Detection of a Potato Disease (Early Blight) Using Artificial Intelligence

This study evaluated the potential of using machine vision in combination with deep learning (DL) to identify the early blight disease in real-time for potato production systems. Four fields were selected to collect images (n = 5199) of healthy and diseased potato plants under variable lights and shadow effects. A database was constructed using DL to identify the disease infestation at different stages throughout the growing season. Three convolutional neural networks (CNNs), namely GoogleNet, VGGNet, and EfficientNet, were trained using the PyTorch framework. The disease images were classified into three classes (2-class, 4-class, and 6-class) for accurate disease identification at different growth stages. Results of 2-class CNNs for disease identification revealed the significantly better performance of EfficientNet and VGGNet when compared with the GoogleNet (FScore range: 0.84–0.98). Results of 4-Class CNNs indicated better performance of EfficientNet when compared with other CNNs (FScore range: 0.79–0.94). Results of 6-class CNNs showed similar results as 4-class, with EfficientNet performing the best. GoogleNet, VGGNet, and EfficientNet inference time values ranged from 6.8–8.3, 2.1–2.5, 5.95–6.53 frames per second, respectively, on a Dell Latitude 5580 using graphical processing unit (GPU) mode. Overall, the CNNs and DL frameworks used in this study accurately classified the early blight disease at different stages. Site-specific application of fungicides by accurately identifying the early blight infected plants has a strong potential to reduce agrochemicals use, improve the profitability of potato growers, and lower environmental risks (runoff of fungicides to water bodies).

Download Full-text

Impact of potato psyllid density and timing of infestation on Zebra chip disease expression in potato plants

Plant Protection Science ◽

10.17221/186/2015-pps ◽

2016 ◽

Vol 52 (No. 4) ◽

pp. 262-269 ◽

Cited By ~ 2

Author(s):

Gao Feng ◽

Zhao Zi-Hua ◽

Jifon John ◽

Liu Tong-Xian

Keyword(s):

Tuber Yield ◽

Potato Crop ◽

Growth Stages ◽

Potato Psyllid ◽

Zebra Chip ◽

Potato Plants ◽

Zebra Chip Disease ◽

Crop Development ◽

The Impact ◽

Different Growth Stages

The impact of vector density and timing of infestation on potato were investigated. Healthy potato plants at different growth stages (4, 5, and 7 weeks after germination) were exposed separately to four different B. cockerelli densities (0, 5, 20, and 40 psyllids per cage) in field cages and Zebra chip (ZC) symptoms, leaf photosynthetic rates, tuber yield, and total nonstructural carbohydrate accumulation in leaves and tubers of healthy and B. cockerelli-infested plants were monitored. Potato psyllid nymph and egg populations reached a seasonal peak at 6 weeks after the exposure to insect. Younger plants at 4-week growth stage after germination were more susceptible to B. cockerelli infestation and ZC expression than older plants. As few as five B. cockerelli adults were enough to transmit the ZC pathogen and cause ZC expression both in foliage and tuber. At the density of 20 psyllids per cage, more than 50% of plants showed ZC symptoms in tubers. Furthermore, B. cockerelli infestation reduced leaf photosynthesis rates (P<sub>n</sub>), resulting in less starch and more reducing sugars in tubers, and hence reduced tuber weight and yield, especially when psyllid infestation occurred at the early growth stages. The results indicate that early B. cockerelli infestation of younger plants was associated with more severe ZC expression in both foliage and tubers, leading to earlier dead plants. The data suggest that strategies for controlling B. cockerelli during early potato crop development could thus lessen the severity of ZC development.

Download Full-text

The Effectiveness of Endophytic Fungi Origin of Potato Plant Roots in Coffee Skin Compost Media to Suppress Development of Potato Leaf Disease (Phytophtora infestans)

Budapest International Research in Exact Sciences (BirEx) Journal ◽

10.33258/birex.v2i1.760 ◽

2020 ◽

Vol 2 (1) ◽

pp. 101-105

Author(s):

Anna Fitriana ◽

Lukman Hakim ◽

Marlina Marlina

Keyword(s):

Experimental Method ◽

Endophytic Fungi ◽

Potato Plant ◽

Potato Production ◽

Leaf Blight ◽

Plant Roots ◽

Potato Leaf ◽

Potato Plants ◽

Pathogen Attack ◽

Blight Disease

Potato leaf blight is caused by Phytophthora infestans fungus is one of the important diseases in potato plants. The decrease in potato production due to P. infestans can reach 90%. Until now, P. infestans pathogen attack is an important problem and there is no fungicide that is really effective against the disease. This study aims to examine the effectiveness of endophytic fungi from potato roots in suppressing the development of P. infestans potato leaf blight disease carried out at University Farm Stasiun Riset Bener Meriah (UFBM) Syiah Kuala University Tunyang Village, Timang Gajah District, Bener Meriah Regency from May to October 2014. The method used is the experimental method. The results of this study indicate that endophytic fungi from the roots of potato plants in coffee skin compost media can suppress the development of leaf blight caused by P. infestans, endophytic fungi from potato plant roots in coffee skin compost media. The best results were found in B9 endophytic fungi isolates with the intensity of the pathogen attack P. infestans 48.00%, the intensity of damage to potato plants due to pathogen P. infestans and 2.60%, the weight of healthy tubers 332.4 grams.

Download Full-text

Effect of Soil Temperature at Different Growth Stages on Growth and Development of Potato Plants 1

Agronomy Journal ◽

10.2134/agronj1966.00021962005800020014x ◽

1966 ◽

Vol 58 (2) ◽

pp. 169-171 ◽

Cited By ~ 37

Author(s):

Eliot Epstein

Keyword(s):

Soil Temperature ◽

Growth And Development ◽

Growth Stages ◽

Potato Plants ◽

Different Growth Stages

Download Full-text

169 Progress in the Development of a Sustainable Production System for Fresh-market Tomatoes

HortScience ◽

10.21273/hortsci.34.3.471c ◽

1999 ◽

Vol 34 (3) ◽

pp. 471C-471 ◽

Cited By ~ 1

Author(s):

D.J. Mills ◽

C.B. Coffman ◽

J.R. Teasdale ◽

J.D. Anderson ◽

K.L. Everts

Keyword(s):

Disease Management ◽

Early Blight ◽

Production Systems ◽

Hairy Vetch ◽

Fresh Market ◽

Foliar Disease ◽

Black Plastic ◽

Marketable Fruit ◽

Blight Disease ◽

Farm Inputs

In the production of fresh-market vegetables, off-farm inputs, such as, plastic, nitrogen fertilizer, fungicides, insecticides, and herbicides are routinely used. One aim of the sustainable agriculture program at the Beltsville Agricultural Research Center is to develop systems that reduce these inputs. We have completed the second year of a study designed to examine foliar disease progress, foliar disease management, and marketable fruit yield in staked fresh-market tomatoes grown in low- and high-input production systems. Specifically, four culture practices (black plastic mulch, hairy vetch mulch, dairy manure compost, and bare ground) were compared in conjunction with three foliar disease management treatments (no fungicide, weekly fungicide, and a foliar disease forecasting model, TOMCAST). Within all culture practices, use of the TOMCAST model reduced fungicide input nearly 50%, compared with the weekly fungicide treatment, without compromising productivity or disease management. With regard to disease level, a significant reduction of early blight disease severity within the hairy vetch mulch was observed in 1997 in relation to the other culture practices. Early blight disease severity within the black plastic and hairy vetch mulches was significantly less than that observed in the bare ground and compost treatments in 1998. In addition, despite a 50 % reduction in synthetic nitrogen input, the hairy vetch mulch generated yields of marketable fruit comparable to or greater than the other culture practices. It appears that low-input, sustainable, production systems can be developed that reduce the dependence on off-farm inputs of plastic, nitrogen fertilizer, and pesticides, yet generate competitive yields.

Download Full-text

Grape Bunch Detection at Different Growth Stages Using Deep Learning Quantized Models

Agronomy ◽

10.3390/agronomy11091890 ◽

2021 ◽

Vol 11 (9) ◽

pp. 1890

Author(s):

André Silva Aguiar ◽

Sandro Augusto Magalhães ◽

Filipe Neves dos Santos ◽

Luis Castro ◽

Tatiana Pinho ◽

...

Keyword(s):

Deep Learning ◽

Low Power ◽

Agricultural Sector ◽

Early Stage ◽

Low Cost ◽

Confidence Score ◽

Growth Stages ◽

Processing Unit ◽

Single Shot ◽

Different Growth Stages

The agricultural sector plays a fundamental role in our society, where it is increasingly important to automate processes, which can generate beneficial impacts in the productivity and quality of products. Perception and computer vision approaches can be fundamental in the implementation of robotics in agriculture. In particular, deep learning can be used for image classification or object detection, endowing machines with the capability to perform operations in the agriculture context. In this work, deep learning was used for the detection of grape bunches in vineyards considering different growth stages: the early stage just after the bloom and the medium stage where the grape bunches present an intermediate development. Two state-of-the-art single-shot multibox models were trained, quantized, and deployed in a low-cost and low-power hardware device, a Tensor Processing Unit. The training input was a novel and publicly available dataset proposed in this work. This dataset contains 1929 images and respective annotations of grape bunches at two different growth stages, captured by different cameras in several illumination conditions. The models were benchmarked and characterized considering the variation of two different parameters: the confidence score and the intersection over union threshold. The results showed that the deployed models could detect grape bunches in images with a medium average precision up to 66.96%. Since this approach uses low resources, a low-cost and low-power hardware device that requires simplified models with 8 bit quantization, the obtained performance was satisfactory. Experiments also demonstrated that the models performed better in identifying grape bunches at the medium growth stage, in comparison with grape bunches present in the vineyard after the bloom, since the second class represents smaller grape bunches, with a color and texture more similar to the surrounding foliage, which complicates their detection.

Download Full-text

A Review of Common Liverwort Control Practices in Container Nurseries and Greenhouse Operations

HortTechnology ◽

10.21273/horttech04652-20 ◽

2020 ◽

Vol 30 (4) ◽

pp. 471-479

Author(s):

Manjot Kaur Sidhu ◽

Roberto G. Lopez ◽

Sushila Chaudhari ◽

Debalina Saha

Keyword(s):

Production Systems ◽

Ornamental Plants ◽

Current Control ◽

Marchantia Polymorpha ◽

Growth Stages ◽

Growing Medium ◽

Production Environments ◽

Container Nurseries ◽

Different Growth Stages ◽

Container Production

Common liverwort (Marchantia polymorpha) is a primitive, spore-bearing bryophyte that thrives in containerized ornamental crop propagation and production environments. It is one of the major weed problems in container nurseries and greenhouses because it competes with ornamental plants for soil/growing medium, nutrients, water, space, and oxygen within the container. As a result, its presence can reduce the overall quality and market value of the ornamental crop. Once established in nurseries and greenhouses, it spreads rapidly because of its ability to propagate both asexually and sexually. Currently, no effective methods of controlling common liverwort in container production systems are available because a significant knowledge gap exists. Therefore, research is needed to determine whether organic mulches (types, depths, moisture holding capacity, and particle size), biopesticides, and strategic placement of fertilizers within containers suppress or inhibit common liverwort growth and development. In addition, newer chemicals (both synthetic and organic) and combinations need to be tested on different growth stages of common liverwort. The objective of this review was to summarize previous and current research related to common liverwort control in container production, and to identify areas where additional research is needed either to improve current control methods or to develop new ones.

Download Full-text

Correlation coefficient between early blight severity, infection rates and meteorological factors in potato under different fungicidal spray

Journal of AgriSearch ◽

10.21921/jas.v5i01.11133 ◽

2018 ◽

Vol 5 (01) ◽

Author(s):

AJAY M. KUMAR ◽

S. K. SINGH ◽

NARENDER KUMAR ◽

VIPIN KUMAR ◽

MAHESH SINGH ◽

...

Keyword(s):

Minimum Temperature ◽

Early Blight ◽

Alternaria Solani ◽

Potato Production ◽

Significant Negative Correlation ◽

Maximum Temperature ◽

Progress Curve ◽

Severe Constraint ◽

Blight Disease ◽

Year 2013

Early blight caused by Alternaria solani is a severe constraint in potato production. The severity of this disease has been increasing day by day for last few years in India due to changes in weather. Disease severity and area under disease progress curve (AUDPC) was recorded in each treatment plot. The early blight disease had significant negative correlation with maximum relative humidity during 2012-13 and in year 2013-14 minimum temperature was significantly correlated. The severity of early blight showed significant positive correlation with maximum temperature and highly significant positive correlations with sun shine hours in year 2013-14 in all tested treatments. The study showed that minimum temperature and rainfall revealed negative but non-significant correlation in all treatments except untreated control in year 2012-13. The maximum tuber yield 223.70 and 222.00 q/ha in first and second years, respectively, were recorded with spray of Fenamidone @ 0.2% at disease initiation and 2nd spray of Mancozeb @ 0.25% followed by Mancozeb @ 0.25% at 15 days intervals in both respective years.

Download Full-text