liu6College of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, ChinaDepartment of Microbiology and Plant Biology, University of Oklahoma, Norman, OK 73019, USADepartment of Microbiology and Plant Biology, University of Oklahoma, Norman, OK 73019, USAKey Laboratory of Indoor Air Environment Quality Control, School of Environmental Science and Engineering, Tianjin University, Tianjin 300350, ChinaCollege of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, ChinaCollege of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, ChinaCollege of Natural Resources and Environment, South China Agricultural University, Guangzhou 510642, ChinaAccurate mapping of built-up land is essential for urbanization monitoring and ecosystem research. At present, remote sensing is one of the primary means used for real-time and accurate surveying and mapping of built-up land, due to the long time series and multi-information advantages of existing remote sensing images and the ability to obtain highly precise year-by-year built-up land maps. In this study, we obtained feature-enhanced data regarding built-up land from Landsat images and phenology-based algorithms and proposed a method that combines the use of the Google Earth Engine (GEE) and deep learning approaches. The Res-UNet++ structural model was improved for built-up land mapping in Guangdong from 1991 to 2020. Experiments show that overall accuracy of built-up land map in the study area in 2020 was 0.99, the kappa coefficient was 0.96, user accuracy of built-up land was 0.98, and producer accuracy was 0.901. The trained model can be applied to other years with good results. The overall accuracy (OA) of the assessment results every five years was above 0.97, and the kappa coefficient was above 0.90. From 1991 to 2020, built-up land in Guangdong has expanded significantly, the area of built-up land has increased by 71%, and the proportion of built-up land has increased by 3.91%. Our findings indicate that the combined approach of GEE and deep learning algorithms can be developed into a large-scale, long time-series of remote sensing classification techniques framework that can be useful for future land-use mapping research.https://www.mdpi.com/2072-4292/14/15/3562remote sensing imagelong time-serieslarge-scalespectral analysisbuilt-up land |
| spellingShingle | Han Xu Xiangming Xiao Yuanwei Qin Zhi Qiao Shaoqiu Long Xianzhe Tang Luo Liu Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine Remote Sensing remote sensing image long time-series large-scale spectral analysis built-up land |
| title | Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine |
| title_full | Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine |
| title_fullStr | Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine |
| title_full_unstemmed | Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine |
| title_short | Annual Maps of Built-Up Land in Guangdong from 1991 to 2020 Based on Landsat Images, Phenology, Deep Learning Algorithms, and Google Earth Engine |
| title_sort | annual maps of built up land in guangdong from 1991 to 2020 based on landsat images phenology deep learning algorithms and google earth engine |
| topic | remote sensing image long time-series large-scale spectral analysis built-up land |
| url | https://www.mdpi.com/2072-4292/14/15/3562 |
| work_keys_str_mv | AT hanxu annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT xiangmingxiao annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT yuanweiqin annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT zhiqiao annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT shaoqiulong annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT xianzhetang annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine AT luoliu annualmapsofbuiltuplandinguangdongfrom1991to2020basedonlandsatimagesphenologydeeplearningalgorithmsandgoogleearthengine |