Biotechnology for the Control of Soybean Diseases

<span lang="EN-US">Plant pathologists desire soft computing technology for accurate and reliable diagnosis of plant diseases. In this study, we propose an efficient soybean disease identification method based on a transfer learning approach by using a pre-trained convolutional neural network (CNN’s) such as AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201. The proposed convolutional neural networks were trained using 1200 plant village image dataset of diseased and healthy soybean leaves, to identify three soybean diseases out of healthy leaves. Pre-trained CNN used to enable a fast and easy system implementation in practice. We used the five-fold cross-validation strategy to analyze the performance of networks. In this study, we used a pre-trained convolutional neural network as feature extractors and classifiers. The experimental results based on the proposed approach using pre-trained AlexNet, GoogleNet, VGG16, ResNet101, and DensNet201 networks achieve an accuracy of 95%, 96.4 %, 96.4 %, 92.1%, 93.6% respectively. The experimental results for the identification of soybean diseases indicated that the proposed networks model achieves the highest accuracy</span>

Download Full-text

First Report of Fusarium proliferatum Causing Root Rot on Soybean (Glycine max) in the United States

Plant Disease ◽

10.1094/pdis-04-11-0346 ◽

2011 ◽

Vol 95 (10) ◽

pp. 1316-1316 ◽

Cited By ~ 18

Author(s):

M. M. Díaz Arias ◽

G. P. Munkvold ◽

L. F. Leandro

Keyword(s):

United States ◽

Root Rot ◽

Morphological Characteristics ◽

Dry Weight ◽

The United States ◽

Growth Stages ◽

Species Identity ◽

First Report ◽

Soybean Roots ◽

Soybean Diseases

Fusarium spp. are widespread soilborne pathogens that cause important soybean diseases such as damping-off, root rot, Fusarium wilt, and sudden death syndrome. At least 12 species of Fusarium, including F. proliferatum, have been associated with soybean roots, but their relative aggressiveness as root rot pathogens is not known and pathogenicity has not been established for all reported species (2). In collaboration with 12 Iowa State University extension specialists, soybean roots were arbitrarily sampled from three fields in each of 98 Iowa counties from 2007 to 2009. Ten plants were collected from each field at V2-V3 and R3-R4 growth stages (2). Typical symptoms of Fusarium root rot (2) were observed. Symptomatic and asymptomatic root pieces were superficially sterilized in 0.5% NaOCl for 2 min, rinsed three times in sterile distilled water, and placed onto a Fusarium selective medium. Fusarium colonies were transferred to carnation leaf agar (CLA) and potato dextrose agar and later identified to species based on cultural and morphological characteristics. Of 1,230 Fusarium isolates identified, 50 were recognized as F. proliferatum based on morphological characteristics (3). F. proliferatum isolates produced abundant, aerial, white mycelium and a violet-to-dark purple pigmentation characteristic of Fusarium section Liseola. On CLA, microconidia were abundant, single celled, oval, and in chains on monophialides and polyphialides (3). Species identity was confirmed for two isolates by sequencing of the elongation factor (EF1-α) gene using the ef1 and ef2 primers (1). Identities of the resulting sequences (~680 bp) were confirmed by BLAST analysis and the FUSARIUM-ID database. Analysis resulted in a 99% match for five accessions of F. proliferatum (e.g., FD01389 and FD01858). To complete Koch's postulates, four F. proliferatum isolates were tested for pathogenicity on soybean in a greenhouse. Soybean seeds of cv. AG2306 were planted in cones (150 ml) in autoclaved soil infested with each isolate; Fusarium inoculum was applied by mixing an infested cornmeal/sand mix with soil prior to planting (4). Noninoculated control plants were grown in autoclaved soil amended with a sterile cornmeal/sand mix. Soil temperature was maintained at 18 ± 1°C by placing cones in water baths. The experiment was a completely randomized design with five replicates (single plant in a cone) per isolate and was repeated three times. Root rot severity (visually scored on a percentage scale), shoot dry weight, and root dry weight were assessed at the V3 soybean growth stage. All F. proliferatum isolates tested were pathogenic. Plants inoculated with these isolates were significantly different from the control plants in root rot severity (P = 0.001) and shoot (P = 0.023) and root (P = 0.013) dry weight. Infected plants showed dark brown lesions in the root system as well as decay of the entire taproot. F. proliferatum was reisolated from symptomatic root tissue of infected plants but not from similar tissues of control plants. To our knowledge, this is the first report of F. proliferatum causing root rot on soybean in the United States. References: (1) D. M. Geiser et al. Eur. J. Plant Pathol. 110:473, 2004. (2) G. L. Hartman et al. Compendium of Soybean Diseases. 4th ed. The American Phytopathologic Society, St. Paul, MN, 1999. (3) J. F. Leslie and B. A. Summerell. The Fusarium Laboratory Manual. Blackwell Publishing, Oxford, UK, 2006. (4) G. P. Munkvold and J. K. O'Mara. Plant Dis. 86:143, 2002.

Download Full-text

A new proposal for automatic identification of multiple soybean diseases

Computers and Electronics in Agriculture ◽

10.1016/j.compag.2019.105060 ◽

2019 ◽

Vol 167 ◽

pp. 105060 ◽

Cited By ~ 2

Author(s):

Juliana Mariana Macedo Araujo ◽

Zelia Myriam Assis Peixoto

Keyword(s):

Automatic Identification ◽

Soybean Diseases

Download Full-text

Effects of Diseases on Soybean Yields in the United States 1996 to 2007

Plant Health Progress ◽

10.1094/php-2009-0401-01-rs ◽

2009 ◽

Vol 10 (1) ◽

pp. 24 ◽

Cited By ~ 83

Author(s):

Allen Wrather ◽

Steve Koenning

Keyword(s):

Soybean Cyst Nematode ◽

Management Strategies ◽

The United States ◽

Cyst Nematode ◽

Disease Suppression ◽

Stem Rot ◽

Soybean Yield ◽

Funding Agencies ◽

The Usa ◽

Soybean Diseases

Research must focus on management of diseases that cause extensive losses, especially when funds for research are limited. Knowledge of yield suppression caused by various soybean diseases is essential when prioritizing research. The objective of this project was to compile estimates of soybean yield suppression due to diseases in the USA from 1996 to 2007. The goal was to provide information to help funding agencies and scientists prioritize research objectives and budgets. Yield suppression due to individual diseases varied among years. Soybean cyst nematode suppressed USA soybean yield more from 1996 to 2007 than any other disease. Phytophthora root and stem rot ranked second among diseases that most suppressed yield seven of 12 years. Seedling diseases and charcoal rot also suppressed soybean yield during these years. Research and extension efforts must be expanded to provide more preventive and therapeutic disease management strategies for producers to reduce disease suppression of soybean yield. Accepted for publication 25 February 2009. Published 1 April 2009.

Download Full-text

Use of Copper-Based Pesticides to Control Fungal Diseases of Soybean in Northern Brazil

Journal of Experimental Agriculture International ◽

10.9734/jeai/2019/v33i230137 ◽

2019 ◽

pp. 1-10 ◽

Cited By ~ 1

Author(s):

Warlles Domingos Xavier ◽

João Vitor de Souza Silva ◽

Claudinei Martins Guimarães ◽

Jorge Luís Sousa Ferreira ◽

Thiago Albuquerque Turozi ◽

...

Keyword(s):

Grain Yield ◽

Fungal Diseases ◽

Brown Spot ◽

Crop Damage ◽

Soybean Rust ◽

Total Production ◽

Asian Soybean Rust ◽

Target Spot ◽

Crop Cycle ◽

Soybean Diseases

At level word fungal diseases that affect soybean crop are one of the main causes of low productivity and annual losses may reach 21% of total production. In this context, the objective of the study was to evaluate the efficiency of copper-based protectors associated with fungicides to control soybean diseases such as: asian soybean rust (Phakopsora pachyrhizi), target spot of soybean (Corynespora cassiicola) and cercospora leaf blight (Cercospora kikuchii) + frogeye leaf spot (Cercospora sojina) + brown spot (Septoria glycines), which together were considered as late-crop cycle diseases, with impact on grain yield, in the region of Aparecida do Rio Negro – TO, Brazil. Treatments were composed of different rates of copper-based pesticides associated with fungicides like Azimut® (first application), Orkestra® (second application), Ativum® (third application) and Horos® (fourth application) in soybean. Diseases were identified and crop damage evaluations on leaves were performed using LI-COR® portable meter 7 days after the fourth application. At physiological maturity, grain yield was evaluated. Combined rates of fungicides + Unizeb Gold® (1.5 kg ha-1), Difere® (0.5 L ha-1), and NHT® Copper Super at a rate higher than 0.109 L ha-1, were effective to control late crop-cycle diseases in soybean. Associated applications of fungicides + 0.219 L/ha of NHT® Copper Super reduced the severity of Asian soybean rust, target spot of soybean and late crop-cycle diseases with a greater increase in grain yield (4.5 Mg ha-1).

Download Full-text

SOYBEAN LEAF DISEASES DETECTION AND CLASSIFICATION USING RECENT IMAGE PROCESSING TECHNIQUES

International Journal of Students Research in Technology & Management ◽

10.18510/ijsrtm.2020.831 ◽

2020 ◽

Vol 8 (3) ◽

pp. 01-08

Author(s):

Arpan Singh Rajput ◽

Shailja Shukla ◽

S. S. Thakur

Keyword(s):

Image Processing ◽

Early Stage ◽

Weather Condition ◽

Plant Diseases ◽

Soybean Plant ◽

Plant Leaf ◽

Image Processing Techniques ◽

Soybean Leaf ◽

Processing Techniques ◽

Soybean Diseases

Purpose: India is an agricultural country and soybean production is one of the major sources of earning. Due to the major factors like diseases, pest attacks, and sudden changes in the weather condition, the productivity of the soybean crop decreases. Automatic detection of soybean plant diseases is essential to detect the symptoms of soybean diseases as early as they appear on the growing stage. This paper proposed a methodology for the analysis and detection of soybean plant leaf diseases using recent digital image processing techniques. In this paper, experimental results demonstrate that the proposed method can successfully detect and classify the major soybean diseases. Methodology: MatLab 18a is used for the simulation for the result and machine learning-based recent image processing techniques for the detection of the soybean leaf disease. Main Findings: The main finding of this work is to create the soybean leaf database which includes healthy and unhealthy leaves and achieved 96 percent accuracy in this work using the proposed methodology. Applications of this study: To detect soybean plant leaf diseases in the early stage in Agricultural. The novelty of this study: Self-prepared database of healthy and unhealthy images of soybean leaf with the proposed algorithm.

Download Full-text