Neural hierarchical models of ecological populations

Joseph, Maxwell B.

doi:10.1101/759944

Cited by 8 publications

(9 citation statements)

References 126 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Capinha et al (2021) proposed a generalized approach to classification and prediction from ecological time‐series data leveraging automated choice of the best network architecture for the task at hand. Joseph (2020) proposed a RNN approach to predicting colonisation and extinction dynamics from presence/absence data.…”

Section: Applications In Ecology and Evolutionmentioning

confidence: 99%

Deep learning as a tool for ecology and evolution

et al. 2022

View full text Add to dashboard Cite

Deep learning is driving recent advances behind many everyday technologies, including speech and image recognition, natural language processing and autonomous driving. It is also gaining popularity in biology, where it has been used for automated species identification, environmental monitoring, ecological modelling, behavioural studies, DNA sequencing and population genetics and phylogenetics, among other applications. Deep learning relies on artificial neural networks for predictive modelling and excels at recognizing complex patterns. In this review we synthesize 818 studies using deep learning in the context of ecology and evolution to give a discipline‐wide perspective necessary to promote a rethinking of inference approaches in the field. We provide an introduction to machine learning and contrast it with mechanistic inference, followed by a gentle primer on deep learning. We review the applications of deep learning in ecology and evolution and discuss its limitations and efforts to overcome them. We also provide a practical primer for biologists interested in including deep learning in their toolkit and identify its possible future applications. We find that deep learning is being rapidly adopted in ecology and evolution, with 589 studies (64%) published since the beginning of 2019. Most use convolutional neural networks (496 studies) and supervised learning for image identification but also for tasks using molecular data, sounds, environmental data or video as input. More sophisticated uses of deep learning in biology are also beginning to appear. Operating within the machine learning paradigm, deep learning can be viewed as an alternative to mechanistic modelling. It has desirable properties of good performance and scaling with increasing complexity, while posing unique challenges such as sensitivity to bias in input data. We expect that rapid adoption of deep learning in ecology and evolution will continue, especially in automation of biodiversity monitoring and discovery and inference from genetic data. Increased use of unsupervised learning for discovery and visualization of clusters and gaps, simplification of multi‐step analysis pipelines, and integration of machine learning into graduate and postgraduate training are all likely in the near future.

show abstract

Section: Applications In Ecology and Evolutionmentioning

confidence: 99%

Deep learning as a tool for ecology and evolution

et al. 2022

View full text Add to dashboard Cite

show abstract

“…An opportunity exists to harness the data revolution to better quantify the nature and strength of interactions among biophysical and social systems that lead to emergent extremes. New analytical approaches should also allow us to integrate data‐driven and process‐based models for extreme event attribution and prediction (Joseph, 2020). Applying theories from other disciplines, such as flickering and critical slowing down from resilience theory (Scheffer et al, 2009), can lead to improved understanding and forecasting of extreme events.…”

Section: A Future Research Agenda For Studying Social‐environmental Ementioning

confidence: 99%

Social‐Environmental Extremes: Rethinking Extraordinary Events as Outcomes of Interacting Biophysical and Social Systems

et al. 2020

Self Cite

View full text Add to dashboard Cite

Extreme droughts, heat waves, fires, hurricanes, floods, and landslides cause the largest losses in the United States, and globally, from natural hazards linked to weather and climate. There is evidence that the frequency of such extremes is increasing, particularly for heat waves, large fires, and intense precipitation, making better understanding of the probability and consequences of these events imperative. Further, these events are not isolated, but rather interact with each other and with other social and biophysical drivers and conditions, to amplify impacts. Less is known about the nature and strength of these interactions. Natural and social science subfields frame extreme events with different definitions and analytical approaches, often neglecting interactions and the subsequent novel extremes that can arise. Here we propose a framework for social‐environmental extremes, defined as extraordinary events that emerge from interactions among biophysical and social systems. We argue that this definition is critical because it constrains the focus to major events that are capturing societal and scientific attention because of their extreme biophysical drivers and/or the extreme social outcomes. We review how different fields approach extremes as interacting phenomena and propose a synthetic framework that allows analytical separation of the multiple drivers and responses that yield extreme events and extreme effects. We conclude with a future research agenda for understanding the extreme events that matter to society. This agenda will help to identify where, when, and why communities may have high exposure and vulnerability to social‐environmental extremes—informing future mitigation and adaptation strategies.

show abstract

“…The development of Neural Networks, a form of Machine Learning, can detect intricate patterns produced by high‐order interactions such as those produced among genes into regulatory networks (Libbrecht & Noble, 2015) or genetic, clinical and histological variables used to diagnose cancer (Kourou et al, 2015). In ecology, deep learning has often been used to assist researchers in processing large datasets produced by automatic monitoring of populations and ecosystems by applying deep neural networks (Christin et al, 2019; Joseph, 2020). However, the possibilities of this methodology are much wider and the road is paved to study high‐dimensional problems related to ecological interactions (Desjardins‐Proulx et al, 2017; Poisot et al, 2021; Strydom et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

A deep Generative Artificial Intelligence system to predict species coexistence patterns

et al. 2022

View full text Add to dashboard Cite

Predicting coexistence patterns is a current challenge to understand diversity maintenance, especially in rich communities where these patterns' complexity is magnified through indirect interactions that prevent their approximation with classical experimental approaches. We explore cutting‐edge Machine Learning techniques called Generative Artificial Intelligence (GenAI) to predict species coexistence patterns in vegetation patches, training generative adversarial networks (GAN) and variational AutoEncoders (VAE) that are then used to unravel some of the mechanisms behind community assemblage. The GAN accurately reproduces real patches' species composition and plant species' affinity to different soil types, and the VAE also reaches a high level of accuracy, above 99%. Using the artificially generated patches, we found that high‐order interactions tend to suppress the positive effects of low‐order interactions. Finally, by reconstructing successional trajectories, we could identify the pioneer species with larger potential to generate a high diversity of distinct patches in terms of species composition. Understanding the complexity of species coexistence patterns in diverse ecological communities requires new approaches beyond heuristic rules. Generative Artificial Intelligence can be a powerful tool to this end as it allows to overcome the inherent dimensionality of this challenge.

show abstract

Neural hierarchical models of ecological populations

Cited by 8 publications

References 126 publications

Deep learning as a tool for ecology and evolution

Deep learning as a tool for ecology and evolution

Social‐Environmental Extremes: Rethinking Extraordinary Events as Outcomes of Interacting Biophysical and Social Systems

A deep Generative Artificial Intelligence system to predict species coexistence patterns

Contact Info

Product

Resources

About