• Rural Digital Europe
• French National Research Agency (AN... close
• BE close

Fundação de Amparo à Pesquisa do Estado de São Paulo http://dx.doi.org/10.13039/501100001807 Belgian Federal Science Policy Office http://dx.doi.org/10.13039/501100002749 Agence Nationale de la Recherche http://dx.doi.org/10.13039/501100001665 Deutsche Forschungsgemeinschaft http://dx.doi.org/10.13039/501100001659 Svenska Forskningsrådet Formas http://dx.doi.org/10.13039/501100001862 Canada Research Chairs http://dx.doi.org/10.13039/501100001804 Austrian Science Fund http://dx.doi.org/10.13039/501100002428 Fondation BNP Paribas http://dx.doi.org/10.13039/501100008393 US NSF Biological Integration Institute program

Abstract Machine learning covers a large set of algorithms that can be trained to identify patterns in data. Thanks to the increase in the amount of data and computing power available, it has become pervasive across scientific disciplines. We first highlight why machine learning is needed in marine ecology. Then we provide a quick primer on machine learning techniques and vocabulary. We built a database of ∼1000 publications that implement such techniques to analyse marine ecology data. For various data types (images, optical spectra, acoustics, omics, geolocations, biogeochemical profiles, and satellite imagery), we present a historical perspective on applications that proved influential, can serve as templates for new work, or represent the diversity of approaches. Then, we illustrate how machine learning can be used to better understand ecological systems, by combining various sources of marine data. Through this coverage of the literature, we demonstrate an increase in the proportion of marine ecology studies that use machine learning, the pervasiveness of images as a data source, the dominance of machine learning for classification-type problems, and a shift towards deep learning for all data types. This overview is meant to guide researchers who wish to apply machine learning methods to their marine datasets. 80 7

International audience; In 2023, the European Union will vote on the reauthorization of glyphosate use, renewed in 2017 despite concern on impacts on the environment and public health. A ban is supported by several Member States but rejected by most farmers. What are citizens’ preferences to phase out glyphosate? To assess whether taxation could be an alternative to a ban, we conducted a discrete choice experiment in five European countries. Our results reveal that the general public is strongly willing to pay for a reduction in glyphosate use. However, while 75.5% of respondents stated to support a ban in the pre-experimental survey, experimental results reveal that in 73.35% of cases, earmarked taxation schemes are preferred when they lead to a strong reduction in glyphosate use for an increase in food price lower than that induced by a ban. When glyphosate reduction is balanced against its costs, a tax may be preferred.; En 2023, l’Union européenne votera sur la réautorisation de l’utilisation du glyphosate, renouvelée en 2017 en dépit des préoccupations sur les impacts sur l’environnement et la santé publique. Une interdiction est soutenue par plusieurs États membres, mais rejetée par la plupart des agriculteurs. Quelles sont les préférences des citoyens pour l’élimination progressive du glyphosate? Pour évaluer si la fiscalité pourrait être une alternative à une interdiction, nous avons mené une expérience de choix discret dans cinq pays européens. Nos résultats révèlent que le grand public est tout à fait disposé à payer pour une réduction de l’utilisation du glyphosate. Cependant, alors que 75,5% des répondants ont déclaré soutenir une interdiction dans le sondage pré-expérimental, les résultats expérimentaux révèlent que dans 73,35% des cas, les régimes fiscaux spécifiques sont préférables lorsqu’ils conduisent à une forte réduction de l’utilisation du glyphosate pour une augmentation du prix des denrées alimentaires inférieure à celle induite par une interdiction. Lorsque la réduction du glyphosate est équilibrée avec ses coûts, une taxe peut être préférée

Pinus contorta is considered one of the most invasive tree species worldwide, generating significant impacts on biodiversity and ecosystems. In several Patagonian ecosystems in southern Chile, it has escaped from plantations established mainly in the 1970s, and is now invading both forests and treeless environments. In this study, we evaluated the impact of the invasion of P. contorta on microenvironmental conditions in Araucaria araucana forest and Patagonian steppe ecosystems, and assessed how these changes related to the richness and abundance of native and non-native plant species. In each ecosystem, 24 plots of 100 m2 were established along a gradient of P. contorta biomass, where 18 environmental variables and the composition of native and non-native vegetation were measured at a local scale. Our results indicated that increased pine biomass was associated with differences in microclimatic conditions (soil and air temperature, photosynthetically active radiation (PAR), and soil moisture) and soil properties (potassium, nitrate, pH, and litter accumulation). These changes were ecosystem dependent, however, as well as associated with the level of invasion. Finally, the reduction in the richness and abundance of native plants was associated with the changes in soil properties (accumulation of leaf litter, pH, and organic matter) as well as in the microclimate (minimum air temperature, PAR) generated by the invasion of P. contorta. Overall, our results confirm that the invasion of P. contorta impacts microenvironmental conditions (i.e., canopy cover, litter accumulation, minimum air temperature, and maximum soil temperature) and reduces native plant diversity. For future restoration plans, more emphasis should be given to how environmental changes can influence the recovery of invaded ecosystems even after the removal of the living pine biomass (i.e., legacy of the invasion).

Trees sustain livelihoods and mitigate climate change but a predominance of trees outside forests and limited resources make it difficult for many tropical countries to conduct automated nation-wide inventories. Here, we propose an approach to map the carbon stock of each individual overstory tree at the national scale of Rwanda using aerial imagery from 2008 and deep learning. We show that 72% of the mapped trees are located in farmlands and savannas and 17% in plantations, accounting for 48.6% of the national aboveground carbon stocks. Natural forests cover 11% of the total tree count and 51.4% of the national carbon stocks, with an overall carbon stock uncertainty of 16.9%. The mapping of all trees allows partitioning to any landscapes classification and is urgently needed for effective planning and monitoring of restoration activities as well as for optimization of carbon sequestration, biodiversity and economic benefits of trees. ispartof: NATURE CLIMATE CHANGE vol:13 issue:1 pages:91-+ ispartof: location:England status: published

Data capturing multiple axes of tree size and shape, such as a tree's stem diameter, height and crown size, underpin a wide range of ecological research-from developing and testing theory on forest structure and dynamics, to estimating forest carbon stocks and their uncertainties, and integrating remote sensing imagery into forest monitoring programmes. However, these data can be surprisingly hard to come by, particularly for certain regions of the world and for specific taxonomic groups, posing a real barrier to progress in these fields. To overcome this challenge, we developed the Tallo database, a collection of 498,838 georeferenced and taxonomically standardized records of individual trees for which stem diameter, height and/or crown radius have been measured. These data were collected at 61,856 globally distributed sites, spanning all major forested and non-forested biomes. The majority of trees in the database are identified to species (88%), and collectively Tallo includes data for 5163 species distributed across 1453 genera and 187 plant families. The database is publicly archived under a CC-BY 4.0 licence and can be access from: https://doi.org/10.5281/zenodo.6637599. To demonstrate its value, here we present three case studies that highlight how the Tallo database can be used to address a range of theoretical and applied questions in ecology-from testing the predictions of metabolic scaling theory, to exploring the limits of tree allometric plasticity along environmental gradients and modelling global variation in maximum attainable tree height. In doing so, we provide a key resource for field ecologists, remote sensing researchers and the modelling community working together to better understand the role that trees play in regulating the terrestrial carbon cycle. Funder: U.S. Department of Energy; Id: http://dx.doi.org/10.13039/100000015 Funder: CAPES; Id: http://dx.doi.org/10.13039/501100002322 Funder: Agua Salud Project