Search

Banana (Musa spp.) is one of the world’s most valuable primary agricultural commodities. Production, worth an estimated $50 billion per annum, occurs in over 130 countries. Exported fruit are key commodities in several producing countries yet they comprise less than 15% of the total annual output of 150 million metric tons. Diseases are the most significant biotic constraints for both export and smallholder production. Notably, tropical race 4 (TR4) of Fusarium wilt (aka Panama disease) affects the Cavendish subgroup, which is now responsible for 47% of all production (virtually all exported fruit and over 30% of all remaining production). The recent outbreak of TR4 in Colombia threatens future export production in tropical America, where most export production occurs. This chapter presents an overview of the disease and its causal agent, Fusarium oxysporum f. sp. cubense . Although there is a substantial positive literature on biological, chemical or cultural measures, management is largely restricted to using resistant cultivars where the pathogen has established.

The Panama disease has been reported to wipe out banana plantations due to the fungal pathogen known as Fusarium oxysporum f. sp. Cubense Tropical Race 4, or Foc TR4. Currently, there are no proven methods to control the spread of the disease. This study aims to develop an early detection model for Foc TR4 to minimize damages to infected plantations. In line with this, CNN models using the ResNet50 architecture were utilized towards the classification of the presence of Foc TR4 in a given microscopy image of a soil sample. Fungi samples were lab-cultivated, and images were taken using a lab microscope with three distinct microscopy configurations in LPO magnification. The initial results have shown that brightfield and darkfield images are generally more helpful in the automatic classification of fungi. Gradient-weighted Class Activation Mapping (Grad-CAM) was used to validate the decision processes of the individual CNN models. The proposed ensemble model shows promising results that achieved an accuracy of 91.46%. The model is beneficial as a low-cost preliminary test that could be performed on areas that are suspected to be infected with the pathogen given that the exported models can easily be implemented in a mobile system.

Some 130 countries grow bananas, with the 120 million tonnes they produce each year mainly being grown by smallholders for home consumption or sale at local markets. Around 800,000 tonnes are imported to the UK each year with each banana having a carbon footprint of 100–200 grams. We waste over a million bananas a day in Britain, at a cost to the climate of over 30,000 tonnes of emissions annually. Disease is the number one threat as almost all our bananas come from a single variety called Cavendish. A fungal disease called Topical Race 4 is already destroying large numbers of banana plants around the world. Storm damage, floods and drought likewise pose an increasing risk. Boosting plant health through good water and nutrient management can help to give resilience to climate change and disease threats alike. Organic production and the use of biological pest control are also proving successful.