Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods
Leaf area index (LAI) is an essential vegetation parameter that represents the light energy utilization and vegetation canopy structure. As the only in-operation hyperspectral satellite launched by China, GF-5 is potentially useful for accurate LAI estimation. However, there is no research focus on...
| Main Authors: | , , , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2020-07-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/12/13/2110 |
| _version_ | 1797563474141773824 |
|---|---|
| author | Zhulin Chen Kun Jia Chenchao Xiao Dandan Wei Xiang Zhao Jinhui Lan Xiangqin Wei Yunjun Yao Bing Wang Yuan Sun Lei Wang |
| author_facet | Zhulin Chen Kun Jia Chenchao Xiao Dandan Wei Xiang Zhao Jinhui Lan Xiangqin Wei Yunjun Yao Bing Wang Yuan Sun Lei Wang |
| author_sort | Zhulin Chen |
| collection | DOAJ |
| description | Leaf area index (LAI) is an essential vegetation parameter that represents the light energy utilization and vegetation canopy structure. As the only in-operation hyperspectral satellite launched by China, GF-5 is potentially useful for accurate LAI estimation. However, there is no research focus on evaluating GF-5 data for LAI estimation. Hyperspectral remote sensing data contains abundant information about the reflective characteristics of vegetation canopies, but these abound data also easily result in a dimensionality curse. Therefore, feature selection (FS) is necessary to reduce data redundancy to achieve more reliable estimations. Currently, machine learning (ML) algorithms have been widely used for FS. Moreover, the same ML algorithm is usually conducted for both FS and regression in LAI estimation. However, no evidence suggests that this is the optimal solution. Therefore, this study focuses on evaluating the capacity of GF-5 spectral reflectance for estimating LAI and the performances of different combination of FS and ML algorithms. Firstly, the PROSAIL model, which coupled leaf optical properties model PROSPECT and the scattering by arbitrarily inclined leaves (SAIL) model, was used to generate simulated GF-5 reflectance data under different vegetation and soil conditions, and then three FS methods, including random forest (RF), K-means clustering (K-means) and mean impact value (MIV), and three ML algorithms, including random forest regression (RFR), back propagation neural network (BPNN) and K-nearest neighbor (KNN) were used to develop nine LAI estimation models. The FS process was conducted twice using different strategies: Firstly, three FS methods were conducted to search the lowest dimension number, which maintained the estimation accuracy of all bands. Then, the sequential backward selection (SBS) method was used to eliminate the bands having minimal impact on LAI estimation accuracy. Finally, three best estimation models were selected and evaluated using reference LAI. The results showed that although the RF_RFR model (RF used for feature selection and RFR used for regression) achieved reliable LAI estimates (coefficient of determination (R<sup>2</sup>) = 0.828, root mean square error (RMSE) = 0.839), the poor performance (R<sup>2</sup> = 0.763, RMSE = 0.987) of the MIV_BPNN model (MIV used for feature selection and BPNN used for regression) suggested using feature selection and regression conducted by the same ML algorithm could not always ensure an optimal estimation. Moreover, RF selection preserved the most informative bands for LAI estimation so that each ML regression method could achieve satisfactory estimation results. Finally, the results indicated that the RF_KNN model (RF used as feature selection and KNN used for regression) with seven GF-5 spectral band reflectance achieved the better estimation results than others when validated by simulated data (R<sup>2</sup> = 0.834, RMSE = 0.824) and actual reference LAI (R<sup>2</sup> = 0.659, RMSE = 0.697). |
| first_indexed | 2024-03-10T18:44:08Z |
| format | Article |
| id | doaj.art-02431103d5c94576a0c9390de0d9a438 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T18:44:08Z |
| publishDate | 2020-07-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-02431103d5c94576a0c9390de0d9a4382023-11-20T05:36:08ZengMDPI AGRemote Sensing2072-42922020-07-011213211010.3390/rs12132110Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning MethodsZhulin Chen0Kun Jia1Chenchao Xiao2Dandan Wei3Xiang Zhao4Jinhui Lan5Xiangqin Wei6Yunjun Yao7Bing Wang8Yuan Sun9Lei Wang10State Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resource of the People’s Republic of China, Beijing 100048, ChinaLand Satellite Remote Sensing Application Center, Ministry of Natural Resource of the People’s Republic of China, Beijing 100048, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaBeijing Engineering Research Center of Industrial Spectrum Imaging, Beijing 100083, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaState Key Laboratory of Remote Sensing Science, Faculty of Geographical Science, Beijing Normal University, Beijing 100875, ChinaAerospace Information Research Institute, Chinese Academy of Sciences, Beijing 100101, ChinaNorthwest National Key Laboratory Breeding Base for Land Degradation and Ecological Restoration, Ningxia University, Yinchuan 750021, ChinaLeaf area index (LAI) is an essential vegetation parameter that represents the light energy utilization and vegetation canopy structure. As the only in-operation hyperspectral satellite launched by China, GF-5 is potentially useful for accurate LAI estimation. However, there is no research focus on evaluating GF-5 data for LAI estimation. Hyperspectral remote sensing data contains abundant information about the reflective characteristics of vegetation canopies, but these abound data also easily result in a dimensionality curse. Therefore, feature selection (FS) is necessary to reduce data redundancy to achieve more reliable estimations. Currently, machine learning (ML) algorithms have been widely used for FS. Moreover, the same ML algorithm is usually conducted for both FS and regression in LAI estimation. However, no evidence suggests that this is the optimal solution. Therefore, this study focuses on evaluating the capacity of GF-5 spectral reflectance for estimating LAI and the performances of different combination of FS and ML algorithms. Firstly, the PROSAIL model, which coupled leaf optical properties model PROSPECT and the scattering by arbitrarily inclined leaves (SAIL) model, was used to generate simulated GF-5 reflectance data under different vegetation and soil conditions, and then three FS methods, including random forest (RF), K-means clustering (K-means) and mean impact value (MIV), and three ML algorithms, including random forest regression (RFR), back propagation neural network (BPNN) and K-nearest neighbor (KNN) were used to develop nine LAI estimation models. The FS process was conducted twice using different strategies: Firstly, three FS methods were conducted to search the lowest dimension number, which maintained the estimation accuracy of all bands. Then, the sequential backward selection (SBS) method was used to eliminate the bands having minimal impact on LAI estimation accuracy. Finally, three best estimation models were selected and evaluated using reference LAI. The results showed that although the RF_RFR model (RF used for feature selection and RFR used for regression) achieved reliable LAI estimates (coefficient of determination (R<sup>2</sup>) = 0.828, root mean square error (RMSE) = 0.839), the poor performance (R<sup>2</sup> = 0.763, RMSE = 0.987) of the MIV_BPNN model (MIV used for feature selection and BPNN used for regression) suggested using feature selection and regression conducted by the same ML algorithm could not always ensure an optimal estimation. Moreover, RF selection preserved the most informative bands for LAI estimation so that each ML regression method could achieve satisfactory estimation results. Finally, the results indicated that the RF_KNN model (RF used as feature selection and KNN used for regression) with seven GF-5 spectral band reflectance achieved the better estimation results than others when validated by simulated data (R<sup>2</sup> = 0.834, RMSE = 0.824) and actual reference LAI (R<sup>2</sup> = 0.659, RMSE = 0.697).https://www.mdpi.com/2072-4292/12/13/2110GF-5LAIfeature selectionmachine learning |
| spellingShingle | Zhulin Chen Kun Jia Chenchao Xiao Dandan Wei Xiang Zhao Jinhui Lan Xiangqin Wei Yunjun Yao Bing Wang Yuan Sun Lei Wang Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods Remote Sensing GF-5 LAI feature selection machine learning |
| title | Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods |
| title_full | Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods |
| title_fullStr | Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods |
| title_full_unstemmed | Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods |
| title_short | Leaf Area Index Estimation Algorithm for GF-5 Hyperspectral Data Based on Different Feature Selection and Machine Learning Methods |
| title_sort | leaf area index estimation algorithm for gf 5 hyperspectral data based on different feature selection and machine learning methods |
| topic | GF-5 LAI feature selection machine learning |
| url | https://www.mdpi.com/2072-4292/12/13/2110 |
| work_keys_str_mv | AT zhulinchen leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT kunjia leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT chenchaoxiao leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT dandanwei leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT xiangzhao leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT jinhuilan leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT xiangqinwei leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT yunjunyao leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT bingwang leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT yuansun leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods AT leiwang leafareaindexestimationalgorithmforgf5hyperspectraldatabasedondifferentfeatureselectionandmachinelearningmethods |