scholarly journals Detecting cassava mosaic disease using a deep residual convolutional neural network with distinct block processing

2021 ◽  
Vol 7 ◽  
pp. e352
Author(s):  
David Opeoluwa Oyewola ◽  
Emmanuel Gbenga Dada ◽  
Sanjay Misra ◽  
Robertas Damaševičius

For people in developing countries, cassava is a major source of calories and carbohydrates. However, Cassava Mosaic Disease (CMD) has become a major cause of concern among farmers in sub-Saharan Africa countries, which rely on cassava for both business and local consumption. The article proposes a novel deep residual convolution neural network (DRNN) for CMD detection in cassava leaf images. With the aid of distinct block processing, we can counterbalance the imbalanced image dataset of the cassava diseases and increase the number of images available for training and testing. Moreover, we adjust low contrast using Gamma correction and decorrelation stretching to enhance the color separation of an image with significant band-to-band correlation. Experimental results demonstrate that using a balanced dataset of images increases the accuracy of classification. The proposed DRNN model outperforms the plain convolutional neural network (PCNN) by a significant margin of 9.25% on the Cassava Disease Dataset from Kaggle.

Plant Disease ◽  
1999 ◽  
Vol 83 (4) ◽  
pp. 398-398 ◽  
Author(s):  
F. O. Ogbe ◽  
G. I. Atiri ◽  
D. Robinson ◽  
S. Winter ◽  
A. G. O. Dixon ◽  
...  

Cassava (Manihot esculenta Crantz) is an important food crop in sub-Saharan Africa. One of the major production constraints is cassava mosaic disease caused by African cassava mosaic (ACMV) and East African cassava mosaic (EACMV) begomoviruses. ACMV is widespread in its distribution, occurring throughout West and Central Africa and in some eastern and southern African countries. In contrast, EACMV has been reported to occur mainly in more easterly areas, particularly in coastal Kenya and Tanzania, Malawi, and Madagascar. In 1997, a survey was conducted in Nigeria to determine the distribution of ACMV and its strains. Samples from 225 cassava plants showing mosaic symptoms were tested with ACMV monoclonal antibodies (MAbs) in triple antibody sandwich enzyme-linked immunosorbent assay (1). Three samples reacted strongly with MAbs that could detect both ACMV and EACMV. One of them did not react with ACMV-specific MAbs while the other two reacted weakly with such MAbs. With polymerase chain reaction (2), the presence of EACMV and a mixture of EACMV and ACMV in the respective samples was confirmed. These samples were collected from two villages: Ogbena in Kwara State and Akamkpa in Cross River State. Co-infection of some cassava varieties with ACMV and EACMV leads to severe symptoms. More importantly, a strain of mosaic geminivirus known as Uganda variant arose from recombination between the two viruses (2). This report provides evidence for the presence of EACMV in West Africa. References: (1) J. E. Thomas et al. J. Gen. Virol. 67:2739, 1986. (2) X. Zhou et al. J. Gen. Virol. 78:2101, 1997.


Insects ◽  
2020 ◽  
Vol 11 (11) ◽  
pp. 761
Author(s):  
Patrick Chiza Chikoti ◽  
Mathias Tembo ◽  
James Peter Legg ◽  
Rudolph Rufini Shirima ◽  
Habibu Mugerwa ◽  
...  

Bemisia tabaci is an important vector of cassava brown streak viruses and cassava mosaic begomoviruses, the causal agents of cassava brown streak disease and cassava mosaic disease (CMD), respectively. A study was carried out to determine the genetic variability of B. tabaci associated with cassava and the occurrence of CMD in Zambia in 2013 and 2015. Phylogenetic analysis showed the presence of only the sub-Saharan Africa 1 (SSA1) genetic group in Zambia. The SSA1 population had three population subgroups (SGs): SSA1-SG1, SSA1-SG2 and SSA1-SG3. All three SSA1 population subgroups occurred in Western Province. However, only SSA1-SG3 occurred in Eastern Province, while only SSA1-SG1 occurred in North Western and Luapula Provinces. Adult B. tabaci were most abundant in Western Province in 2013 (11.1/plant) and 2015 (10.8/plant), and least abundant (0.2/plant) in Northern Province in both 2013 and 2015. CMD was prevalent in all seven provinces surveyed, with the highest incidence recorded in Lusaka Province in both 2013 (78%) and 2015 (83.6%), and the lowest in Northern Province in both 2013 (26.6%) and 2015 (29.3%). Although SSA1-SG1 occurred at greater abundances than the other subgroups, there was no direct association demonstrated between whitefly subgroup and incidence of CMD. Establishing which B. tabaci genetic groups and populations are associated with CMD and their distribution in the country is a key factor in guiding the development of CMD control strategies for cassava-dependent households.


2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Bunmi Olasanmi ◽  
Martina Kyallo ◽  
Nasser Yao

AbstractCassava mosaic disease (CMD) is a serious threat to cassava production in sub-Saharan Africa. The use of genomic-assisted selection at the seedling trial stage would help to reduce the time for release, breeding cost, and resources used, hence increase selection efficiency in cassava breeding programs. Five cassava populations were screened for resistance to CMD during the seedling evaluation trial at 1, 3, and 5 months after planting using a scale of 1–5. The genotypes in the five populations were also screened using six molecular markers linked to the CMD2 gene. The correlation between the phenotypic and marker data was estimated. Based on Cassava Mosaic Disease Severity Score (CMDSS), between 53 and 82% of the progenies were resistant across the populations with an average of 70.5%. About 70% of the progenies were identified to be resistant to the disease across the populations with a range of 62–80% using the marker data. With both marker data and CMDSS combined, 40–60% of the progenies in each population, with an average of 52%, were identified to be resistant to CMD. There was a fairly significant correlation between the marker data and CMDSS in each cassava population with correlation coefficients ranging from 0.2024 to 0.3460 suggesting that novel genes not associated to the markers used might be involved in the resistance to CMD. The resistant genotypes identified in this study with potential for other desirable traits were selected for evaluation at the advanced trial stage thereby shortening the period required for the breeding program.


Insects ◽  
2021 ◽  
Vol 12 (10) ◽  
pp. 875
Author(s):  
Florence M. Munguti ◽  
Dora C. Kilalo ◽  
Evans N. Nyaboga ◽  
Everlyne N. Wosula ◽  
Isaac Macharia ◽  
...  

The whitefly, Bemisia tabaci (Gennadium, Hemiptera) has been reported to transmit viruses that cause cassava mosaic disease (CMD) and cassava brown streak disease (CBSD) in many parts of sub-Saharan Africa (SSA). Currently, there is limited information on the distribution, species and haplotype composition of the whitefly populations colonizing cassava in Kenya. A study was conducted in the major cassava growing regions of Kenya to address this gap. Analyses of mitochondrial DNA cytochrome oxidase 1 (mtCO1) sequences revealed the presence of four distinct whitefly species: Bemisia tabaci, Bemisia afer, Aleurodicus dispersus and Paraleyrodes bondari in Kenya. The B. tabaci haplotypes were further resolved into SSA1, SSA2 and Indian Ocean (IO) putative species. The SSA1 population had three haplogroups of SSA1-SG1, SSA-SG2 and SSA1-SG3. Application of KASP genotyping grouped the Bemisia tabaci into two haplogroups namely sub-Saharan Africa East and Southern Africa (SSA-ESA) and sub-Saharan Africa East and Central Africa (SSA-ECA). The study presents the first report of P. bondari (Bondar’s nesting whitefly) on cassava in Kenya. Bemisia tabaci was widely distributed in all the major cassava growing regions in Kenya. The increased detection of different whitefly species on cassava and genetically diverse B. tabaci mitotypes indicates a significant influence on the dynamics of cassava virus epidemics in the field. The study highlights the need for continuous monitoring of invasive whitefly species population on cassava for timely application of management practices to reduce the impact of cassava viral diseases and prevent potential yield losses.


2021 ◽  
Author(s):  
Anna Maria Szyniszewska ◽  
Patrick Chiza Chikoti ◽  
Mathias Tembo ◽  
Rabson Mulenga ◽  
Christopher Gilligan ◽  
...  

Cassava is an important food crop across sub-Saharan Africa, where production is severely inhibited by two viral diseases; cassava mosaic disease (CMD) and cassava brown streak disease (CBSD), both propagated by a whitefly vector and via human-mediated movement of infected cassava stems. There is limited information on growers’ behaviour related to movement of planting material, as well as growers’ perception and awareness of cassava diseases, despite the importance of these factors for disease control. This study surveyed a total of 96 cassava subsistence growers and their fields across five provinces in Zambia between 2015 and 2017, to address these knowledge gaps. CMD symptoms were observed in 81.6% of the fields, with an average incidence of 52% across the infected fields. No CBSD symptoms were observed. Most growers used planting materials from their own (94%) or nearby (<10 km) fields of family and friends, although several large transactions over longer distances (10-350 km) occurred with friends (15 transactions), markets (1), middlemen (5), and NGOs (6). Information related to cassava diseases and certified clean (disease-free) seed reached only 48% of growers. The most frequent sources of information related to cassava diseases included nearby friends, family and neighbours, whilst extension workers were the most highly preferred source of information. These data provide a benchmark on which to plan management approaches to controlling CMD and CBSD, which should include clean propagation material, increasing growers' awareness of the diseases and increasing information provided to farmers (specifically disease symptom recognition and disease management options).


Author(s):  
L. N. Navangi ◽  
S. M. Githiri ◽  
E. M. Ateka ◽  
E. Kanju ◽  
T. L. Munga ◽  
...  

Cassava (Manihot esculenta Crantz) production in sub-Saharan Africa (SSA) is constrained by the two biotic constraints namely, cassava mosaic disease (CMD) and cassava brown streak disease (CBSD). The aim of this study was to evaluate elite cassava genotypes for variation in agronomical traits, correlate them to CMD and CBSD parameters and identify stable genotypes in Alupe, Kakamega and Kibos in Western Kenya. Twenty three (23) elite cassava genotypes that had shown resistance to either one or both of CMD and CBSD in Eastern Africa were evaluated. The trial was conducted using an alpha lattice balanced design with twenty three (23) genotypes, replicated three times at Alupe, Kakamega and Kibos in Western Kenya for an extended cropping cycle between 2016 and 2017. Results showed significant differences (P ≤ 0.05) between genotypes and location (or agro-ecology), but not interaction (P ≥ 0.05), for all the agronomic performance parameters evaluated. All the 23 cassava genotypes evaluated across the three locations had mean cyanide potential levels ranging from of 3.00–6.00 and were therefore, sweet and not bitter. The significant but negative relationship between CMD and CBSD incidence and severity with agronomic performance implied that their relationship was inverse. Confirmation of stability for agronomic performance was achieved through AMMI analysis, using AMMI stability value (ASV). Stable genotypes based on AMMI stability values (ASV) for fresh root yield across Alupe, Kakamega and Kibos were KBH/2002/066, Kibandameno (a local standard check), NASE-18, Kizimbani and NASE-3. These genotypes need to be further evaluated in more environments to assess their wider adaptability and stability.


2019 ◽  
Author(s):  
Anna Maria Szyniszewska ◽  
Patrick Chiza Chikoti ◽  
Mathias Tembo ◽  
Rabson Mulenga ◽  
Frank van den Bosch ◽  
...  

AbstractCassava is an important food crop for most small-holder growers across sub-Saharan Africa, where production is largely limited by the presence of two viral diseases: cassava mosaic disease (CMD) and cassava brown streak disease (CBSD), both propagated by a vector whitefly and via human-mediated movement of infected cassava stems. Despite its importance, there is limited knowledge of growers’ behaviour related to planting material movement, as well as growers’ perception and knowledge of cassava diseases, which have major implications for disease spread and control. This study was conducted to address this knowledge gap by surveying small-holder growers in Zambia. A total of 96 subsistence cassava growers across five provinces were surveyed between 2015 and 2017. Most growers interviewed used planting materials from their own fields (94%) or those of nearby (<10 km) family and friends, although some large transactions with markets, middlemen, and NGOs occurred over longer distances. At the same time, information related to cassava diseases and uninfected planting material only reached 48% of growers, where those with access to information were more concerned about the disease. These data provide a basis for future planning of cassava clean seed systems to control virus diseases, emphasising the critical role of grower knowledge, and consequently education, in success of these systems. In particular, we highlight the importance of extension workers in this education process, as well as farmer’s groups and the media.


2017 ◽  
Vol 107 (10) ◽  
pp. 1229-1242 ◽  
Author(s):  
A. M. Szyniszewska ◽  
C. Busungu ◽  
S. B. Boni ◽  
R. Shirima ◽  
H. Bouwmeester ◽  
...  

To improve understanding of the dynamics of the cassava mosaic disease (CMD) pandemic front, geospatial approaches were applied to the analysis of 3 years’ data obtained from a 2-by-2° (approximately 222-by-222 km) area of northwestern Tanzania. In total, 80 farmers’ fields were assessed in each of 2009, 2010, and 2011, with 20 evenly distributed fields per 1-by-1° quadrant. CMD-associated variables (CMD incidence, CMD severity, vector-borne CMD infection, and vector abundance) increased in magnitude from 2009 to 2010 but showed little change from 2010 to 2011. Increases occurred primarily in the two westernmost quadrants of the study area. A pandemic “front” was defined by determining the values of CMD incidence and whitefly abundance where predicted disease gradients were greatest. The pandemic-associated virus (East African cassava mosaic virus-Uganda) and vector genotype (Bemisia tabaci sub-Saharan Africa 1–subgroup 1) were both present within the area bounded by the CMD incidence front but both also occurred ahead of the front. The average speed and direction of movement of the CMD incidence front (22.9 km/year; southeast) and whitefly abundance front (46.6 km/year; southeast) were calculated, and production losses due to CMD were estimated to range from US$4.3 million to 12.2 million.


Sign in / Sign up

Export Citation Format

Share Document