Climatic niche shifts are common in introduced plants

Nature Ecology & Evolution, Journal Year: 2017, Volume and Issue: 2(1), P. 34 - 43

Published: Nov. 30, 2017

Language: Английский

---

Machine learning and deep learning—A review for ecologists

Methods in Ecology and Evolution, Journal Year: 2023, Volume and Issue: 14(4), P. 994 - 1016

Published: Feb. 13, 2023

Abstract The popularity of machine learning (ML), deep (DL) and artificial intelligence (AI) has risen sharply in recent years. Despite this spike popularity, the inner workings ML DL algorithms are often perceived as opaque, their relationship to classical data analysis tools remains debated. Although it is assumed that excel primarily at making predictions, can also be used for analytical tasks traditionally addressed with statistical models. Moreover, most discussions reviews on focus mainly DL, failing synthesise wealth different advantages general principles. Here, we provide a comprehensive overview field starting by summarizing its historical developments, existing algorithm families, differences traditional tools, universal We then discuss why when models prediction where they could offer alternatives methods inference, highlighting current emerging applications ecological problems. Finally, summarize trends such scientific causal ML, explainable AI, responsible AI may significantly impact future. conclude powerful new predictive modelling analysis. superior performance compared explained higher flexibility automatic data‐dependent complexity optimization. However, use inference still disputed predictions creates challenges interpretation these Nevertheless, expect become an indispensable tool ecology evolution, comparable other tools.

Language: Английский

---

Assessing the reliability of species distribution projections in climate change research

Diversity and Distributions, Journal Year: 2021, Volume and Issue: 27(6), P. 1035 - 1050

Published: Feb. 19, 2021

Abstract Aim Forecasting changes in species distribution under future scenarios is one of the most prolific areas application for models (SDMs). However, no consensus yet exists on reliability such drawing conclusions species’ response to changing climate. In this study, we provide an overview common modelling practices field and assess model predictions using a virtual approach. Location Global. Methods We first review papers published between 2015 2019. Then, use approach three commonly applied SDM algorithms (GLM, MaxEnt random forest) estimated actual predictive performance parameterized with different settings violations assumptions. Results Most relied single (65%) small samples ( N < 50, 62%), used presence‐only data (85%), binarized models' output (74%) split‐sample validation (94%). Our simulation reveals that tends be over‐optimistic compared real performance, whereas spatial block provides more honest estimate, except when datasets are environmentally biased. The binarization predicted probabilities presence reduces models’ ability considerably. Sample size main predictors accuracy, but has little influence accuracy. Finally, inclusion ecologically irrelevant violation assumptions increases accuracy decreases projections, leading biased estimates range contraction expansion. Main predict low average, particularly binarized. A robust by spatially independent required, does not rule out inflation assumption violation. findings call caution interpretation projections climates.

Language: Английский

---

Using herbaria to study global environmental change

New Phytologist, Journal Year: 2018, Volume and Issue: 221(1), P. 110 - 122

Published: Aug. 30, 2018

During the last centuries, humans have transformed global ecosystems. With their temporal dimension, herbaria provide otherwise scarce long-term data crucial for tracking ecological and evolutionary changes over this period of intense change. The sheer size herbaria, together with increasing digitization possibility sequencing DNA from preserved plant material, makes them invaluable resources understanding species' responses to environmental Following chronology change, we highlight how can inform about effects on plants at least four main drivers change: pollution, habitat climate change invasive species. We summarize herbarium specimens so far been used in research, discuss future opportunities challenges posed by nature these data, advocate an intensified use 'windows into past' research beyond.

Language: Английский

---

GIFT – A Global Inventory of Floras and Traits for macroecology and biogeography

Journal of Biogeography, Journal Year: 2019, Volume and Issue: 47(1), P. 16 - 43

Published: June 9, 2019

Abstract Aim To understand how functional traits and evolutionary history shape the geographic distribution of plant life on Earth, we need to integrate high‐quality global‐scale data with phylogenetic information. Large‐scale for plants are, however, often restricted either certain taxonomic groups or regions. Range maps only exist a small subset all species digitally available point‐occurrence information is biased both geographically taxonomically. Floras checklists represent an alternative, yet rarely used potential source They contain highly curated about composition clearly defined area, together virtually cover entire global land surface. Here, report our recent efforts mobilize this macroecological biogeographical analyses in GIFT database, Global Inventory Traits. Location Global. Taxon Land (Embryophyta). Methods integrates distributions from regional traits, information, region‐level geographic, environmental socio‐economic data. It contains floristic status (native, endemic, alien naturalized) takes advantage wealth trait Floras, complemented by databases. Results 1.0 holds lists 2,893 regions across whole globe including ~315,000 taxonomically standardized names (i.e. c. 80% known species) ~3 million species‐by‐region occurrences. Based hierarchical taxonomical derivation scheme, 83 more than 2.3 trait‐by‐species combinations achieves unprecedented coverage categorical such as woodiness (~233,000 spp.) growth form (~213,000 spp.). Main conclusions present structure, content automated workflows corresponding web‐interface ( http://gift.uni-goettingen.de ) proof concept feasibility mobilizing aggregated biodiversity research.

Language: Английский

---