RESUMO
Plant pathology has developed a wide range of concepts and tools for improving plant disease management, including models for understanding and responding to new risks from climate change. Most of these tools can be improved using new advances in artificial intelligence (AI), such as machine learning to integrate massive data sets in predictive models. There is the potential to develop automated analyses of risk that alert decision-makers, from farm managers to national plant protection organizations, to the likely need for action and provide decision support for targeting responses. We review machine-learning applications in plant pathology and synthesize ideas for the next steps to make the most of these tools in digital agriculture. Global projects, such as the proposed global surveillance system for plant disease, will be strengthened by the integration of the wide range of new data, including data from tools like remote sensors, that are used to evaluate the risk ofplant disease. There is exciting potential for the use of AI to strengthen global capacity building as well, from image analysis for disease diagnostics and associated management recommendations on farmers' phones to future training methodologies for plant pathologists that are customized in real-time for management needs in response to the current risks. International cooperation in integrating data and models will help develop the most effective responses to new challenges from climate change.
Assuntos
Inteligência Artificial , Big Data , Agricultura , Mudança Climática , Aprendizado de MáquinaRESUMO
Transport networks are vital components of multi-cellular organisms, distributing nutrients and removing waste products. Animal cardiovascular and respiratory systems, and plant vasculature, are branching trees whose architecture is thought to determine universal scaling laws in these organisms. In contrast, the transport systems of many multi-cellular fungi do not fit into this conceptual framework, as they have evolved to explore a patchy environment in search of new resources, rather than ramify through a three-dimensional organism. These fungi grow as a foraging mycelium, formed by the branching and fusion of threadlike hyphae, that gives rise to a complex network. To function efficiently, the mycelial network must both transport nutrients between spatially separated source and sink regions and also maintain its integrity in the face of continuous attack by mycophagous insects or random damage. Here we review the development of novel imaging approaches and software tools that we have used to characterise nutrient transport and network formation in foraging mycelia over a range of spatial scales. On a millimetre scale, we have used a combination of time-lapse confocal imaging and fluorescence recovery after photobleaching to quantify the rate of diffusive transport through the unique vacuole system in individual hyphae. These data then form the basis of a simulation model to predict the impact of such diffusion-based movement on a scale of several millimetres. On a centimetre scale, we have used novel photon-counting scintillation imaging techniques to visualize radiolabel movement in small microcosms. This approach has revealed novel N-transport phenomena, including rapid, preferential N-resource allocation to C-rich sinks, induction of simultaneous bi-directional transport, abrupt switching between different pre-existing transport routes, and a strong pulsatile component to transport in some species. Analysis of the pulsatile transport component using Fourier techniques shows that as the colony forms, it self-organizes into well demarcated domains that are identifiable by differences in the phase relationship of the pulses. On the centimetre to metre scale, we have begun to use techniques borrowed from graph theory to characterize the development and dynamics of the network, and used these abstracted network models to predict the transport characteristics, resilience, and cost of the network.
Assuntos
Alimentos , Fungos/metabolismo , Processamento de Imagem Assistida por Computador/métodos , Microscopia Confocal/métodos , Microscopia de Fluorescência/métodos , Microscopia de Vídeo/métodos , Micélio/metabolismoRESUMO
Saprotrophic woodland fungi forage for mineral nutrients and woody resources by extension of a mycelial network across the forest floor. Different species explore at different rates and establish networks with qualitatively differing architecture. However, detailed understanding of fungal foraging behaviour has been hampered by the absence of tools to quantify resource allocation and growth accurately and non-invasively. To solve this problem, we have used photon-counting scintillation imaging (PCSI) to map and quantify nutrient allocation and localised growth simultaneously in heterogeneous resource environments. We show that colonies spontaneously shift to an asymmetric growth pattern, even in the absence of added resources, often with a distinct transition between the two growth phases. However, the extent of polarisation was much more pronounced and focussed in the presence of an additional cellulose resource. In this case, there was highly localised growth, often at the expense of growth elsewhere in the colony, and marked accumulation of (14)C-AIB in the sector of the colony with the added resource. The magnitude of the response was greatest when resource was added around the time of the endogenous developmental transition. The focussed response required a metabolisable resource, as only limited changes were seen with glass fibre discs used to mimic the osmotic and thigmotropic stimuli upon resource addition. Overall the behaviour is consistent with an adaptive foraging strategy, both to exploit new resources and also to redirect subsequent foraging effort to this region, presumably with an expectation that the probability of finding additional resources is increased.
Assuntos
Modelos Estatísticos , Phanerochaete/citologia , Phanerochaete/crescimento & desenvolvimento , Transporte Biológico , Radioisótopos de Carbono/metabolismo , Câmaras gama , Hifas/química , Hifas/citologia , Hifas/crescimento & desenvolvimento , Hifas/fisiologia , Modelos Biológicos , Phanerochaete/química , Phanerochaete/fisiologiaRESUMO
Fungi play a central role in the nutrient cycles of boreal and temperate forests. In these biomes, the saprotrophic wood-decay fungi are the only organisms that can completely decompose woody plant litter. In particular, cord-forming basidiomycete fungi form extensive mycelial networks that scavenge scarce mineral nutrients and translocate them over long distances to exploit new food resources. Despite the importance of resource allocation, there is limited information on nutrient dynamics in these networks, particularly for nitrogen, as there is no suitable radioisotope available. We have mapped N-translocation using photon-counting scintillation imaging of the non-metabolised amino acid analogue, (14)C-aminoisobutyrate. We describe a number of novel phenomena, including rapid, preferential N-resource allocation to C-rich sinks, induction of simultaneous bi-directional N-transport, abrupt switching between different pre-existing transport routes, and emergence of locally synchronised, oscillatory phase domains. It is possible that such self-organised oscillatory behaviour is a mechanism to achieve global co-ordination in the mycelium.