Plant traits—the morphological, anatomical, physiological, biochemical and phenological characteristics of plants—determine how plants respond to environmental factors, affect other trophic levels, and influence ecosystem properties and their benefits and detriments to people. Plant trait data thus represent the basis for a vast area of research spanning from evolutionary biology, community and functional ecology, to biodiversity conservation, ecosystem and landscape management, restoration, biogeography and earth system modelling. Since its foundation in 2007, the TRY database of plant traits has grown continuously. It now provides unprecedented data coverage under an open access data policy and is the main plant trait database used by the research community worldwide. Increasingly, the TRY database also supports new frontiers of trait‐based plant research, including the identification of data gaps and the subsequent mobilization or measurement of new data. To support this development, in this article we evaluate the extent of the trait data compiled in TRY and analyse emerging patterns of data coverage and representativeness. Best species coverage is achieved for categorical traits—almost complete coverage for ‘plant growth form’. However, most traits relevant for ecology and vegetation modelling are characterized by continuous intraspecific variation and trait–environmental relationships. These traits have to be measured on individual plants in their respective environment. Despite unprecedented data coverage, we observe a humbling lack of completeness and representativeness of these continuous traits in many aspects. We, therefore, conclude that reducing data gaps and biases in the TRY database remains a key challenge and requires a coordinated approach to data mobilization and trait measurements. This can only be achieved in collaboration with other initiatives.

Many factors influence global change: Global environmental change is driven by multiple natural and anthropogenic factors. With a focus on global change as it affects soils, Rilliget al.point out that nearly all published studies consider just one or two factors at a time (see the Perspective by Manning). In a laboratory experiment, they tested 10 drivers of global change both individually and in combination, at levels ranging from 2 to 10 factors. They found that soil properties, processes, and microbial communities could not be predicted from single-effect responses and that multiple factors in combination produced unsuspected responses. They concluded that single-factor studies remain important for uncovering mechanisms but that global change biology needs to embrace more fully the multitude of drivers impinging on ecosystems.Science, this issue p.886; see also p.801

Most statistical models assume linearity and few variable interactions, even though real‐world ecological patterns often result from nonlinear and highly interactive processes. We here introduce a set of novel empirical modeling techniques which can address this mismatch: statistically reinforced machine learning. We demonstrate the behaviors of three techniques (conditional inference tree, model‐based tree, and permutation‐based random forest) by analyzing an artificially generated example dataset that contains patterns based on nonlinearity and variable interactions. The results show the potential of statistically reinforced machine learning algorithms to detect nonlinear relationships and higher‐order interactions. Estimation reliability for any technique, however, depended on sample size. The applications of statistically reinforced machine learning approaches would be particularly beneficial for investigating (1) novel patterns for which shapes cannot be assumed a priori, (2) higher‐order interactions which are often overlooked in parametric statistics, (3) context dependency where patterns change depending on other conditions, (4) significance and effect sizes of variables while taking nonlinearity and variable interactions into account, and (5) a hypothesis using parametric statistics after identifying patterns using statistically reinforced machine learning techniques.

Species distribution models (SDMs) are widely used in ecology, biogeography and conservation biology to estimate relationships between environmental variables and species occurrence data and make predictions of how their distributions vary in space and time. During the past two decades, the field has increasingly made use of machine learning approaches for constructing and validating SDMs. Model accuracy has steadily increased as a result, but the interpretability of the fitted models, for example the relative importance of predictor variables or their causal effects on focal species, has not always kept pace. Here we draw attention to an emerging subdiscipline of artificial intelligence, explainable AI (xAI), as a toolbox for better interpreting SDMs. xAI aims at deciphering the behavior of complex statistical or machine learning models (e.g. neural networks, random forests, boosted regression trees), and can produce more transparent and understandable SDM predictions. We describe the rationale behind xAI and provide a list of tools that can be used to help ecological modelers better understand complex model behavior at different scales. As an example, we perform a reproducible SDM analysis in R on the African elephant and showcase some xAI tools such as local interpretable model‐agnostic explanation (LIME) to help interpret local‐scale behavior of the model. We conclude with what we see as the benefits and caveats of these techniques and advocate for their use to improve the interpretability of machine learning SDMs.

All ecological disciplines consider temporal dynamics, although relevant concepts have been developed almost independently. We here introduce basic principles of temporal dynamics in ecology. We figured out essential features that describe temporal dynamics by finding similarities among about 60 ecological concepts and theories. We found that considering the hierarchically nested structure of complexity in temporal patterns (i.e. hierarchical complexity) can well describe the fundamental nature of temporal dynamics by expressing which patterns are observed at each scale. Across all ecological levels, driver-response relationships can be temporally variant and dependent on both short- and long-term past conditions. The framework can help with designing experiments, improving predictive power of statistics, and enhancing communications among ecological disciplines.

Biodiversity is crucial for the provision of ecosystem functions. However, ecosystems are now exposed to a rapidly growing number of anthropogenic pressures, and it remains unknown whether biodiversity can still promote ecosystem functions under multifaceted pressures. Here we investigated the effects of soil microbial diversity on soil functions and properties when faced with an increasing number of simultaneous global change factors in experimental microcosms. Higher soil microbial diversity had a positive effect on soil functions and properties when no or few (i.e., 1–4) global change factors were applied, but this positive effect was eliminated by the co-occurrence of numerous global change factors. This was attributable to the reduction of soil fungal abundance and the relative abundance of an ecological cluster of coexisting soil bacterial and fungal taxa. Our study indicates that reducing the number of anthropogenic pressures should be a goal in ecosystem management, in addition to biodiversity conservation.