skip to main content
US FlagAn official website of the United States government
dot gov icon
Official websites use .gov
A .gov website belongs to an official government organization in the United States.
https lock icon
Secure .gov websites use HTTPS
A lock ( lock ) or https:// means you've safely connected to the .gov website. Share sensitive information only on official, secure websites.

Explore Research Products in the PAR
It may take a few hours for recently added research products to appear in PAR search results.


Title: A Transfer Learning-Based Deep Convolutional Neural Network for Detection of Fusarium Wilt in Banana Crops
During the 1950s, the Gros Michel species of bananas were nearly wiped out by the incurable Fusarium Wilt, also known as Panama Disease. Originating in Southeast Asia, Fusarium Wilt is a banana pandemic that has been threatening the multi-billion-dollar banana industry worldwide. The disease is caused by a fungus that spreads rapidly throughout the soil and into the roots of banana plants. Currently, the only way to stop the spread of this disease is for farmers to manually inspect and remove infected plants as quickly as possible, which is a time-consuming process. The main purpose of this study is to build a deep Convolutional Neural Network (CNN) using a transfer learning approach to rapidly identify Fusarium wilt infections on banana crop leaves. We chose to use the ResNet50 architecture as the base CNN model for our transfer learning approach owing to its remarkable performance in image classification, which was demonstrated through its victory in the ImageNet competition. After its initial training and fine-tuning on a data set consisting of 600 healthy and diseased images, the CNN model achieved near-perfect accuracy of 0.99 along with a loss of 0.46 and was fine-tuned to adapt the ResNet base model. ResNet50’s distinctive residual block structure could be the reason behind these results. To evaluate this CNN model, 500 test images, consisting of 250 diseased and healthy banana leaf images, were classified by the model. The deep CNN model was able to achieve an accuracy of 0.98 and an F-1 score of 0.98 by correctly identifying the class of 492 of the 500 images. These results show that this DCNN model outperforms existing models such as Sangeetha et al., 2023’s deep CNN model by at least 0.07 in accuracy and is a viable option for identifying Fusarium Wilt in banana crops.  more » « less
Award ID(s):
2239677
PAR ID:
10495998
Author(s) / Creator(s):
; ;
Publisher / Repository:
Molecular Diversity Preservation International
Date Published:
Journal Name:
AgriEngineering
Volume:
5
Issue:
4
ISSN:
2624-7402
Page Range / eLocation ID:
2381 to 2394
Format(s):
Medium: X
Sponsoring Org:
National Science Foundation
More Like this
  1. ; (, AgriEngineering)
    Plant diseases are one of the grand challenges that face the agriculture sector worldwide. In the United States, crop diseases cause losses of one-third of crop production annually. Despite the importance, crop disease diagnosis is challenging for limited-resources farmers if performed through optical observation of plant leaves’ symptoms. Therefore, there is an urgent need for markedly improved detection, monitoring, and prediction of crop diseases to reduce crop agriculture losses. Computer vision empowered with Machine Learning (ML) has tremendous promise for improving crop monitoring at scale in this context. This paper presents an ML-powered mobile-based system to automate the plant leaf disease diagnosis process. The developed system uses Convolutional Neural networks (CNN) as an underlying deep learning engine for classifying 38 disease categories. We collected an imagery dataset containing 96,206 images of plant leaves of healthy and infected plants for training, validating, and testing the CNN model. The user interface is developed as an Android mobile app, allowing farmers to capture a photo of the infected plant leaves. It then displays the disease category along with the confidence percentage. It is expected that this system would create a better opportunity for farmers to keep their crops healthy and eliminate the use of wrong fertilizers that could stress the plants. Finally, we evaluated our system using various performance metrics such as classification accuracy and processing time. We found that our model achieves an overall classification accuracy of 94% in recognizing the most common 38 disease classes in 14 crop species. 
    more » « less
  2. ; ; ; ; ; ; ; ; ; ; et al (, Plant Physiology and Biochemistry)
    The addition of biochars and nanoparticles with adsorbed Azotobacter vinelandii and Bacillus megaterium alleviated damage from Fusarium infection in both tomato (Solanum lycopersicum) and watermelon (Citrullus lanatus) plants. Tomato and watermelon plants were grown in greenhouse for 28 and 30 days (respectively) and were treated with either nanoparticles (chitosan-coated mesoporous silica or nanoclay) or varying biochars (biochar produced by pyrolysis, gasification and pyrogasification). Treatments with nanoparticles and biochars were applied in two variants – with or without adsorbed plant-growth promoting bacteria (PGPR). Chitosan-coated mesoporous silica nanoparticles with adsorbed bacteria increased chlorophyll content in infected tomato and watermelon plants (1.12 times and 1.63 times, respectively) to a greater extent than nanoclay with adsorbed bacteria (1.10 times and 1.38 times, respectively). However, the impact on other endpoints (viability of plant cells, phosphorus and nitrogen content, as well antioxidative status) was species-specific. In all cases, plants treated with adsorbed bacteria responded better than plants without bacteria. For example, the content of antioxidative compounds in diseased watermelon plants increased nearly 46% upon addition of Aries biochar and by approximately 52% upon addition of Aries biochar with adsorbed bacteria. The overall effect on disease suppression was due to combination of the antifungal effects of both nanoparticles (and biochars) and plant-growth promoting bacteria. These findings suggest that nanoparticles or biochars with adsorbed PGPR could be viewed as a novel and sustainable solution for management of Fusarium wilt. 
    more » « less
  3. ; ; ; ; ; ; ; (, Environmental Science & Technology)
    null (Ed.)
    Projected population increases over the next 30 years have elevated the need to develop novel agricultural technologies to dramatically increase crop yield, particularly under conditions of high pathogen pressure. In this study, silica nanoparticles (NPs) with tunable dissolution rates were synthesized and applied to watermelon (Citrullus lanatus) to enhance plant growth while mitigating development of the Fusarium wilt disease caused by Fusarium oxysporum f. sp. niveum. The hydrolysis rates of the silica particles were controlled by the degree of condensation or the catalytic activity of aminosilane. The results demonstrate that the plants treated with fast dissolving NPs maintained or increased biomass whereas the particle-free plants had a 34% decrease in biomass. Further, higher silicon concentrations were measured in root parts when the plants were treated with fast dissolving NPs, indicating effective silicic acid delivery. In a follow-up field study over 2.5 months, the fast dissolving NP treatment enhanced fruit yield by 81.5% in comparison to untreated plants. These findings indicate that the colloidal behavior of designed nanoparticles can be critical to nanoparticle-plant interactions, leading to disease suppression and plant health as part of a novel strategy for nanoenabled agriculture. 
    more » « less
  4. ; ; ; ; ; (, IEEE)
    This paper presents experimental results on differentiating between healthy wheat plants and plants infected with Fusarium Head Blight (FHB) based on sensing the ambient gases in the plant environment using a gravimetric electronic nose enabled by a functionalized capacitive micromachined ultrasonic transducer (CMUT) array and machine learning (ML) algorithms. The CMUT sensor array is functionalized with organic/inorganic materials to capture disease-related volatile signals. The sensor data is processed and analyzed using ML algorithms for accurate plant classification. Experimental results demonstrate the effectiveness of the proposed approach in achieving high accuracy for plant disease detection at the end of the 11th day after plant inoculation. 
    more » « less
  5. ; ; ; ; ; ; (, Microbiology Resource Announcements)
    Rokas, Antonis (Ed.)
    ABSTRACT The genomes of eighteen Fusarium isolates cultured from diseased and healthy citrus trees were sequenced, assembled, and annotated. Isolate species identification was confirmed using single marker (TEF1-alpha) phylogenetic assessment. Studies of the traits and genotypes of plant-associated isolates are important to understanding the fungal contribution to phytobiomes of citrus. 
    more » « less
  • Citation Formats
  • MLA
  • APA
  • Chicago
  • BibTeX
  • Save / Share this Record
  • Send to Email