Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

Silva, Sandro Valerio; Andermann, Tobias; Zizka, Alexander; Kozlowski, Gregor; Silvestro, Daniele

doi:10.3389/fpls.2022.839792

Cited by 21 publications

(30 citation statements)

References 52 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…For example, while soft tissues hold great importance in determining key features of animal ecology, they are rarely preserved in the fossil record and accurate imputation could help predicting these pieces of the puzzle in long-extinct taxa. For instance imputation can be used to predict phenotypic traits in dinosaurs like feathers or night vision that are only rarely preserved in the fossil record (Choiniere et al, 2021) of the conservation status of under-represented taxonomic groups in the Red List of the International Union for the Conservation of Nature (Silva et al, 2022).…”

Section: Discussionmentioning

confidence: 99%

Benchmarking imputation methods for discrete biological data

Gendre

Hauffe

Pimiento

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

Trait datasets are at the basis of a large share of ecology and evolutionary research, being used to infer ancestral morphologies, to quantify species extinction risks, or to evaluate the functional diversity of biological communities. These datasets, however, are often plagued by missing data, for instance due to incomplete sampling limited data and resource availabilities. Several imputation methods exist to predict missing values and have been successfully evaluated and used to fill the gaps in datasets of quantitative traits. Here we explore the performance of different imputation methods on discrete biological traits i.e. qualitative or categorical traits such as diet or habitat. We develop a bioinformatics pipeline to impute trait data combining phylogenetic, machine learning, and deep learning methods while integrating a simulation framework to evaluate their performance on synthetic datasets. Using this pipeline we run a wide range of simulations under different missing rates, mechanisms, and biases and different evolutionary models. Our results indicate that a new ensemble approach, where we combined the imputation results of a selection of imputation methods provides the most robust and accurate prediction of missing discrete traits. We apply our pipeline to an incomplete trait dataset of 1015 elasmobranch species (including sharks and rays) and found a high imputation accuracy of the predictions based on an expert-based assessment of the missing traits. Our bioinformatic pipeline, implemented in an open-source R package, facilitates the application and comparison of multiple imputation methods to make robust predictions of missing trait values in biological datasets.

show abstract

Section: Discussionmentioning

confidence: 99%

Benchmarking imputation methods for discrete biological data

Gendre

Hauffe

Pimiento

et al. 2023

Preprint

Self Cite

View full text Add to dashboard Cite

show abstract

“…This human footprint map compiles an indicator of human disturbance in a site, combining factors like human population density, presence of roads, electricity lines, dams and other infrastructure, impacts by agriculture and mining, among others (Correa-Ayram et al, 2018). Humanfootprint estimates have been shown as good predictors of extinction risk of species, as they accurately represent cumulative human pressure on habitats (Di Marco et al, 2018), and they are being increasingly used in Red List assessments for plants (e.g., Cazalis et al, 2022;Silva et al, 2022;Stévart et al, 2019;Zizka et al, 2021).…”

Section: Methodsmentioning

confidence: 99%

The Red List for the endemic trees of Colombia: Effective conservation targeted for plants required in biodiversity hotspots

López-Gallego

Morales

2023

Plants People Planet

View full text Add to dashboard Cite

Conserving trees is fundamental to maintaining forests, which are home to about half of the global biodiversity and provide unmeasurable benefits to people. Colombia has 5868 known species of trees, 1148 of which are endemic to the country. Unfortunately, 45% of the endemic trees of Colombia are threatened with extinction, and therefore, the ecosystem services they provide might be in jeopardy. This study represents an important contribution to conservation planning for the endemic trees of a megadiverse country and highlights critical considerations for their conservation. Summary• Colombia has a very rich tree flora and high levels of tree endemism. As a contribution to the "Global Tree Assessment", we assessed 860 species to complete the Red List of the 1148 endemic trees of the country. The information is being used to support spatial conservation planning as Key Biodiversity Areas identification.• To categorize the species according to the International Union for the Conservation of Nature (IUCN) Red List guidelines, we used geographic occurrences obtained from herbarium specimens. We carried out detailed analysis of habitat quantity and quality (using forest cover and human footprint maps) and documented anthropogenic threats and conservation actions.• Almost half (45%) of the endemic trees were categorized as threatened. Most species had small distributions (with an extent of occurrence of less than 40,000 km 2 ). Endemic tree occurrences were more common in the Andes and Magdalena regions, which have very high human footprint and consequently a large proportion of threatened species. The major threat to endemic trees was habitat destruction, due mainly to deforestation for livestock and crops. Many endemic trees were present in protected areas (65%), but threatened and nonthreatened species had low coverage with habitat protection, and many of their populations persist in disturbed habitats.• Colombia has hundreds of threatened endemic trees, most of them in global biodiversity hotspots, with very few proactive conservation actions. It is urgent to

show abstract

“…These analyses can efficiently harvest information for tens of thousands of species based on online databases (e.g. gbif.org; wolrdclim.org) and use these data along with the available IUCN Red List assessments to train ANN models capable of predicting the conservation status of taxa currently not included in the Red List (Figure 6; (Silva et al, 2022)).…”

Section: Challenge 2: Prioritising Species Conservationmentioning

confidence: 99%

Integrating machine learning, remote sensing and citizen science to create an early warning system for biodiversity

Antonelli

Dhanjal‐Adams

Silvestro

2022

Plants People Planet

Self Cite

View full text Add to dashboard Cite

Societal Impact Statement The development and implementation of conservation actions that address urgent threats to biodiversity across the globe require large amounts of historic and current data. Machine learning approaches offer the tools to process, analyse and interpret large data sets, giving insights into trends and guiding evidence‐based allocation of limited resources to maximise positive biodiversity outcomes. Here we describe how data acquired from remote sensing, citizen science and other monitoring approaches could feed in near‐real time into an early warning system for biodiversity that integrates automated red‐listing of species with the identification of priority areas for conservation. Summary Application of machine learning approaches is aiding biodiversity conservation and research at a time of rapid global change. Two emerging topics and their data requirements are presented. First, to identify areas of priority protection for preventing biodiversity loss, reinforcement learning is used by training models that take into account human disturbance and climate change under recurrent monitoring schemes. Second, neural networks are used to approximate classification of species into Red List categories of the International Union for Conservation of Nature, offering the possibility of real‐time re‐classification after events such as widespread fires and deforestation. We discuss how the identification of areas and species most at risk could be integrated into an ‘early warning system’ based on climatic monitoring, remotely sensed land‐use changes and near‐real time biological and threat data from citizen science initiatives. Such system would help guide actions to prevent biodiversity loss at the speed required for effective conservation.

show abstract

Global Estimation and Mapping of the Conservation Status of Tree Species Using Artificial Intelligence

Cited by 21 publications

References 52 publications

Benchmarking imputation methods for discrete biological data

Benchmarking imputation methods for discrete biological data

The Red List for the endemic trees of Colombia: Effective conservation targeted for plants required in biodiversity hotspots

Integrating machine learning, remote sensing and citizen science to create an early warning system for biodiversity

Contact Info

Product

Resources

About