About this Research Topic
There is growing interest in the potential for combining eDNA and artificial intelligence (machine learning) to detect and evaluate in real time changes in ecosystems at the global scale, in a more sensitive and cost-effective way than current biomonitoring methods. Machine learning might make better use of the eDNA census data that can currently be collected to evaluate the network of ecological interactions that are at the base of the services that ecosystems supply and that we wish to protect. To date, eDNA and machine learning developments have effectively progressed in parallel and in isolation in various spheres of ecosystem monitoring (disease, invasion, conservation, etc. in aerial, terrestrial, and aquatic systems).
The goal of this Research Topic is to explore the range of ongoing activities to build the next generation of biomonitoring tools and in doing so to make researchers in the different spheres aware of the breadth of work being undertaken, and to set a unifying research agenda (the key questions) for the development of global biomonitoring using eDNA and machine learning.
The scope of this Research Topic will be to explore:
1. eDNA approaches currently being used in case study systems from all spheres of monitoring;
2. Theoretical underpinnings of machine learning for biomonitoring;
3. What type of networks do we need to reconstruct for effective monitoring (co-occurrence, trophic, etc);
4. Examples of learning large scale, replicated networks from eDNA in the different spheres;
5. Statistical and analytical approaches to analysing large-scale, highly replicated networks;
6. Technological developments necessary to build a next-generation biomonitoring framework at the global scale;
7. A research agenda paper that develops “10 key questions for eDNA and machine learning in biomonitoring”.
Details for Authors: The Research Topic “A next-generation of global biomonitoring to detect ecosystem change” will publish conceptual, data, case study, technological and synthetic papers on eDNA and machine learning approaches for developing a unified next-generation biomonitoring framework. Paper length conforms to the guidelines of the journal Frontiers in Ecology and Evolution.
The goal of this Research Topic is to explore the range of ongoing activities to build the next generation of biomonitoring tools and in doing so to make researchers in the different spheres aware of the breadth of work being undertaken, and to set a unifying research agenda (the key questions) for the development of global biomonitoring using eDNA and machine learning.
The scope of this Research Topic will be to explore:
1. eDNA approaches currently being used in case study systems from all spheres of monitoring;
2. Theoretical underpinnings of machine learning for biomonitoring;
3. What type of networks do we need to reconstruct for effective monitoring (co-occurrence, trophic, etc);
4. Examples of learning large scale, replicated networks from eDNA in the different spheres;
5. Statistical and analytical approaches to analysing large-scale, highly replicated networks;
6. Technological developments necessary to build a next-generation biomonitoring framework at the global scale;
7. A research agenda paper that develops “10 key questions for eDNA and machine learning in biomonitoring”.
Details for Authors: The Research Topic “A next-generation of global biomonitoring to detect ecosystem change” will publish conceptual, data, case study, technological and synthetic papers on eDNA and machine learning approaches for developing a unified next-generation biomonitoring framework. Paper length conforms to the guidelines of the journal Frontiers in Ecology and Evolution.
Keywords: machine learning, ecological interactions, environmental DNA (eDNA), ecological networks
Important Note: All contributions to this Research Topic must be within the scope of the section and journal to which they are submitted, as defined in their mission statements. Frontiers reserves the right to guide an out-of-scope manuscript to a more suitable section or journal at any stage of peer review.
