This is an early access version, the complete PDF, HTML, and XML versions will be available soon.
Open AccessArticle
Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants
by
Mohamed Farag Taha
Mohamed Farag Taha 1,2,3,
Hanping Mao
Hanping Mao 1,*,
Samar Mousa
Samar Mousa 4,
Lei Zhou
Lei Zhou
Dr. Lei Zhou obtained his bachelor's degree from the School of Engineering at Beijing Forestry from [...]
Dr. Lei Zhou obtained his bachelor's degree from the School of Engineering at Beijing Forestry University from September 2013 to June 2017. He obtained a doctoral degree from the School of Biosystems Engineering and Food Science, Zhejiang University, from September 2017 to June 2022. Since August 2022, he has been working as a postdoctoral fellow at the School of Mechanical and Electronic Engineering, Nanjing Forestry University. Since July 2022, he has been serving as a lecturer at the School of Mechanical and Electronic Engineering, Nanjing Forestry University. His research directions include deep learning, machine learning, plant phenotypes, machine vision, spectrum analysis, and fruit-picking robots.
5,
Yafei Wang
Yafei Wang
Dr. Yafei Wang obtained his undergraduate degree in Agricultural Electrification and Automation from [...]
Dr. Yafei Wang obtained his undergraduate degree in Agricultural Electrification and Automation from Henan University of Science and Technology from September 2012 to July 2016, his Master's degree in Agricultural Engineering from Henan University of Science and Technology from September 2016 to July 2019, and his doctoral degree in Agricultural Engineering from Jiangsu University from September 2019 to June 2023. Since August 2023, he has been a lecturer at the School of Agricultural Engineering, Jiangsu University. From January 2024 to present, he has been working as a postdoctoral fellow at Jiangsu Changdian Technology Co., Ltd. His research direction is intelligent facility agriculture technology and equipment.
1,
Gamal Elmasry
Gamal Elmasry 6,
Salim Al-Rejaie
Salim Al-Rejaie 7,
Abdallah Elshawadfy Elwakeel
Abdallah Elshawadfy Elwakeel 8,
Yazhou Wei
Yazhou Wei 1 and
Zhengjun Qiu
Zhengjun Qiu 2
1
School of Agricultural Engineering, Jiangsu University, Zhenjiang 212013, China
2
College of Biosystems Engineering and Food Science, Zhejiang University, Hangzhou 310058, China
3
Department of Soil and Water Sciences, Faculty of Environmental Agricultural Sciences, Arish University, North Sinai 45516, Egypt
4
Agricultural Botany Department, Faculty of Agriculture, Suez Canal University, Ismailia 41522, Egypt
5
College of Mechanical and Electronic Engineering, Nanjing Forestry University, Nanjing 210037, China
6
Agricultural Engineering Department, Faculty of Agriculture, Suez Canal University, Ismailia 41522, Egypt
7
Department of Pharmacology & Toxicology, College of Pharmacy, King Saud University, Riyadh 4545, Saudi Arabia
8
Agricultural Engineering Department, Faculty of Agriculture and Natural Resources, Aswan University, Aswan 81528, Egypt
*
Author to whom correspondence should be addressed.
Agronomy 2024, 14(10), 2290; https://doi.org/10.3390/agronomy14102290 (registering DOI)
Submission received: 3 September 2024
/
Revised: 30 September 2024
/
Accepted: 1 October 2024
/
Published: 5 October 2024
Abstract
Developing models to assess the nutrient status of plants at various growth stages is challenging due to the dynamic nature of plant development. Hence, this study encoded spatiotemporal information of plants within a single time-series model to precisely assess the nutrient status of aquaponically cultivated lettuce. In particular, the long short-term memory (LSTM) and deep autoencoder (DAE) approaches were combined to classify aquaponically grown lettuce plants according to their nutrient status. The proposed approach was validated using extensive sequential hyperspectral reflectance measurements acquired from lettuce leaves at different growth stages across the growing season. A DAE was used to extract distinct features from each sequential spectral dataset time step. These features were used as input to an LSTM model to classify lettuce grown across a gradient of nutrient levels. The results demonstrated that the LSTM outperformed the convolutional neural network (CNN) and multi-class support vector machine (MCSVM) approaches. Also, features selected by the DAE showed better performance compared to features extracted using both genetic algorithms (GAs) and sequential forward selection (SFS). The hybridization of deep autoencoder and long short-term memory (DAE-LSTM) obtained the highest overall classification accuracy of 94%. The suggested methodology presents a pathway to automating the process of nutrient status diagnosis throughout the entire plant life cycle, with the LSTM technique poised to assume a pivotal role in forthcoming time-series analyses for precision agriculture.
Share and Cite
MDPI and ACS Style
Taha, M.F.; Mao, H.; Mousa, S.; Zhou, L.; Wang, Y.; Elmasry, G.; Al-Rejaie, S.; Elwakeel, A.E.; Wei, Y.; Qiu, Z.
Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants. Agronomy 2024, 14, 2290.
https://doi.org/10.3390/agronomy14102290
AMA Style
Taha MF, Mao H, Mousa S, Zhou L, Wang Y, Elmasry G, Al-Rejaie S, Elwakeel AE, Wei Y, Qiu Z.
Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants. Agronomy. 2024; 14(10):2290.
https://doi.org/10.3390/agronomy14102290
Chicago/Turabian Style
Taha, Mohamed Farag, Hanping Mao, Samar Mousa, Lei Zhou, Yafei Wang, Gamal Elmasry, Salim Al-Rejaie, Abdallah Elshawadfy Elwakeel, Yazhou Wei, and Zhengjun Qiu.
2024. "Deep Learning-Enabled Dynamic Model for Nutrient Status Detection of Aquaponically Grown Plants" Agronomy 14, no. 10: 2290.
https://doi.org/10.3390/agronomy14102290
Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details
here.
Article Metrics
Article metric data becomes available approximately 24 hours after publication online.