Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data
The all-wave net radiation (Rn) at the land surface represents surface radiation budget and plays an important role in the Earth's energy and water cycles. Many studies have been conducted to estimate from satellite top-of-atmosphere (TOA) data using various methods, particularly the applicatio...
| Main Authors: | , , , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Taylor & Francis Group
2022-12-01
|
| Series: | International Journal of Digital Earth |
| Subjects: | |
| Online Access: | http://dx.doi.org/10.1080/17538947.2022.2130460 |
| _version_ | 1797678509700677632 |
|---|---|
| author | Shaopeng Li Bo Jiang Shunlin Liang Jianghai Peng Hui Liang Jiakun Han Xiuwan Yin Yunjun Yao Xiaotong Zhang Jie Cheng Xiang Zhao Qiang Liu Kun Jia |
| author_facet | Shaopeng Li Bo Jiang Shunlin Liang Jianghai Peng Hui Liang Jiakun Han Xiuwan Yin Yunjun Yao Xiaotong Zhang Jie Cheng Xiang Zhao Qiang Liu Kun Jia |
| author_sort | Shaopeng Li |
| collection | DOAJ |
| description | The all-wave net radiation (Rn) at the land surface represents surface radiation budget and plays an important role in the Earth's energy and water cycles. Many studies have been conducted to estimate from satellite top-of-atmosphere (TOA) data using various methods, particularly the application of machine learning (ML) and deep learning (DL). However, few studies have been conducted to provide a comprehensive evaluation about various ML and DL methods in retrieving. Based on extensive in situ measurements distributed at mid-low latitudes, the corresponding Moderate Resolution Imaging Spectroradiometer (MODIS) TOA observations, and the daily from the fifth generation of European Centre for Medium-Range Weather Forecasts Reanalysis 5 (ERA5) used as a priori knowledge, this study assessed nine models for daily estimation, including six classic ML methods (random forest -RF, adaptive boosting - Adaboost, extreme gradient boosting -XGBoost, multilayer perceptron -MLP, radial basis function neural network -RBF, and support vector machine -SVM) and three DL methods (multilayer perceptron neural network with stacked autoencoders -SAE, deep belief network -DBN and residual neural network -ResNet). The validation results showed that the three DL methods were generally better than the six ML methods except XGBoost, although they all performed poorly in certain conditions such as winter days, rugged terrain, and high elevation. ResNet had the most robust performance across different land cover types, elevations, seasons, and latitude zones, but it has disadvantages in practice because of its highly configurable implementation environment and low computational efficiency. The estimated daily values from all nine models were more accurate than the corresponding Global LAnd Surface Satellite (GLASS) product. |
| first_indexed | 2024-03-11T23:00:49Z |
| format | Article |
| id | doaj.art-b8beb09b60ed42d19d252e864b90a647 |
| institution | Directory Open Access Journal |
| issn | 1753-8947 1753-8955 |
| language | English |
| last_indexed | 2024-03-11T23:00:49Z |
| publishDate | 2022-12-01 |
| publisher | Taylor & Francis Group |
| record_format | Article |
| series | International Journal of Digital Earth |
| spelling | doaj.art-b8beb09b60ed42d19d252e864b90a6472023-09-21T14:57:11ZengTaylor & Francis GroupInternational Journal of Digital Earth1753-89471753-89552022-12-011511784181610.1080/17538947.2022.21304602130460Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite dataShaopeng Li0Bo Jiang1Shunlin Liang2Jianghai Peng3Hui Liang4Jiakun Han5Xiuwan Yin6Yunjun Yao7Xiaotong Zhang8Jie Cheng9Xiang Zhao10Qiang Liu11Kun Jia12Jointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesUniversity of MarylandJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesJointly Sponsored by Beijing Normal University and Institute of Remote Sensing and Digital Earth of Chinese Academy of SciencesThe all-wave net radiation (Rn) at the land surface represents surface radiation budget and plays an important role in the Earth's energy and water cycles. Many studies have been conducted to estimate from satellite top-of-atmosphere (TOA) data using various methods, particularly the application of machine learning (ML) and deep learning (DL). However, few studies have been conducted to provide a comprehensive evaluation about various ML and DL methods in retrieving. Based on extensive in situ measurements distributed at mid-low latitudes, the corresponding Moderate Resolution Imaging Spectroradiometer (MODIS) TOA observations, and the daily from the fifth generation of European Centre for Medium-Range Weather Forecasts Reanalysis 5 (ERA5) used as a priori knowledge, this study assessed nine models for daily estimation, including six classic ML methods (random forest -RF, adaptive boosting - Adaboost, extreme gradient boosting -XGBoost, multilayer perceptron -MLP, radial basis function neural network -RBF, and support vector machine -SVM) and three DL methods (multilayer perceptron neural network with stacked autoencoders -SAE, deep belief network -DBN and residual neural network -ResNet). The validation results showed that the three DL methods were generally better than the six ML methods except XGBoost, although they all performed poorly in certain conditions such as winter days, rugged terrain, and high elevation. ResNet had the most robust performance across different land cover types, elevations, seasons, and latitude zones, but it has disadvantages in practice because of its highly configurable implementation environment and low computational efficiency. The estimated daily values from all nine models were more accurate than the corresponding Global LAnd Surface Satellite (GLASS) product.http://dx.doi.org/10.1080/17538947.2022.2130460net radiationenergy balancemid-low latitudemodel comparisonmachine learningdeep learningmodisera5 |
| spellingShingle | Shaopeng Li Bo Jiang Shunlin Liang Jianghai Peng Hui Liang Jiakun Han Xiuwan Yin Yunjun Yao Xiaotong Zhang Jie Cheng Xiang Zhao Qiang Liu Kun Jia Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data International Journal of Digital Earth net radiation energy balance mid-low latitude model comparison machine learning deep learning modis era5 |
| title | Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data |
| title_full | Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data |
| title_fullStr | Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data |
| title_full_unstemmed | Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data |
| title_short | Evaluation of nine machine learning methods for estimating daily land surface radiation budget from MODIS satellite data |
| title_sort | evaluation of nine machine learning methods for estimating daily land surface radiation budget from modis satellite data |
| topic | net radiation energy balance mid-low latitude model comparison machine learning deep learning modis era5 |
| url | http://dx.doi.org/10.1080/17538947.2022.2130460 |
| work_keys_str_mv | AT shaopengli evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT bojiang evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT shunlinliang evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT jianghaipeng evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT huiliang evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT jiakunhan evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT xiuwanyin evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT yunjunyao evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT xiaotongzhang evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT jiecheng evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT xiangzhao evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT qiangliu evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata AT kunjia evaluationofninemachinelearningmethodsforestimatingdailylandsurfaceradiationbudgetfrommodissatellitedata |