Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon
In precision agriculture, the nitrogen level is significantly important for establishing phenotype, quality and yield of crops. It cannot be achieved in the future without appropriate nitrogen fertilizer application. Moreover, a convenient and real-time advance technology for nitrogen nutrition diag...
Guardado en:
| Autores principales: | , , , , , |
|---|---|
| Formato: | article |
| Lenguaje: | EN |
| Publicado: |
MDPI AG
2021
|
| Materias: | |
| Acceso en línea: | https://doaj.org/article/6cf92179863b477e842ff9ec229ec050 |
| Etiquetas: |
Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
|
| id |
oai:doaj.org-article:6cf92179863b477e842ff9ec229ec050 |
|---|---|
| record_format |
dspace |
| spelling |
oai:doaj.org-article:6cf92179863b477e842ff9ec229ec0502021-11-25T17:47:35ZUsing a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon10.3390/horticulturae71104892311-7524https://doaj.org/article/6cf92179863b477e842ff9ec229ec0502021-11-01T00:00:00Zhttps://www.mdpi.com/2311-7524/7/11/489https://doaj.org/toc/2311-7524In precision agriculture, the nitrogen level is significantly important for establishing phenotype, quality and yield of crops. It cannot be achieved in the future without appropriate nitrogen fertilizer application. Moreover, a convenient and real-time advance technology for nitrogen nutrition diagnosis of crops is a prerequisite for an efficient and reasonable nitrogen-fertilizer management system. With the development of research on plant phenotype and artificial intelligence technology in agriculture, deep learning has demonstrated a great potential in agriculture for recognizing nondestructive nitrogen nutrition diagnosis in plants by automation and high throughput at a low cost. To build a nitrogen nutrient-diagnosis model, muskmelons were cultivated under different nitrogen levels in a greenhouse. The digital images of canopy leaves and the environmental factors (light and temperature) during the growth period of muskmelons were tracked and analyzed. The nitrogen concentrations of the plants were measured, we successfully constructed and trained machine-learning- and deep-learning models based on the traditional backpropagation neural network (BPNN), the emerging convolution neural network (CNN), the deep convolution neural network (DCNN) and the long short-term memory (LSTM) for the nitrogen nutrition diagnosis of muskmelon. The adjusted determination coefficient (R<sup>2</sup>) and mean square error (MSE) between the predicted values and measured values of nitrogen concentration were adopted to evaluate the models’ accuracy. The values were R<sup>2</sup> = 0.567 and MSE = 0.429 for BPNN model; R<sup>2</sup> = 0.376 and MSE = 0.628 for CNN model; R<sup>2</sup> = 0.686 and MSE = 0.355 for deep convolution neural network (DCNN) model; and R<sup>2</sup> = 0.904 and MSE = 0.123 for the hybrid model DCNN–LSTM. Therefore, DCNN–LSTM shows the highest accuracy in predicting the nitrogen content of muskmelon. Our findings highlight a base for achieving a convenient, precise and intelligent diagnosis of nitrogen nutrition in muskmelon.Liying ChangDaren LiMuhammad Khalid HameedYilu YinDanfeng HuangQingliang NiuMDPI AGarticlemachine learningdeep learningconvolution neural network (CNN)long-short term memory (LSTM)deep convolution neural network (DCNN)nitrogen nutrition diagnosisPlant cultureSB1-1110ENHorticulturae, Vol 7, Iss 489, p 489 (2021) |
| institution |
DOAJ |
| collection |
DOAJ |
| language |
EN |
| topic |
machine learning deep learning convolution neural network (CNN) long-short term memory (LSTM) deep convolution neural network (DCNN) nitrogen nutrition diagnosis Plant culture SB1-1110 |
| spellingShingle |
machine learning deep learning convolution neural network (CNN) long-short term memory (LSTM) deep convolution neural network (DCNN) nitrogen nutrition diagnosis Plant culture SB1-1110 Liying Chang Daren Li Muhammad Khalid Hameed Yilu Yin Danfeng Huang Qingliang Niu Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| description |
In precision agriculture, the nitrogen level is significantly important for establishing phenotype, quality and yield of crops. It cannot be achieved in the future without appropriate nitrogen fertilizer application. Moreover, a convenient and real-time advance technology for nitrogen nutrition diagnosis of crops is a prerequisite for an efficient and reasonable nitrogen-fertilizer management system. With the development of research on plant phenotype and artificial intelligence technology in agriculture, deep learning has demonstrated a great potential in agriculture for recognizing nondestructive nitrogen nutrition diagnosis in plants by automation and high throughput at a low cost. To build a nitrogen nutrient-diagnosis model, muskmelons were cultivated under different nitrogen levels in a greenhouse. The digital images of canopy leaves and the environmental factors (light and temperature) during the growth period of muskmelons were tracked and analyzed. The nitrogen concentrations of the plants were measured, we successfully constructed and trained machine-learning- and deep-learning models based on the traditional backpropagation neural network (BPNN), the emerging convolution neural network (CNN), the deep convolution neural network (DCNN) and the long short-term memory (LSTM) for the nitrogen nutrition diagnosis of muskmelon. The adjusted determination coefficient (R<sup>2</sup>) and mean square error (MSE) between the predicted values and measured values of nitrogen concentration were adopted to evaluate the models’ accuracy. The values were R<sup>2</sup> = 0.567 and MSE = 0.429 for BPNN model; R<sup>2</sup> = 0.376 and MSE = 0.628 for CNN model; R<sup>2</sup> = 0.686 and MSE = 0.355 for deep convolution neural network (DCNN) model; and R<sup>2</sup> = 0.904 and MSE = 0.123 for the hybrid model DCNN–LSTM. Therefore, DCNN–LSTM shows the highest accuracy in predicting the nitrogen content of muskmelon. Our findings highlight a base for achieving a convenient, precise and intelligent diagnosis of nitrogen nutrition in muskmelon. |
| format |
article |
| author |
Liying Chang Daren Li Muhammad Khalid Hameed Yilu Yin Danfeng Huang Qingliang Niu |
| author_facet |
Liying Chang Daren Li Muhammad Khalid Hameed Yilu Yin Danfeng Huang Qingliang Niu |
| author_sort |
Liying Chang |
| title |
Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| title_short |
Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| title_full |
Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| title_fullStr |
Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| title_full_unstemmed |
Using a Hybrid Neural Network Model DCNN–LSTM for Image-Based Nitrogen Nutrition Diagnosis in Muskmelon |
| title_sort |
using a hybrid neural network model dcnn–lstm for image-based nitrogen nutrition diagnosis in muskmelon |
| publisher |
MDPI AG |
| publishDate |
2021 |
| url |
https://doaj.org/article/6cf92179863b477e842ff9ec229ec050 |
| work_keys_str_mv |
AT liyingchang usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon AT darenli usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon AT muhammadkhalidhameed usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon AT yiluyin usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon AT danfenghuang usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon AT qingliangniu usingahybridneuralnetworkmodeldcnnlstmforimagebasednitrogennutritiondiagnosisinmuskmelon |
| _version_ |
1718411990651633664 |