Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data
Spatial prediction of soil ammonia (NH<sub>3</sub>) plays an important role in monitoring climate warming and soil ecological health. However, traditional machine learning (ML) models do not consider optimal parameter selection and spatial autocorrelation. Here, we present an integration...
| Main Authors: | , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-08-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/17/4268 |
| _version_ | 1827727815043186688 |
|---|---|
| author | Yingqiang Song Mingzhu Ye Zhao Zheng Dexi Zhan Wenxu Duan Miao Lu Zhenqi Song Dengkuo Sun Kaizhong Yao Ziqi Ding |
| author_facet | Yingqiang Song Mingzhu Ye Zhao Zheng Dexi Zhan Wenxu Duan Miao Lu Zhenqi Song Dengkuo Sun Kaizhong Yao Ziqi Ding |
| author_sort | Yingqiang Song |
| collection | DOAJ |
| description | Spatial prediction of soil ammonia (NH<sub>3</sub>) plays an important role in monitoring climate warming and soil ecological health. However, traditional machine learning (ML) models do not consider optimal parameter selection and spatial autocorrelation. Here, we present an integration method (tree-structured Parzen estimator–machine learning–ordinary kriging (TPE–ML–OK)) to predict spatial variability of soil NH<sub>3</sub> from Sentinel-2 remote sensing image and air quality data. In TPE–ML–OK, we designed the TPE search algorithm, which encourages gradient boosting decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGB) models to pay more attention to the optimal hyperparameters’ high-possibility range, and then the residual ordinary kriging model is used to further improve the prediction accuracy of soil NH<sub>3</sub> flux. We found a weak linear correlation between soil NH<sub>3</sub> flux and environmental variables using scatter matrix correlation analysis. The optimal hyperparameters from the TPE search algorithm existed in the densest iteration region, and the TPE–XGB–OK method exhibited the highest predicted accuracy (R<sup>2</sup> = 85.97%) for soil NH<sub>3</sub> flux in comparison with other models. The spatial mapping results based on TPE–ML–OK methods showed that the high fluxes of soil NH<sub>3</sub> were concentrated in the central and northeast areas, which may be influenced by rivers or soil water. The analysis result of the SHapley additive explanation (SHAP) algorithm found that the variables with the highest contribution to soil NH<sub>3</sub> were O<sub>3</sub>, SO<sub>2</sub>, PM<sub>10</sub>, CO, and NDWI. The above results demonstrate the powerful linear–nonlinear interpretation ability between soil NH<sub>3</sub> and environmental variables using the integration method, which can reduce the impact on agricultural nitrogen deposition and regional air quality. |
| first_indexed | 2024-03-10T23:14:21Z |
| format | Article |
| id | doaj.art-67d7b098e9404af086bf8e35c17212cc |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T23:14:21Z |
| publishDate | 2023-08-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-67d7b098e9404af086bf8e35c17212cc2023-11-19T08:46:49ZengMDPI AGRemote Sensing2072-42922023-08-011517426810.3390/rs15174268Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality DataYingqiang Song0Mingzhu Ye1Zhao Zheng2Dexi Zhan3Wenxu Duan4Miao Lu5Zhenqi Song6Dengkuo Sun7Kaizhong Yao8Ziqi Ding9School of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaState Key Laboratory of Efficient Utilization of Arid and Semi-Arid Arable Land in Northern China, Institute of Agricultural Resources and Regional Planning, Chinese Academy of Agricultural Sciences, Beijing 100081, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSchool of Civil Engineering and Geomatics, Shandong University of Technology, Zibo 255000, ChinaSpatial prediction of soil ammonia (NH<sub>3</sub>) plays an important role in monitoring climate warming and soil ecological health. However, traditional machine learning (ML) models do not consider optimal parameter selection and spatial autocorrelation. Here, we present an integration method (tree-structured Parzen estimator–machine learning–ordinary kriging (TPE–ML–OK)) to predict spatial variability of soil NH<sub>3</sub> from Sentinel-2 remote sensing image and air quality data. In TPE–ML–OK, we designed the TPE search algorithm, which encourages gradient boosting decision tree (GBDT), random forest (RF), and extreme gradient boosting (XGB) models to pay more attention to the optimal hyperparameters’ high-possibility range, and then the residual ordinary kriging model is used to further improve the prediction accuracy of soil NH<sub>3</sub> flux. We found a weak linear correlation between soil NH<sub>3</sub> flux and environmental variables using scatter matrix correlation analysis. The optimal hyperparameters from the TPE search algorithm existed in the densest iteration region, and the TPE–XGB–OK method exhibited the highest predicted accuracy (R<sup>2</sup> = 85.97%) for soil NH<sub>3</sub> flux in comparison with other models. The spatial mapping results based on TPE–ML–OK methods showed that the high fluxes of soil NH<sub>3</sub> were concentrated in the central and northeast areas, which may be influenced by rivers or soil water. The analysis result of the SHapley additive explanation (SHAP) algorithm found that the variables with the highest contribution to soil NH<sub>3</sub> were O<sub>3</sub>, SO<sub>2</sub>, PM<sub>10</sub>, CO, and NDWI. The above results demonstrate the powerful linear–nonlinear interpretation ability between soil NH<sub>3</sub> and environmental variables using the integration method, which can reduce the impact on agricultural nitrogen deposition and regional air quality.https://www.mdpi.com/2072-4292/15/17/4268soil ammoniaXGBoostordinary krigingspatial predictionhyperparameter |
| spellingShingle | Yingqiang Song Mingzhu Ye Zhao Zheng Dexi Zhan Wenxu Duan Miao Lu Zhenqi Song Dengkuo Sun Kaizhong Yao Ziqi Ding Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data Remote Sensing soil ammonia XGBoost ordinary kriging spatial prediction hyperparameter |
| title | Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data |
| title_full | Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data |
| title_fullStr | Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data |
| title_full_unstemmed | Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data |
| title_short | Tree-Structured Parzan Estimator–Machine Learning–Ordinary Kriging: An Integration Method for Soil Ammonia Spatial Prediction in the Typical Cropland of Chinese Yellow River Delta with Sentinel-2 Remote Sensing Image and Air Quality Data |
| title_sort | tree structured parzan estimator machine learning ordinary kriging an integration method for soil ammonia spatial prediction in the typical cropland of chinese yellow river delta with sentinel 2 remote sensing image and air quality data |
| topic | soil ammonia XGBoost ordinary kriging spatial prediction hyperparameter |
| url | https://www.mdpi.com/2072-4292/15/17/4268 |
| work_keys_str_mv | AT yingqiangsong treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT mingzhuye treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT zhaozheng treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT dexizhan treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT wenxuduan treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT miaolu treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT zhenqisong treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT dengkuosun treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT kaizhongyao treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata AT ziqiding treestructuredparzanestimatormachinelearningordinarykriginganintegrationmethodforsoilammoniaspatialpredictioninthetypicalcroplandofchineseyellowriverdeltawithsentinel2remotesensingimageandairqualitydata |