A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage
Nitrogen (N) and potassium (K) are two key mineral nutrient elements involved in rice growth. Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage. Therefore, we propose a hybrid model for diagnosing rice nutrient levels a...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Elsevier
2024-02-01
|
| Series: | Journal of Integrative Agriculture |
| Subjects: | |
| Online Access: | http://www.sciencedirect.com/science/article/pii/S2095311923001570 |
| _version_ | 1797326291803832320 |
|---|---|
| author | Fubing Liao Xiangqian Feng Ziqiu Li Danying Wang Chunmei Xu Guang Chu Hengyu Ma Qing Yao Song Chen |
| author_facet | Fubing Liao Xiangqian Feng Ziqiu Li Danying Wang Chunmei Xu Guang Chu Hengyu Ma Qing Yao Song Chen |
| author_sort | Fubing Liao |
| collection | DOAJ |
| description | Nitrogen (N) and potassium (K) are two key mineral nutrient elements involved in rice growth. Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage. Therefore, we propose a hybrid model for diagnosing rice nutrient levels at the early panicle initiation stage (EPIS), which combines a convolutional neural network (CNN) with an attention mechanism and a long short-term memory network (LSTM). The model was validated on a large set of sequential images collected by an unmanned aerial vehicle (UAV) from rice canopies at different growth stages during a two-year experiment. Compared with VGG16, AlexNet, GoogleNet, DenseNet, and inceptionV3, ResNet101 combined with LSTM obtained the highest average accuracy of 83.81% on the dataset of Huanghuazhan (HHZ, an indica cultivar). When tested on the datasets of HHZ and Xiushui 134 (XS134, a japonica rice variety) in 2021, the ResNet101-LSTM model enhanced with the squeeze-and-excitation (SE) block achieved the highest accuracies of 85.38 and 88.38%, respectively. Through the cross-dataset method, the average accuracies on the HHZ and XS134 datasets tested in 2022 were 81.25 and 82.50%, respectively, showing a good generalization. Our proposed model works with the dynamic information of different rice growth stages and can efficiently diagnose different rice nutrient status levels at EPIS, which are helpful for making practical decisions regarding rational fertilization treatments at the panicle initiation stage. |
| first_indexed | 2024-03-08T06:21:13Z |
| format | Article |
| id | doaj.art-49cfa110e2d047578c77eb946284af21 |
| institution | Directory Open Access Journal |
| issn | 2095-3119 |
| language | English |
| last_indexed | 2024-03-08T06:21:13Z |
| publishDate | 2024-02-01 |
| publisher | Elsevier |
| record_format | Article |
| series | Journal of Integrative Agriculture |
| spelling | doaj.art-49cfa110e2d047578c77eb946284af212024-02-04T04:44:12ZengElsevierJournal of Integrative Agriculture2095-31192024-02-01232711723A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stageFubing Liao0Xiangqian Feng1Ziqiu Li2Danying Wang3Chunmei Xu4Guang Chu5Hengyu Ma6Qing Yao7Song Chen8School of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, China; School of Agriculture, Yangtze University, Jingzhou 434025, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, ChinaSchool of Computer Science and Technology, Zhejiang Sci-Tech University, Hangzhou 310018, ChinaChina National Rice Research Institute, Chinese Academy of Agricultural Sciences, Hangzhou 310006, China; Correspondence Song Chen, Tel: +86-571-63370276Nitrogen (N) and potassium (K) are two key mineral nutrient elements involved in rice growth. Accurate diagnosis of N and K status is very important for the rational application of fertilizers at a specific rice growth stage. Therefore, we propose a hybrid model for diagnosing rice nutrient levels at the early panicle initiation stage (EPIS), which combines a convolutional neural network (CNN) with an attention mechanism and a long short-term memory network (LSTM). The model was validated on a large set of sequential images collected by an unmanned aerial vehicle (UAV) from rice canopies at different growth stages during a two-year experiment. Compared with VGG16, AlexNet, GoogleNet, DenseNet, and inceptionV3, ResNet101 combined with LSTM obtained the highest average accuracy of 83.81% on the dataset of Huanghuazhan (HHZ, an indica cultivar). When tested on the datasets of HHZ and Xiushui 134 (XS134, a japonica rice variety) in 2021, the ResNet101-LSTM model enhanced with the squeeze-and-excitation (SE) block achieved the highest accuracies of 85.38 and 88.38%, respectively. Through the cross-dataset method, the average accuracies on the HHZ and XS134 datasets tested in 2022 were 81.25 and 82.50%, respectively, showing a good generalization. Our proposed model works with the dynamic information of different rice growth stages and can efficiently diagnose different rice nutrient status levels at EPIS, which are helpful for making practical decisions regarding rational fertilization treatments at the panicle initiation stage.http://www.sciencedirect.com/science/article/pii/S2095311923001570dynamic model of deep learningUAVrice panicle initiationnutrient level diagnosisimage classification |
| spellingShingle | Fubing Liao Xiangqian Feng Ziqiu Li Danying Wang Chunmei Xu Guang Chu Hengyu Ma Qing Yao Song Chen A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage Journal of Integrative Agriculture dynamic model of deep learning UAV rice panicle initiation nutrient level diagnosis image classification |
| title | A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| title_full | A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| title_fullStr | A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| title_full_unstemmed | A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| title_short | A hybrid CNN-LSTM model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| title_sort | hybrid cnn lstm model for diagnosing rice nutrient levels at the rice panicle initiation stage |
| topic | dynamic model of deep learning UAV rice panicle initiation nutrient level diagnosis image classification |
| url | http://www.sciencedirect.com/science/article/pii/S2095311923001570 |
| work_keys_str_mv | AT fubingliao ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT xiangqianfeng ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT ziqiuli ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT danyingwang ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT chunmeixu ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT guangchu ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT hengyuma ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT qingyao ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT songchen ahybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT fubingliao hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT xiangqianfeng hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT ziqiuli hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT danyingwang hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT chunmeixu hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT guangchu hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT hengyuma hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT qingyao hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage AT songchen hybridcnnlstmmodelfordiagnosingricenutrientlevelsatthericepanicleinitiationstage |