Banana Xanthomonas Wilt Research Articles

Review On: Impact of Genetic Engineering in Biotic Stresses Resistance Crop Breeding

Genetic engineering is recombinant DNA technology that involves artificial addition, deletion or rearrangement of sequences of bases in DNA to alter form and function of organism. It complement plant breeding efforts by increasing the diversity of genes and germplasm available for incorporation into crops and by shortening the time required for the production of new varieties and hybrids. As the conventional breeding is restricted to sexually compatible crop species, time intensive and random process the genetic engineering is an alternative method to develop promising varieties with higher resistance to biotic stresses. Genetic engineering facilitates development of biotic stress resistant crops by expressing bacterial δ-endotoxins and vegetative insecticidal proteins, plant genes like lectins, protease inhibitors, RNA interference and genome editing through CRISPR Cas9. Bt-crops (maize, cotton Tobacco, Soyabean and etc), Bacillus thuringiensis (BT) are insect-resistant crops and the most outstanding achievements through genetic engineering of insecticidal protein coding genes from soil bacterium B. thuringiensis. Several studies indicated that genetically modified crops have reduced pesticide quantity by 37% and pesticide cost by 39% and on average crop yields increased by 21%. Transgenic lines of banana and tomato have showed resistance to Banana Xanthomonas wilt (BXW) and Fusarium wilt, respectively. In summary, Genetic engineering has played pivotal role in developing biotic resistance cultivars and cultivation area of these crops is growing fast each year, which indicates understanding and applying this new technologies offer more effective solutions against evolving biotic stress.

Control of Bacterial Diseases of Banana Using CRISPR/Cas-Based Gene Editing.

Banana is an important staple food crop and a source of income for smallholder farmers in about 150 tropical and sub-tropical countries. Several bacterial diseases, such as banana Xanthomonas wilt (BXW), blood, and moko disease, cause substantial impacts on banana production. There is a vast yield gap in the production of bananas in regions where bacterial pathogens and several other pathogens and pests are present together in the same field. BXW disease caused by Xanthomonas campestris pv. musacearum is reported to be the most destructive banana disease in East Africa. The disease affects all the banana varieties grown in the region. Only the wild-type diploid banana, Musa balbisiana, is resistant to BXW disease. Developing disease-resistant varieties of bananas is one of the most effective strategies to manage diseases. Recent advances in CRISPR/Cas-based gene editing techniques can accelerate banana improvement. Some progress has been made to create resistance against bacterial pathogens using CRISPR/Cas9-mediated gene editing by knocking out the disease-causing susceptibility (S) genes or activating the expression of the plant defense genes. A synopsis of recent advancements and perspectives on the application of gene editing for the control of bacterial wilt diseases are presented in this article.

The contestations of diversity, culture and commercialization: why tissue culture technology alone cannot solve the banana Xanthomonas wilt problem in central Uganda

Several initiatives by the Government of Uganda, Research Institutes and CGIAR centers have promoted the use of tissue culture (TC) banana technology as an effective means of providing clean planting material to reduce the spread of Banana Xanthomonas wilt (BXW) but its uptake is still low. We examine factors that constrain uptake of tissue culture banana planting materials in central Uganda by considering the cultural context of banana cultivation. Data were collected using eight focus group discussions involving 64 banana farmers and 10 key informant interviews and subjected to thematic analysis. Results showed that banana cultivars in the study communities were important for food, cultural practices and medicine. Cultivars supplied through TC were based on commercial considerations focusing on market value and household income and insufficient attention was given to their cultural importance. Farmers regard banana from TC planting material to be incompatible with their tastes and preferences for traditional food and drinks, culture and medicine. Furthermore, the plantlets are perceived as complicated to use, and farmers report requiring more knowledge and information on how to plant and maintain the plantlets on-farm. In these aspects, TC planting material does not align with cultural values linked to societal welfare. Future efforts aimed at controlling pests and diseases would benefit from more location-specific and holistic approaches that integrate cultural dimensions alongside planting material hygiene, quality and vigor.

A mathematical Model to assess the Role of Neglected Control Techniques in the Dynamics of Banana Xanthomonas Wilt Disease

A mathematical Model to assess the Role of Neglected Control Techniques in the Dynamics of Banana Xanthomonas Wilt Disease

UAV-Based Mapping of Banana Land Area for Village-Level Decision-Support in Rwanda

Crop monitoring is crucial to understand crop production changes, agronomic practice decision-support, pests/diseases mitigation, and developing climate change adaptation strategies. Banana, an important staple food and cash crop in East Africa, is threatened by Banana Xanthomonas Wilt (BXW) disease. Yet, there is no up-to-date information about the spatial distribution and extent of banana lands, especially in Rwanda, where banana plays a key role in food security and livelihood. Therefore, delineation of banana-cultivated lands is important to prioritize resource allocation for optimal productivity. We mapped the spatial extent of smallholder banana farmlands by acquiring and processing high-resolution (25 cm/px) multispectral unmanned aerial vehicles (UAV) imageries, across four villages in Rwanda. Georeferenced ground-truth data on different land cover classes were combined with reflectance data and vegetation indices (NDVI, GNDVI, and EVI2) and compared using pixel-based supervised multi-classifiers (support vector models-SVM, classification and regression trees-CART, and random forest–RF), based on varying ground-truth data richness. Results show that RF consistently outperformed other classifiers regardless of data richness, with overall accuracy above 95%, producer’s/user’s accuracies above 92%, and kappa coefficient above 0.94. Estimated banana farmland areal coverage provides concrete baseline for extension-delivery efforts in terms of targeting banana farmers relative to their scale of production, and highlights opportunity to combine UAV-derived data with machine-learning methods for rapid landcover classification.

Does the accessibility of a farmer predict the delivery of extension services? Evidence from Rwanda

To determine whether a farmer’s accessibility predicts the delivery of extension services, this study used banana Xanthomonas wilt (BXW) disease-management advisory as a typical case with which to collect extension-delivery information from 690 farmers, distinguished by their respective accessibility. Cost–distance analysis was applied to define each farmer’s accessibility. The results revealed that a farmer’s accessibility does not predict extension delivery to that farmer in all forms of the examined extension parameters. Significant factors contributing to the delivery of extension services included BXW incidence and membership in Twigire Muhinzi groups. Given the results of this paper, I argue that the nature of the advisory and the type of farmers’ networks are more predictive factors than physical proximity. The findings of this study support the argument that the group-based extension approach is more effective; therefore, the Twigire Muhinzi initiative is recommended as a suitable model for delivering agricultural advisory services. The absence of a significant association between extension delivery and distance (accessibility) suggests that extension agents do not follow the first-reached, first-served rule but instead follow the problem-solving-based approach.

Single Stem Rouging of Banana Xanthomonas Wilt Infected Plants for Orchard Rehabilitation

Banana Xanthomonas Wilt (BXW), caused by Xanthomonas campestris pv. musacearum (Xcm), a devastating disease, causes up to 100% loss and affects all banana varieties. The disease is widespread in East and Central Africa region. Study objective was to evaluate the performance of single stem rouging options for rehabilitation of severely affected banana orchard. Five single stem rouging options were implemented in banana orchard with 80% BXW severity in Western Kenya. The options included rouging of infected banana plants; uprooting, cutting at the base, injecting 20 ml of glyphosate herbicide at the soil base of the pseudostem, uprooting the whole stool and control leaving the infected stools. Initial visual assesment before implementation of the orchard was over 80% infection. Later samples were collected for diagnosis of ten plants per treatment from different plant parts and were subjected to ELISA and PCR procedures for confirmion of the presence of Xcm. Rouging options was implemented for one year. During and after experimentation periodic visual assesment of BXW incidence and severity reduced. Results of ELISA assays and PCR results indicated Xanthomonas was present on banana plants. Rouging the infected banana stems by cutting at the base, uprooting and injection of herbicide reduced BXW incidence within six months. Xanthomonas, an inhibiting bacteria cannot surve without host and by killing the banana plant the Xanthomonas dies. Yields were recovered from the rehabilitated orchard within one year. Banana orchard highly infected with BXW was effectively rehabilitated.

Has Continued Exposure to Banana Xanthomonas Wilt Worsened Farmers’ Welfare Over Time? Evidence From Banana-Producing Households in Uganda

The livelihoods of millions of banana-farming households have been affected by Banana Xanthomonas Wilt (BXW) in Uganda for nearly two decades. The disease has no known cure, all banana cultivars grown are susceptible to it and it is endemic in all banana-producing regions in the country. This study analysed the long-term impact of the disease on the livelihoods of banana-producing households. Using a balanced panel dataset of 1,056 households, which were visited in 2015 and revisited in 2018, provides the opportunity to empirically measure the long-term consequences of the disease on farmers’ economic wellbeing in the four major banana growing regions in Uganda. We find striking results pertinent to disease incidence, success in disease management, household income and poverty when deploying BXW control practices. Although the disease has remained present in farmers’ fields, there is a significant reduction in household poverty levels. Results show that some farmers expanded the production of beans and coffee without encroaching on their banana plantations. Increase in bean production was largely through intercropping. Investment in coffee was constrained by land ownership, hence only a viable venture for the wealthy farmers who own bigger pieces of land. Land-poor farmers continued to rely on bananas for their livelihoods. Consistent participation in disease management training significantly influenced adoption of the cultural control practices. Consequently, farming households that systematically adopted these practices were able to maintain low levels of disease incidence, improve productivity by 438 kg/ha/year and increased their daily and annual household income by US$1.75 and UGX 2.383 million (US$648), respectively. The findings suggest that banana is an important crop to smallholder farmers and expansion into other cash crops requires bigger resource outlays, and that despite continued exposure to BXW, farmers’ income increased over time. Farmers should continuously and systematically use the recommended control practices to avoid BXW resurgence and, consequently, a reduction in their income.

Livelihood assets\u2019 influence on Ugandan farmers\u2019 control practices for Banana Xanthomonas Wilt (BXW)

This study analyzes the influence of livelihood assets on Ugandan farmers’ decisions to control Banana Xanthomonas Wilt (BXW), a disease that has threatened banana production and the livelihoods of Ugandan farmers since 2001. The BXW control strategy is based on the simultaneous implementation of four cultural practices: de-budding, infected plant removal, disinfecting tools, and using clean planting materials. The Sustainable Rural Livelihood (SRL) framework represents a very useful theoretical architecture for examining the interplay between livelihood systems of rural Ugandan households and the external context. Empirically, this study applies a double-hurdle model with the base assumption that the two adoption decision processes (whether to adopt and the intensity of adoption of the cultural practices) are separate. Results indicate that the vulnerability context and the human, social, natural, and physical capitals are the factors that drive farmers to adopt the identified strategy. Farmers’ decisions about the extent of adoption are instead negatively influenced by natural capital and positively associated with social capital. These findings highlight the importance of supporting the improvement of livelihood assets to enable tailored support to farmers. It is particularly important to support the social and natural capitals that facilitate information exchange and provide critical resources for the adoption of the BXW control strategy.

A Public Bad Game Method to Study Dynamics in Socio-Ecological Systems (Part II): Results of Testing Musa-Game in Rwanda and Adding Emergence and Spatiality to the Analysis

This article is the second in a series of two and presented findings from field-testing an experimental boardgame (Musa-game) with banana farmers in four villages in Eastern Rwanda. The conceptualization and design of the Musa-game were described in Part I. Musa-game gives insights into how farmers’ individual and collective decision-making and actions regarding management of a public bad interplay with other factors and characteristics of the socio-ecological system (SES). A public bad is a non-rivalrous, non-excludable issue that causes loss of social-welfare of individuals and communities. The method contributes contextual understanding about the emergence of phenomena that arise from the interactions between human and non-human actors. Musa-game was framed to study one public bad challenge in particular: the infectious crop disease Banana Xanthomonas Wilt disease (BXW). Findings increased the knowhow about the emergence and governance of conditions that hinder or enhance the spread of infectious diseases like BXW. Analysis of qualitative and quantitative data suggested that individual farmers’ actions were influenced by perceptions of risk, affecting both individual and collective disease management. Additionally, the used experimental treatments allowed us to evaluate the influence of communication on risk-governance strategies. It appears that a combination of possession of technical knowledge about the disease, opportunities to communicate about the disease, and a collective disease management strategy enables the best individual actions and collective performance.

Adding Emergence and Spatiality to a Public Bad Game for Studying Dynamics in Socio-Ecological Systems (Part I): The Design of Musa-Game for Integrative Analysis of Collective Action in Banana Disease Management

Human decision-making plays a critical and challenging role in the prevention and control of public bads within socio-ecological systems. Farmers daily confront dilemmas regarding public bad management, such as infectious diseases in their crops. Their decisions interplay with multiple factors and may create the risk conditions in which a public bad can occur (e.g., a disease outbreak). This article presents an experimental board game method (DySE) and its contextualized version (Musa-game) to study the effect of individual and collective human actions on creating or preventing a public bad. The DySE method and the Musa-game add emergence and spatiality (both attributes of SES) to the study of public bads and collective action problems. This methodological proposal allows us to build a contextual understanding of how individual and collective actions of various entities lead to typical system outcomes, i.e., conditions that are (un)favourable to pathogens, and individual decisions about infectious disease management. To conceptualize our method, we used the case of Banana Xanthomonas Wilt disease in Rwanda. This research is published as a diptych. Part I (this article) covers the conceptualization and design of Musa-game. Part II presents empirical findings from testing Musa-game with farmers in Rwanda and recommendations for using the method.

CRISPR/Cas9‐mediated editing of DMR6 orthologue in banana (Musa spp.) confers enhanced resistance to bacterial disease

Banana (Musa spp.) is an important staple food crop and a source of income for resource-poor farmers in more than 136 tropical and sub-tropical countries with an annual production of 155 million tons (FAOSTAT, 2018). Many diseases severely constrain banana production, particularly where many pathogens co-exist (Tripathi et al., 2020). Banana Xanthomonas wilt (BXW) caused by Xanthomonas campestris pv. musacearum (Xcm) is considered among the most destructive banana diseases in East and Central Africa (Tripathi et al., 2009). All the cultivated banana varieties are susceptible, and only the wild-type progenitor, Musa balbisiana, is resistant to BXW disease (Tripathi et al., 2019). Overall economic losses from BXW were estimated at US$ 2-8 billion over a decade. The use of disease-resistant varieties is one of the most effective strategies to manage diseases. Recent advances in CRISPR/Cas-based genome-editing can accelerate banana improvement. The availability of reference genome-sequences and the CRISPR/Cas9-editing system has made it possible to develop disease-resistant banana by precisely editing the endogenous genes (Ntui et al., 2020).

Farmer Friendly Options for Sterilizing Farm Tools for the Control of Xanthomonas Wilt Disease of Banana

The adoption of tool sterilization using either 3.5% sodium hypochlorite (household bleach) or fire, a core element of the cultural control packages for Xanthomonas wilt (XW) of banana has been poorly adopted hampering XW control in East and Central Africa. Household bleach is costly and not accessible to the rural poor while repeated heating weakens metal blades of garden tools (machetes, knives, and hoes). Identification of economically viable tool sterilization options is thus crucial for XW management. We explored a range of practices including tool insertion for varying time periods into cold and hot ash, fire and boiling water; tool exposure over varying time periods to the sun while under black or transparent plastic sheets; and washing tools with cold water and laundry soap or detergent. Cleaning with household bleach served as a negative control while uncleaned tools as positive control. Like for household bleach, no Xanthomonas vasicola pv. musacearum (Xvm) the causal agent of XW was recovered from tools washed with cold water and different laundry soaps or detergents. Culturing Xvm in varying detergent and soap concentrations (0.00125–0.035 g/mL), only resulted in growth at lower concentrations of 0.00125 and 0.0025 g/mL. The cleaning effect of soap could thus be due to both an anti-bacterial effect and dislodgment of bacteria from tools. Laundry soaps/detergents are cheaper than household bleach and used for various purposes within and across households, including the resource poor and rural households, hence a cheaper and convenient tool sterilization alternative. Tool insertion into boiling water was effective from the 40th second and thus a viable alternative. Heating tools in fire required up to a minute to clear all bacteria. The currently recommended 20–40 s heating could thus be inadequate. Repeated heating for 1 min may also damage tools. Other practices (washing with cold water only, use of solar radiation, repeatedly and forcefully inserting tools into the soil, tool insertion into hot and cold ash for up to 5 min) only reduced Xvm populations on tools, thus not independently recommended. We recommend expanding the tool sterilization options to include washing with soap/ detergents and tool insertion into boiling water for at least 1 min.

Comparing effectiveness, cost- and time-efficiency of control options for Xanthomonas wilt of banana under Rwandan agro-ecological conditions

Xanthomonas wilt of banana (XW) is a major disease affecting banana throughout East and Central Africa (ECA). Initial control was through complete diseased mat uprooting (CDMU), which had limited adoption due to high labour demands and cost. Further research demonstrated single diseased stem removal (SDSR) was an effective, less labour intensive and less costly alternative to CDMU. A comparative assessment of the two control practices was needed to foster uptake by policy makers, especially in countries like Rwanda where SDSR had not been tested or scaled up. To test SDSR in Rwanda, a study was conducted in farmers’ fields comparing the effectiveness, labour cost and time demands of CDMU and SDSR. SDSR was equally effective as CDMU for XW control, with initial XW incidences of 3.0 to 9.4% being reduced to <0.5% within 3 months of using either method. The major benefit of SDSR lies in its significantly lower resource requirements. The total time needed for applying SDSR on a single plant was 88% less, averaging 4.3 min (standard deviation, sd = 0.3) compared to 36.5 min (sd = 4.5) for CDMU on a complete mat. Accordingly, the cost of labour was significantly lower for SDSR. The main cost of CDMU (78% of total cost) arose from the need to replant with healthy banana plantlets. The total cost of SDSR (26 Rwandan Francs [Frw], sd = 2) was 96% lower than that for CDMU (619 Frw, sd = 27). Hence, the incentive to use SDSR for managing XW is very high. These findings will boost SDSR adoption by both policy makers and farmers in ECA.

Prevalence of banana Xanthomonas wilt in Nithi, Tharaka-Nithi County in Kenya

Banana (Musa spp.) is a nutrient rich crop grown in small and large scale across the globe. It is rich in carbohydrates, vitamins and minerals thus, it may serve as the source of nutrition in low resourced regions such as Tharaka Nithi County, Kenya. However, banana production in many areas is faced with biotic constraints such as banana Xanthomonas wilt (BXW) disease caused by Xanthomonas campestris pv. musacearum. The pathogen attacks photosynthetic leaves and young fruits, reducing palatability and marketability. There is currently scanty information on prevalence of BXW in Nithi region of Tharaka Nithi County. Additionally, it remains unclear whether farmers in the region are knowledgeable on occurrence of BXW disease, symptoms and management practices. The prevalence of BXW was assessed through survey method in five villages (Kiang’ondu, Marima, Mitheru, Kibumbu and Giampampo) in Nithi. Percentage BXW prevalence in the studied villages was not significantly different (p&gt;0.05). However, slightly higher BXW prevalence value of 21.14% was recorded at Giampampo village and was lower at Mitheru 11.24%. There was significant relationship (X2 (8, N = 46) = 19.93, p= 0.0034) between banana variety grown and occurrence of banana diseases. There was significant relationship (X2 (8, N = 46) = 31.165, p = 0.0053) between banana variety grown and susceptibility to diseases. The relationship between years of growing banana in the same farm and occurrence of banana diseases was significant (X2(6,N= 46) = 8.761,p= &lt;0.0001. The relationship between occurrence of banana diseases and season of the year was significant (X2(8,N= 46) = 32.4591, p= &lt;0.0001). The relationship between occurrence of banana diseases and management option in Nithi was significant (X2(4,N= 46) = 6.9758,p= 0.0025). Majority of the farmers (92%) were unaware of existence of BXW in the region. Farmers expressed lack of knowledge on managing BXW diseases in their banana farms with the majority not being able to identify common diseases of banana. Based on these observations, there is need to educate farmers on best banana farming practices, disease identification and management.

Genetic Engineering of Banana Against Bacterial Diseases

Banana (<i>Musa</i> spp) is among the top ten most important food crops worldwide in terms of production and consumption. However, banana production is threatened by several bacterial diseases, including Banana Xanthomonas wilt (BXW) caused by <i>Xanthomonas campestris </i>pathovar (pv)<i>. musacearum</i>, Moko disease caused by <i>Ralstonia solanacearum,</i> and Blood disease caused by <i>Ralstonia syzygii </i>sub-species (subsp)<i>. Celebesensis. </i>Banana Xanthomonas wilt (BXW), caused by <i>Xanthomonas campestris pv. musacearum</i> (Xcm) is the most economically important bacterial disease affecting banana production, particularly in the African Great Lakes region. Banana breeding through conventional approach is key to overcoming yield losses to bacterial phytopathogens. However, conventional breeding of bananas is limited by low male and female fertility and the lack of diversity and important traits in the gene pool. At present, only <i>Musa</i> <i>balbisiana</i> (banana progenitor species) is resistant to BXW, but breeders do not prefer it for breeding because it harbors banana streak virus (BSV) sequences in its B genome, which get activated during abiotic stress, such as drought, leading Banana Streak Disease (BSD). Thus, genetic engineering serves as a viable alternative and complement to conventional breeding for banana improvement. This review highlights the strategies, challenges, status, and prospects of genetic engineering of bananas against bacterial diseases.

SNP-based genotyping and whole-genome sequencing reveal previously unknown genetic diversity in Xanthomonas vasicola pv. musacearum, causal agent of banana xanthomonas wilt, in its presumed Ethiopian origin.

For decades, Xanthomonas vasicola pv. musacearum (Xvm) has been an economically important bacterial pathogen on enset in Ethiopia. Since 2001, Xvm has also been responsible for significant losses to banana crops in several East and Central African countries, with devastating consequences for smallholder farmers. Understanding the genetic diversity within Xvm populations is essential for the smart design of transnationally reasoned, durable, and effective management practices. Previous studies have revealed limited genetic diversity in Xvm, with East African isolates from banana each falling into one of two closely related clades previously designated as sublineages SL 1 and SL 2, the former of which had also been detected on banana and enset in Ethiopia. Given the presumed origin of Xvm in Ethiopia, we hypothesized that both clades might be found in that country, along with additional genotypes not seen in Central and East African bananas. Genotyping of 97 isolates and whole‐genome sequencing of 15 isolates revealed not only the presence of SL 2 in Ethiopia, but additional diversity beyond SL 1 and SL 2 in four new clades. Moreover, SL 2 was detected in the Democratic Republic of Congo, where previously SL 1 was the only clade reported. These results demonstrate a greater range of genetic diversity among Xvm isolates than previously reported, especially in Ethiopia, and further support the hypothesis that the East/Central Africa xanthomonas wilt epidemic has been caused by a restricted set of genotypes drawn from a highly diverse pathogen pool in Ethiopia.

Pest Incursions Pose a Serious Threat To Food Security and the Kenyan Economy

Although Kenya has a well-developed phytosanitary system to regulate introduction of plant and plant products, several pest incursions have been reported in the last two decades. The incursions have culminated in devastating impact on agriculture, biodiversity and the entire Kenyan economy. The objective of this review is to consolidate information on the pests involved, their distribution, estimate the economic losses associated with them and management measures in place. A total of 11 major pests and diseases namely Asian citrus psyllid (ACP), Bactrocera dorsalis, Banana xanthomonas wilt (BXW), Cassava brown streak disease (CBSD), Cassava mosaic disease (CMD), Fall army worm (FAW), Maize lethal necrosis disease (MLND), Papaya mealybug (PMB), Parthenium hysterophorus, potato cyst nematode (PCN) and tomato leaf miners (Tuta absoluta) have been reported in the last two decades. Some of the pests are persistent, invasive, vicious and fast spreading. For instance, the FAW has now spread to nearly all maize growing areas in Kenya in one year after the pest was first reported in 2017. The incursion pests are a major threat to food security, expensive to control and are a barrier to international market access. Integrated measures including improvement of diagnostic potential, increased pest and disease surveillance, improvement in rapid response and pest containment are needed in view of the dangers posed by incursion pests to the entire Kenyan economy whose mainstay is agriculture. Key words: Bactrocera dorsalis, maize lethal necrosis disease, Parthenium hysterophorus, Tuta absoluta

Public and private investments for banana Xanthomonas Wilt control in Uganda: The economic feasibility for smallholder farmers

Banana Xanthomonas Wilt (BXW) poses a serious threat to livelihoods and food security for millions of households in Africa. Despite considerable investments in Uganda by the Government and other national and international stakeholders, the disease persists in the country after periods of significant resurgence. Building on the Agricultural Innovation Systems framework, this paper reviews the role of the major stakeholders involved in controlling the disease in Uganda. Next, using household survey data, it analyzes economic costs and benefits of adopting an integrated BXW control package for the Ugandan smallholder farmers. After 2015, there has been a significant reduction in both public and private investments in BXW management, which may contribute to future disease resurgence. Our analysis reveals a high level of partial adoption of BXW recommended practices, and just a third of farmers adopting a full control package. This means significant economic losses for non-adopters, as indicated by our findings that households adopting the full package registered a net balance of US$65 per acre higher than non-adopters. We find that disproportionally large costs need to be borne at the beginning of the process, while the benefits are distributed over time, which may present a barrier to adoption by resource-poor smallholders.

Detection of banana plants and their major diseases through aerial images and machine learning methods: A case study in DR Congo and Republic of Benin

Front-line remote sensing tools, coupled with machine learning (ML), have a significant role in crop monitoring and disease surveillance. Crop type classification and a disease early warning system are some of these remote sensing applications that provide precise, timely, and cost-effective information at different spatial, temporal, and spectral resolutions. To our knowledge, most disease surveillance systems focus on a single-sensor based solutions and lagging the integration of multiple information sources. Moreover, monitoring larger landscapes using unmanned aerial vehicles (UAV) are challenging, and, therefore combining high resolution satellite imagery data with advanced machine learning (ML) models through the use of mobile apps could help detect and classify banana plants and provide more information on its overall health status. In this study, we classified banana under mixed-complex African landscapes through pixel-based classifications and ML models derived from multi-level satellite images (Sentinel 2, PlanetScope and WorldView-2) and UAV (MicaSense RedEdge) platforms. Our pixel-based classification from random forest (RF) model using combined features of vegetation indices (VIs) and principal component analysis (PCA) showed up to 97% overall accuracy (OA) with less than 10% omission and commission errors (OE and CE) and Kappa coefficient of 0.96 in high resolution multispectral images. We used UAV-RGB aerial images from DR Congo and Republic of Benin fields to develop a mixed-model system combining object detection model (RetinaNet) and a custom classifier for simultaneous banana localization and disease classification. Their accuracies were tested using different performance metrics. Our UAV-RGB mixed-model revealed that the developed object detection and classification model successfully classified healthy and diseased plants with 99.4%, 92.8%, 93.3% and 90.8% accuracy for the four classes: banana bunchy top disease (BBTD), Xanthomonas Wilt of Banana (BXW), healthy banana cluster and individual banana plants, respectively. These approaches of aerial image-based ML models have high potential to provide a decision support system for major banana diseases in Africa.