Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm
Efficient land management and farming practices are critical to maintaining agricultural production, especially in Europe with limited arable land. It is very time consuming to rely on a manual field inspection of cultivated land to archive farm crops. But with the help of satellite monitoring data...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2023-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/15/21/5203 |
| _version_ | 1797631345186308096 |
|---|---|
| author | Xiaoguang Yuan Shiruo Liu Wei Feng Gabriel Dauphin |
| author_facet | Xiaoguang Yuan Shiruo Liu Wei Feng Gabriel Dauphin |
| author_sort | Xiaoguang Yuan |
| collection | DOAJ |
| description | Efficient land management and farming practices are critical to maintaining agricultural production, especially in Europe with limited arable land. It is very time consuming to rely on a manual field inspection of cultivated land to archive farm crops. But with the help of satellite monitoring data on the earth’s surface, it is a new vision to classify farmland based on deep learning. This article has studied the Sentinel 2 (S2) data, which are top-of-atmosphere (TOA) reflectance values at the processing level-1C (L1C) observed from some areas of Germany and France. Aiming at the problem that the interference of atmosphere and cloud coverage weakens the recognition accuracy of subsequent algorithms, a method of combining feature expansion and feature importance analysis is proposed to optimize the raw S2 data. Specifically, the new 13 spectral features are expanded based on the linear and nonlinear combination of the raw 13 spectral bands of S2. The random forest (RF) algorithm is used to score the importance of features, and the important features of each time series are selected to form a new dataset. Then, an end-to-end deep learning model has been used for training. The structure of the model is a two-layer unidirectional recurrent neural network with long short-term memory (LSTM) as the backbone. And two linear layers as the output, which form two decision-making heads, respectively, representing output classification probability and the stop decision. The results show that adding features and selecting features is beneficial for the model to improve classification accuracy and predict the classification without all of the input data. This end-to-end classification pattern with early prediction would support intelligent monitoring of farm crops with a great advantage to the implementation of various agricultural policies. |
| first_indexed | 2024-03-11T11:22:25Z |
| format | Article |
| id | doaj.art-90fa1e8b452147069056ff58b8fc1669 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-11T11:22:25Z |
| publishDate | 2023-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-90fa1e8b452147069056ff58b8fc16692023-11-10T15:11:22ZengMDPI AGRemote Sensing2072-42922023-11-011521520310.3390/rs15215203Feature Importance Ranking of Random Forest-Based End-to-End Learning AlgorithmXiaoguang Yuan0Shiruo Liu1Wei Feng2Gabriel Dauphin3Department of Remote Sensing Science and Technology, School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaDepartment of Remote Sensing Science and Technology, School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaDepartment of Remote Sensing Science and Technology, School of Electronic Engineering, Xidian University, Xi’an 710071, ChinaLaboraory of Information Processing and Transmission, L2TI, Institut Galilée, University Paris XIII, 93430 Villetaneuse, FranceEfficient land management and farming practices are critical to maintaining agricultural production, especially in Europe with limited arable land. It is very time consuming to rely on a manual field inspection of cultivated land to archive farm crops. But with the help of satellite monitoring data on the earth’s surface, it is a new vision to classify farmland based on deep learning. This article has studied the Sentinel 2 (S2) data, which are top-of-atmosphere (TOA) reflectance values at the processing level-1C (L1C) observed from some areas of Germany and France. Aiming at the problem that the interference of atmosphere and cloud coverage weakens the recognition accuracy of subsequent algorithms, a method of combining feature expansion and feature importance analysis is proposed to optimize the raw S2 data. Specifically, the new 13 spectral features are expanded based on the linear and nonlinear combination of the raw 13 spectral bands of S2. The random forest (RF) algorithm is used to score the importance of features, and the important features of each time series are selected to form a new dataset. Then, an end-to-end deep learning model has been used for training. The structure of the model is a two-layer unidirectional recurrent neural network with long short-term memory (LSTM) as the backbone. And two linear layers as the output, which form two decision-making heads, respectively, representing output classification probability and the stop decision. The results show that adding features and selecting features is beneficial for the model to improve classification accuracy and predict the classification without all of the input data. This end-to-end classification pattern with early prediction would support intelligent monitoring of farm crops with a great advantage to the implementation of various agricultural policies.https://www.mdpi.com/2072-4292/15/21/5203deep learningfeature importancerandom forestSentinel 2 |
| spellingShingle | Xiaoguang Yuan Shiruo Liu Wei Feng Gabriel Dauphin Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm Remote Sensing deep learning feature importance random forest Sentinel 2 |
| title | Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm |
| title_full | Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm |
| title_fullStr | Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm |
| title_full_unstemmed | Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm |
| title_short | Feature Importance Ranking of Random Forest-Based End-to-End Learning Algorithm |
| title_sort | feature importance ranking of random forest based end to end learning algorithm |
| topic | deep learning feature importance random forest Sentinel 2 |
| url | https://www.mdpi.com/2072-4292/15/21/5203 |
| work_keys_str_mv | AT xiaoguangyuan featureimportancerankingofrandomforestbasedendtoendlearningalgorithm AT shiruoliu featureimportancerankingofrandomforestbasedendtoendlearningalgorithm AT weifeng featureimportancerankingofrandomforestbasedendtoendlearningalgorithm AT gabrieldauphin featureimportancerankingofrandomforestbasedendtoendlearningalgorithm |