Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques
The equivalent water thickness (EWT) is an important biophysical indicator of water status in crops. The effective monitoring of EWT in wheat under different nitrogen and water treatments is important for irrigation management in precision agriculture. This study aimed to investigate the performance...
| Main Authors: | , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2021-11-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/13/21/4476 |
| _version_ | 1797511883705548800 |
|---|---|
| author | Adama Traore Syed Tahir Ata-Ul-Karim Aiwang Duan Mukesh Kumar Soothar Seydou Traore Ben Zhao |
| author_facet | Adama Traore Syed Tahir Ata-Ul-Karim Aiwang Duan Mukesh Kumar Soothar Seydou Traore Ben Zhao |
| author_sort | Adama Traore |
| collection | DOAJ |
| description | The equivalent water thickness (EWT) is an important biophysical indicator of water status in crops. The effective monitoring of EWT in wheat under different nitrogen and water treatments is important for irrigation management in precision agriculture. This study aimed to investigate the performances of machine learning (ML) algorithms in retrieving wheat EWT. For this purpose, a rain shelter experiment (Exp. 1) with four irrigation quantities (0, 120, 240, 360 mm) and two nitrogen levels (75 and 255 kg N/ha), and field experiments (Exps. 2–3) with the same irrigation and rainfall water levels (360 mm) but different nitrogen levels (varying from 75 to 255 kg N/ha) were conducted in the North China Plain. The canopy reflectance was measured for all plots at 30 m using an unmanned aerial vehicle (UAV)-mounted multispectral camera. Destructive sampling was conducted immediately after the UAV flights to measure total fresh and dry weight. Deep Neural Network (DNN) is a special type of neural network, which has shown performance in regression analysis is compared with other machine learning (ML) models. A feature selection (FS) algorithm named the decision tree (DT) was used as the automatic relevance determination method to obtain the relative relevance of 5 out of 67 vegetation indices (Vis), which were used for estimating EWT. The selected VIs were used to estimate EWT using multiple linear regression (MLR), deep neural network multilayer perceptron (DNN-MLP), artificial neural networks multilayer perceptron (ANN-MLP), boosted tree regression (BRT), and support vector machines (SVMs). The results show that the DNN-MLP with R<sup>2</sup> = 0.934, NSE = 0.933, RMSE = 0.028 g/cm<sup>2</sup>, and MAE of 0.017 g/cm<sup>2</sup> outperformed other ML algorithms (ANN-MPL, BRT, and SVM- Polynomial) owing to its high capacity for estimating EWT as compared to other ML methods. Our findings support the conclusion that ML can potentially be applied in combination with VIs for retrieving EWT. Despite the complexity of the ML models, the EWT map should help farmers by improving the real-time irrigation efficiency of wheat by quantifying field water content and addressing variability. |
| first_indexed | 2024-03-10T05:53:15Z |
| format | Article |
| id | doaj.art-c79f61f95aa648aebaafe8e999af4efb |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-10T05:53:15Z |
| publishDate | 2021-11-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-c79f61f95aa648aebaafe8e999af4efb2023-11-22T21:34:02ZengMDPI AGRemote Sensing2072-42922021-11-011321447610.3390/rs13214476Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning TechniquesAdama Traore0Syed Tahir Ata-Ul-Karim1Aiwang Duan2Mukesh Kumar Soothar3Seydou Traore4Ben Zhao5Key Laboratory of Crop Water Use and Regulation, Ministry of Agriculture, Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang 453003, ChinaGraduate School of Agricultural and Life Sciences, The University of Tokyo, Tokyo 113-8657, JapanKey Laboratory of Crop Water Use and Regulation, Ministry of Agriculture, Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang 453003, ChinaKey Laboratory of Crop Water Use and Regulation, Ministry of Agriculture, Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang 453003, ChinaMetropolitan Solar Inc., Washington, DC 20032, USAKey Laboratory of Crop Water Use and Regulation, Ministry of Agriculture, Farmland Irrigation Research Institute, Chinese Academy of Agricultural Sciences, Xinxiang 453003, ChinaThe equivalent water thickness (EWT) is an important biophysical indicator of water status in crops. The effective monitoring of EWT in wheat under different nitrogen and water treatments is important for irrigation management in precision agriculture. This study aimed to investigate the performances of machine learning (ML) algorithms in retrieving wheat EWT. For this purpose, a rain shelter experiment (Exp. 1) with four irrigation quantities (0, 120, 240, 360 mm) and two nitrogen levels (75 and 255 kg N/ha), and field experiments (Exps. 2–3) with the same irrigation and rainfall water levels (360 mm) but different nitrogen levels (varying from 75 to 255 kg N/ha) were conducted in the North China Plain. The canopy reflectance was measured for all plots at 30 m using an unmanned aerial vehicle (UAV)-mounted multispectral camera. Destructive sampling was conducted immediately after the UAV flights to measure total fresh and dry weight. Deep Neural Network (DNN) is a special type of neural network, which has shown performance in regression analysis is compared with other machine learning (ML) models. A feature selection (FS) algorithm named the decision tree (DT) was used as the automatic relevance determination method to obtain the relative relevance of 5 out of 67 vegetation indices (Vis), which were used for estimating EWT. The selected VIs were used to estimate EWT using multiple linear regression (MLR), deep neural network multilayer perceptron (DNN-MLP), artificial neural networks multilayer perceptron (ANN-MLP), boosted tree regression (BRT), and support vector machines (SVMs). The results show that the DNN-MLP with R<sup>2</sup> = 0.934, NSE = 0.933, RMSE = 0.028 g/cm<sup>2</sup>, and MAE of 0.017 g/cm<sup>2</sup> outperformed other ML algorithms (ANN-MPL, BRT, and SVM- Polynomial) owing to its high capacity for estimating EWT as compared to other ML methods. Our findings support the conclusion that ML can potentially be applied in combination with VIs for retrieving EWT. Despite the complexity of the ML models, the EWT map should help farmers by improving the real-time irrigation efficiency of wheat by quantifying field water content and addressing variability.https://www.mdpi.com/2072-4292/13/21/4476equivalent water thicknessUAVdeep learningvegetation indicesmultispectral images |
| spellingShingle | Adama Traore Syed Tahir Ata-Ul-Karim Aiwang Duan Mukesh Kumar Soothar Seydou Traore Ben Zhao Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques Remote Sensing equivalent water thickness UAV deep learning vegetation indices multispectral images |
| title | Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques |
| title_full | Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques |
| title_fullStr | Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques |
| title_full_unstemmed | Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques |
| title_short | Predicting Equivalent Water Thickness in Wheat Using UAV Mounted Multispectral Sensor through Deep Learning Techniques |
| title_sort | predicting equivalent water thickness in wheat using uav mounted multispectral sensor through deep learning techniques |
| topic | equivalent water thickness UAV deep learning vegetation indices multispectral images |
| url | https://www.mdpi.com/2072-4292/13/21/4476 |
| work_keys_str_mv | AT adamatraore predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques AT syedtahirataulkarim predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques AT aiwangduan predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques AT mukeshkumarsoothar predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques AT seydoutraore predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques AT benzhao predictingequivalentwaterthicknessinwheatusinguavmountedmultispectralsensorthroughdeeplearningtechniques |