A novel hybrid deep network for diagnosing water status in wheat crop using IoT-based multimodal data

Elsherbiny, Osama; Zhou, Lei; He, Yong; Qiu, Zhengjun

doi:10.1016/j.compag.2022.107453

Cited by 18 publications

(12 citation statements)

References 38 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Second, the specific neural network architecture chosen for the task played a significant role in shaping the network’s behavior [ 35 ]. Third, augmented data significantly contributes to the improvement of the proposed models [ 8 ].…”

Section: Resultsmentioning

confidence: 99%

“…The VGG16-based hybrid network, empowered by data augmentation, proved to be an effective model for grapevine health assessment. Its exceptional architecture and rich features propelled it to outperform all other approaches [ 8 ], setting a new benchmark in vineyard diagnostics.…”

Section: Resultsmentioning

confidence: 99%

“…As a result, the agricultural industry makes extensive use of distant and proximal sensing techniques, as well as big data technologies, computer vision, robots, deep learning (DL) and machine learning (ML) techniques, and high-performance computers. These methods have utility beyond plant disease diagnosis, encompassing weed detection, crop quality assessment, yield prediction, species identification, water and soil monitoring, and irrigation system management [ 7 , 8 ].…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning

Elsherbiny,

Elaraby,

Alahmadi

et al. 2024

Plants

Self Cite

View full text Add to dashboard Cite

Deep learning plays a vital role in precise grapevine disease detection, yet practical applications for farmer assistance are scarce despite promising results. The objective of this research is to develop an intelligent approach, supported by user-friendly, open-source software named AI GrapeCare (Version 1, created by Osama Elsherbiny). This approach utilizes RGB imagery and hybrid deep networks for the detection and prevention of grapevine diseases. Exploring the optimal deep learning architecture involved combining convolutional neural networks (CNNs), long short-term memory (LSTM), deep neural networks (DNNs), and transfer learning networks (including VGG16, VGG19, ResNet50, and ResNet101V2). A gray level co-occurrence matrix (GLCM) was employed to measure the textural characteristics. The plant disease detection platform (PDD) created a dataset of real-life grape leaf images from vineyards to improve plant disease identification. A data augmentation technique was applied to address the issue of limited images. Subsequently, the augmented dataset was used to train the models and enhance their capability to accurately identify and classify plant diseases in real-world scenarios. The analyzed outcomes indicated that the combined CNNRGB-LSTMGLCM deep network, based on the VGG16 pretrained network and data augmentation, outperformed the separate deep network and nonaugmented version features. Its validation accuracy, classification precision, recall, and F-measure are all 96.6%, with a 93.4% intersection over union and a loss of 0.123. Furthermore, the software developed through the proposed approach holds great promise as a rapid tool for diagnosing grapevine diseases in less than one minute. The framework of the study shows potential for future expansion to include various types of trees. This capability can assist farmers in early detection of tree diseases, enabling them to implement preventive measures.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning

Elsherbiny,

Elaraby,

Alahmadi

et al. 2024

Plants

Self Cite

View full text Add to dashboard Cite

show abstract

“…The author's previously reported ML classifier [22] was able to detect water stress with an accuracy of 99.54%, but it was unable to distinguish between different levels of stress. In contrast, the works of [36][37][38] proposed deep learning approaches to detect crop water stress from images captured, which showed particularly promising results. However, the performance of their models remains to be tested under different luminosity conditions.…”

Section: Discussionmentioning

confidence: 99%

A deep neural network with electronic nose for water stress prediction in Khasi Mandarin Orange plants

Sharma,

Barkataki,

Sarma

2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

Water stress is a significant environmental factor that hampers plant productivity and leads to various physiological and biological changes in plants. These include modifications in stomatal conductance and distribution, alteration of leaf water potential & turgor loss, altered chlorophyll content, and reduced cell expansion and growth. Additionally, water stress induces changes in the emission of volatile organic compounds across different parts of the plants. This study presents the development of an electronic nose (E-nose) system integrated with a deep neural network (DNN) to detect the presence and levels of water stress induced in Khasi Mandarin Orange plants. The proposed approach offers an alternative to conventional analytical methods that demand expensive and complex laboratory facilities. The investigation employs the leaf relative water content (RWC) estimation, a conventional technique, to evaluate water stress induction in the leaves of 20 plants collected over a span of 9 days after stopping irrigation. Supervised pattern recognition algorithms are trained using the results of RWC measurement, categorising leaves into non-stressed or one of four stress levels based on their water content. The dataset used for training and optimising the DNN model consists of 27 940 samples. The performance of the DNN model is compared to traditional machine learning methods, including linear and radial basis function support vector machines, k-nearest neighbours, decision tree, and random forest. From the results, it is seen that the optimised DNN model achieves the highest accuracy of 97.59% in comparison to other methods. Furthermore, the model is validated on an unseen dataset, exhibiting an accuracy of 97.32%. The proposed model holds the potential to enhance agricultural practices by enabling the detection and classification of water stress in crops, thereby aiding in water management improvements and increased productivity.

show abstract

“…Previous studies (Elmetwalli et al, 2022;Elsayed et al, 2021) have underscored the necessity of various practices, including feature filtration and model hyperparameter adjustment, to enhance regression approaches for precise prediction, yielding outcomes surpassing expectations. Additionally, the superior performance of deep learning algorithms in classification tasks is attributed to four primary factors: optimal feature selection for color space images, integration of image data with environmental information about plants, implementation of data augmentation techniques, and fusion of multiple trained deep networks (Elsherbiny et al, 2022).…”

Section: Outcomes Of Dt Modelmentioning

confidence: 99%

Employing Machine Learning Approaches and Multivariate Analysis to Assess Groundwater Quality for Irrigation in the Mornag Plain, Tunisia

Hfaiedh,

Gaagai,

Moussa

et al. 2024

Preprint

Self Cite

View full text Add to dashboard Cite

The crucial assessment of water quality in the Mornag Plain, Tunisia, is fundamental for reservoir management, ensuring suitability for consumption, and preserving environmental integrity. Employing a diverse range of methodologies, such as water quality indices (WQIs), statistical analyses, geographic information systems (GIS), and decision tree (DT) model, provided a nuanced understanding of the compositional attributes of groundwater designated for irrigation. Detected categories of water, for instance Na-Cl, Ca-Mg-SO4, and a combination of Ca-Mg-Cl/SO4, displayed unique chemical signatures. These patterns were shaped by diverse processes including interactions between water and rock, the breakdown of dolomite, the concentration of minerals through evaporation, the swapping of ions, and human impact. Evaluating groundwater's suitability for irrigation purposes by employing measures like Na%, SAR, SSP, and MH, demonstrated that a significant portion of the samples conformed to approved norms. However, the analysis revealing 65.6% of the IWQI and every instance of PS falling within the spectrum of high to severe constraints, as well as ranging from detrimental to unsatisfactory classes, underscores the obstacles in sustaining superior irrigation water standards. The predictive model, DT, demonstrated robust results in forecasting all water quality indices. The DT-HyC-9 model stood out as the top performer in prediction accuracy, demonstrating a robust correlation with prime factors affecting IWQI, as shown by substantial R2 metrics in both the training and evaluation phases. Likewise, the DT-HyC-3 approach showcased remarkable precision in forecasting IWQI, highlighting the critical role of three essential factors. These results provide crucial guidance for policymakers engaged in managing water quality, laying the groundwork for the sustainable management of water resources within the Mornag Plain. The integration of advanced methodologies and predictive models enhances the understanding of groundwater dynamics, facilitating informed decision-making for the region's water sustainability.

show abstract

A novel hybrid deep network for diagnosing water status in wheat crop using IoT-based multimodal data

Cited by 18 publications

References 38 publications

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning

Rapid Grapevine Health Diagnosis Based on Digital Imaging and Deep Learning

A deep neural network with electronic nose for water stress prediction in Khasi Mandarin Orange plants

Employing Machine Learning Approaches and Multivariate Analysis to Assess Groundwater Quality for Irrigation in the Mornag Plain, Tunisia

Contact Info

Product

Resources

About