Search

Improvement of deep learning algorithms in smart agriculture is important to support the early detection of plant diseases, thereby improving crop yields. Data acquisition for machine learning applications is an expensive task due to the requirements of expert knowledge and professional equipment. The usability of any application in a real‐world setting is often limited by unskilled users and the limitations of devices used for acquiring images for classification. We aim to improve the accuracy of deep learning models on low‐quality test images using data augmentation techniques for neural network training. We generate synthetic images with a modified colour value distribution to expand the trainable image colour space and to train the neural network to recognize important colour‐based features, which are less sensitive to the deficiencies of low‐quality images such as those affected by blurring or motion. This paper introduces a novel image colour histogram transformation technique for generating synthetic images for data augmentation in image classification tasks. The approach is based on the convolution of the Chebyshev orthogonal functions with the probability distribution functions of image colour histograms. To validate our proposed model, we used four methods (resolution down‐sampling, Gaussian blurring, motion blur, and overexposure) for reducing image quality from the Cassava leaf disease dataset. The results based on the modified MobileNetV2 neural network showed a statistically significant improvement of cassava leaf disease recognition accuracy on lower‐quality testing images when compared with the baseline network. The model can be easily deployed for recognizing and detecting cassava leaf diseases in lower quality images, which is a major factor in practical data acquisition. [ABSTRACT FROM AUTHOR]

A key constraint to cassava productivity in Africa is the lack of adoption of improved cassava varieties tolerant to pests and diseases. To understand the drivers of adoption behavior, we examine the simultaneous adoption of improved cassava varieties and intercropping by 1200 smallholder farmers in Malawi, Tanzania, and Uganda. Using a linear model, we find that varietal characteristics, such as yield and early maturity, are critical drivers of adoption. Access to extension and credit is associated with an increase in the attractiveness of yield‐improving characteristics. We conclude that a more targeted extension approach would increase technology adoption in these countries. [ABSTRACT FROM AUTHOR]

Cassava (Manihot esculenta. Crantz) is a starch‐rich, woody tuberous, root crop important for food, with little being done to investigate its potential as a bioenergy crop despite its enormous potential. The major bottleneck in the crop being able to serve this dual role is the competition of its storage roots for both purposes. The major cassava production regions primarily use the tuberous roots for food, and this has resulted in its neglect as a bioenergy crop. The use of non‐food cassava parts as a feedstock in cellulosic biofuel production is a promising strategy that can overcome this challenge. However, in non‐tuber parts, most of the sugars are highly sequestered in lignin complexes making them inaccessible to bacterial bioconversion. Additionally, cassava production in these major growing areas is not optimal owing to several production constraints. The challenges affecting cassava production as a food and bioenergy crop are interconnected and therefore need to be addressed together. Cassava improvement against biotic and abiotic stresses can enhance productivity and cater for the high demand of the roots for food and bioenergy production. Furthermore, increased production will enhance the usability of non‐food parts for bioenergy as the bigger goal. This review addresses efforts in cassava improvement against stresses that reduce its productivity as well as strategies that enhance biomass production, both important for food and bioenergy. Additionally, prospective strategies that could ease bioconversion of cassava for enhanced bioenergy production are explored. [ABSTRACT FROM AUTHOR]

The impacts of invasive alien plant species on native plants are generally well documented, but little is known about the mechanisms underlying their impacts on crop growth. A better understanding of immediate as well as legacy effects and of direct and indirect impacts of invasive alien plant species is essential for an improved management of invaded cropland. We investigated how Lantana camara impacts the growth of two subsistence crops (maize and cassava) through competition for resources, allelopathy and the indirect plant–plant interactions. We carried out two pot experiments using soils from invaded abandoned, invaded cultivated and non‐invaded cultivated crop fields. In the first experiment maize and cassava were grown alone or together with L. camara and half of the pots were treated with activated carbon to suppress allelochemicals. The effect of the soil microbial community on L. camara—crop interactions was assessed in a second experiment using autoclaved soil with 5% of soil from the three soil types. We found that L. camara reduced the growth of maize by 29%, but cassava was not affected. We did not find evidence of allelopathic effects of L. camara. Inoculation of autoclaved soil with microorganisms from all soil types increased biomass of cassava and reduced the growth of maize. Because L. camara only caused impacts when growing simultaneously with maize, the results suggest that removal of L. camara will immediately mitigate its negative impacts on maize. [ABSTRACT FROM AUTHOR]

This study aimed to develop a cassava‐based rice analogue with improved nutritional value as an alternative to commercial white rice. The rice analogue formulations (RAFs) were developed by the substitution of modified cassava flour (MOCAF) with rice flour at different ratios as 1:0, 7:3, 5:5, 3:7, and 0:1, followed by the addition of cassava leaves (0, 10, and 20 wt%). The developed rice analogues were evaluated for physicochemical, functional, morphological, and antioxidant properties. The rice analogue containing a 5:5 ratio of rice flour to MOCAF (RAF 2) added with 20% cassava leaves presented the most desirable nutritional composition and functional properties. However, RAF 4 (100% MOCAF with 20% cassava leaves) showed the highest total polyphenol content (TPC) (198.8 mg gallic acid equivalent (GAE)/100 g), total chlorophyll content (TCC) (198 mg/ml), 2,2‐diphenyl‐1‐picrylhydrazyl (DPPH) inhibition (79%), and ferric reducing antioxidant power (FRAP) inhibition (85%). Hence, the addition of MOCAF and cassava leaves improved the nutritional value of cassava‐based rice analogues, which could be a healthy alternative to commercial rice in the daily diet. [ABSTRACT FROM AUTHOR]

Cassava is a rich source of carbohydrates, and it is vulnerable to virus diseases. Literature survey shows that the image recognition and integrated deep learning approach is successfully employed for Cassava leaf disease classification. Mostly, transfer learning based on a convolutional neural network (CNN) models were successfully applied for Cassava leaf disease classification. However, existing approaches are not effective in identifying the tiny portion of the disease in the overall leaf area. Identifying and focussing on regions affected by the disease is vital to achieving a good classification accuracy. An attention‐based approach is integrated into pretrained CNN‐based EfficientNet models to locate and identify the tiny infected regions in Cassava leaf. Penultimate layer features of attention‐based EfficientNet models such as A_EfficientNetB4, A_EfficientNetB5, and A_EfficientNetB6 were extracted. Next, the dimensionality of the extracted features was reduced using kernel principal component analysis. The reduced features were fused and passed into a stacked ensemble meta‐classifier for Cassava leaf disease classification. A stacked ensemble meta‐classifier is a two‐stage approach in which the first stage employs random forest and support vector machine (SVM) for prediction followed by logistic regression for classification. Detailed investigation and analysis of the proposed method, attention, and non‐attention‐based approaches with CNN pretrained models were tested using a publicly available benchmark dataset of Cassava leaf disease images. The proposed method achieved better performances in all experiments than several existing methods as well as various attention and non‐attention‐based CNN pretrained models. The proposed approach can be used as a deployable tool for Cassava leaf disease classification in agricultural field. [ABSTRACT FROM AUTHOR]

Summary: The genus Manihot, with around 120 known species, is native to a wide range of habitats and regions in the tropical and subtropical Americas. Its high species richness and recent diversification only c. 6 million years ago have significantly complicated previous phylogenetic analyses. Several basic elements of Manihot evolutionary history therefore remain unresolved.Here, we conduct a comprehensive phylogenomic analysis of Manihot, focusing on exhaustive sampling of South American taxa.We find that two recently described species from northeast Brazil's Atlantic Forest were the earliest to diverge, strongly suggesting a South American common ancestor of Manihot. Ancestral state reconstruction indicates early Manihot diversification in dry forests, with numerous independent episodes of new habitat colonization, including into savannas and rainforests within South America. We identify the closest wild relatives to Manihot esculenta, including the crop cassava, and we quantify extensive wild introgression into the cassava gene pool from at least five wild species, including Manihot glaziovii, a species used widely in breeding programs. Finally, we show that this wild‐to‐crop introgression substantially shapes the mutation load in cassava.Our findings provide a detailed case study for neotropical evolutionary history in a diverse and widespread group, and a robust phylogenomic framework for future Manihot and cassava research. [ABSTRACT FROM AUTHOR]

Xanthomonas phaseoli pv. manihotis (Xpm) and X. cassavae (Xc) are two bacterial pathogens attacking cassava. Cassava bacterial blight (CBB) is a systemic disease caused by Xpm, which might have dramatic effects on plant growth and crop production. Cassava bacterial necrosis is a nonvascular disease caused by Xc with foliar symptoms similar to CBB, but its impacts on the plant vigour and the crop are limited. In this review, we describe the epidemiology and ecology of the two pathogens, the impacts and management of the diseases, and the main research achievements for each pathosystem. Because Xc data are sparse, our main focus is on Xpm and CBB. [ABSTRACT FROM AUTHOR]