Deep learning image analysis for filamentous fungi taxonomic classification: Dealing with small datasets with class imbalance and hierarchical grouping.

Deep learning applications in taxonomic classification for animals and plants from images have become popular, while those for microorganisms are still lagging behind. Our study investigated the potential of deep learning for the taxonomic classification of hundreds of filamentous fungi from colony images, which is typically a task that requires specialized knowledge. We isolated soil fungi, annotated their taxonomy using standard molecular barcode techniques, and took images of the fungal colonies grown in petri dishes (n = 606). We applied a convolutional neural network with multiple training approaches and model architectures to deal with some common issues in ecological datasets: small amounts of data, class imbalance, and hierarchically structured grouping. Model performance was overall low, mainly due to the relatively small dataset, class imbalance, and the high morphological plasticity exhibited by fungal colonies. However, our approach indicates that morphological features like color, patchiness, and colony extension rate could be used for the recognition of fungal colonies at higher taxonomic ranks (i.e. phylum, class, and order). Model explanation implies that image recognition characters appear at different positions within the colony (e.g. outer or inner hyphae) depending on the taxonomic resolution. Our study suggests the potential of deep learning applications for a better understanding of the taxonomy and ecology of filamentous fungi amenable to axenic culturing. Meanwhile, our study also highlights some technical challenges in deep learning image analysis in ecology, highlighting that the domain of applicability of these methods needs to be carefully considered.

Progressing beyond colonization strategies to understand arbuscular mycorrhizal fungal life history.

Knowledge of differential life-history strategies in arbuscular mycorrhizal (AM) fungi is relevant for understanding the ecology of this group and its potential role in sustainable agriculture and carbon sequestration. At present, AM fungal life-history theories often focus on differential investment into intra- vs extraradical structures among AM fungal taxa, and its implications for plant benefits. With this Viewpoint we aim to expand these theories by integrating a mycocentric economics- and resource-based life-history framework. As in plants, AM fungal carbon and nutrient demands are stoichiometrically coupled, though uptake of these elements is spatially decoupled. Consequently, investment in morphological structures for carbon vs nutrient uptake is not in competition. We argue that understanding the ecology and evolution of AM fungal life-history trade-offs requires increased focus on variation among structures foraging for the same element, that is within intra- or extraradical structures (in our view a 'horizontal' axis), not just between them ('vertical' axis). Here, we elaborate on this argument and propose a range of plausible life-history trade-offs that could lead to the evolution of strategies in AM fungi, providing testable hypotheses and creating opportunities to explain AM fungal co-existence, and the context-dependent effects of AM fungi on plant growth and soil carbon dynamics.

Number and dissimilarity of global change factors influences soil properties and functions.

Soil biota and functions are impacted by various anthropogenic stressors, including climate change, chemical pollution or microplastics. These stressors do not occur in isolation, and soil properties and functions appear to be directionally driven by the number of global change factors acting simultaneously. Building on this insight, we here hypothesize that co-acting factors with more diverse effect mechanisms, or higher dissimilarity, have greater impacts on soil properties and functions. We created a factor pool of 12 factors and calculated dissimilarity indices of randomly-chosen co-acting factors based on the measured responses of soil properties and functions to the single factors. Results show that not only was the number of factors important, but factor dissimilarity was also key for predicting factor joint effects. By analyzing deviations of soil properties and functions from three null model predictions, we demonstrate that higher factor dissimilarity and a larger number of factors could drive larger deviations from null models and trigger more frequent occurrence of synergistic factor net interactions on soil functions (decomposition rate, cellulase, and ß-glucosidase activity), which provides mechanistic insights for understanding high-dimensional effects of factors. Our work highlights the importance of considering factor similarity in future research on interacting factors.

Nitrifying niche in estuaries is expanded by the plastisphere.

The estuarine plastisphere, a novel ecological habitat in the Anthropocene, has garnered global concerns. Recent geochemical evidence has pointed out its potential role in influencing nitrogen biogeochemistry. However, the biogeochemical significance of the plastisphere and its mechanisms regulating nitrogen cycling remain elusive. Using 15N- and 13C-labelling coupled with metagenomics and metatranscriptomics, here we unveil that the plastisphere likely acts as an underappreciated nitrifying niche in estuarine ecosystems, exhibiting a 0.9 ~ 12-fold higher activity of bacteria-mediated nitrification compared to surrounding seawater and other biofilms (stone, wood and glass biofilms). The shift of active nitrifiers from O2-sensitive nitrifiers in the seawater to nitrifiers with versatile metabolisms in the plastisphere, combined with the potential interspecific cooperation of nitrifying substrate exchange observed among the plastisphere nitrifiers, collectively results in the unique nitrifying niche. Our findings highlight the plastisphere as an emerging nitrifying niche in estuarine environment, and deepen the mechanistic understanding of its contribution to marine biogeochemistry.

Mycorrhization enhances plant growth and stabilizes biomass allocation under drought.

Plants and their symbionts, such as arbuscular mycorrhizal (AM) fungi, are increasingly subjected to various environmental stressors due to climate change, including drought. As a response to drought, plants generally allocate more biomass to roots over shoots, thereby facilitating water uptake. However, whether this biomass allocation shift is modulated by AM fungi remains unknown. Based on 5691 paired observations from 154 plant species, we conducted a meta-analysis to evaluate how AM fungi modulate the responses of plant growth and biomass allocation (e.g., root-to-shoot ratio, R/S) to drought. We found that AM fungi attenuate the negative impact of drought on plant growth, including biomass production, photosynthetic performance and resource (e.g. nutrient and water) uptake. Accordingly, drought significantly increased R/S in non-inoculated plants, but not in plants symbiotic with established AM fungal symbioses. These results suggest that AM fungi promote plant growth and stabilize their R/S through facilitating nutrient and water uptake in plants under drought. Our findings highlight the crucial role of AM fungi in enhancing plant resilience to drought by optimizing resource allocation. This knowledge opens avenues for sustainable agricultural practices that leverage symbiotic relationships for climate adaptation.

Microplastic pollution promotes soil respiration: A global-scale meta-analysis.

Microplastic (MP) pollution likely affects global soil carbon (C) dynamics, yet it remains uncertain how and to what extent MP influences soil respiration. Here, we report on a global meta-analysis to determine the effects of MP pollution on the soil microbiome and CO2 emission. We found that MP pollution significantly increased the contents of soil organic C (SOC) (21%) and dissolved organic C (DOC) (12%), the activity of fluorescein diacetate hydrolase (FDAse) (10%), and microbial biomass (17%), but led to a decrease in microbial diversity (3%). In particular, increases in soil C components and microbial biomass further promote CO2 emission (25%) from soil, but with a much higher effect of MPs on these emissions than on soil C components and microbial biomass. The effect could be attributed to the opposite effects of MPs on microbial biomass vs. diversity, as soil MP accumulation recruited some functionally important bacteria and provided additional C substrates for specific heterotrophic microorganisms, while inhibiting the growth of autotrophic taxa (e.g., Chloroflexi, Cyanobacteria). This study reveals that MP pollution can increase soil CO2 emission by causing shifts in the soil microbiome. These results underscore the potential importance of plastic pollution for terrestrial C fluxes, and thus climate feedbacks.

Aligning spatial ecological theory with the study of clonal organisms: the case of fungal coexistence.

Established ecological theory has focused on unitary organisms, and thus its concepts have matured into a form that often hinders rather than facilitates the ecological study of modular organisms. Here, we use the example of filamentous fungi to develop concepts that enable integration of non-unitary (modular) organisms into the established community ecology theory, with particular focus on its spatial aspects. In doing so, we provide a link between fungal community ecology and modern coexistence theory (MCT). We first show how community processes and predictions made by MCT can be used to define meaningful scales in fungal ecology. This leads to the novel concept of the unit of community interactions (UCI), a promising conceptual tool for applying MCT to communities of modular organisms with indeterminate clonal growth and hierarchical individuality. We outline plausible coexistence mechanisms structuring fungal communities, and show at what spatial scales and in what habitats they are most likely to act. We end by describing challenges and opportunities for empirical and theoretical research in fungal competitive coexistence.

Arbuscular mycorrhizal fungi attenuate negative impact of drought on soil functions.

Although positive effects of arbuscular mycorrhizal (AM) fungi on plant performance under drought have been well documented, how AM fungi regulate soil functions and multifunctionality requires further investigation. In this study, we first performed a meta-analysis to test the potential role of AM fungi in maintaining soil functions under drought. Then, we conducted a greenhouse experiment, using a pair of hyphal ingrowth cores to spatially separate the growth of AM fungal hyphae and plant roots, to further investigate the effects of AM fungi on soil multifunctionality and its resistance against drought. Our meta-analysis showed that AM fungi promote multiple soil functions, including soil aggregation, microbial biomass and activities of soil enzymes related to nutrient cycling. The greenhouse experiment further demonstrated that AM fungi attenuate the negative impact of drought on these soil functions and thus multifunctionality, therefore, increasing their resistance against drought. Moreover, this buffering effect of AM fungi persists across different frequencies of water supply and plant species. These findings highlight the unique role of AM fungi in maintaining multiple soil functions by mitigating the negative impact of drought. Our study highlights the importance of AM fungi as a nature-based solution to sustaining multiple soil functions in a world where drought events are intensifying.

The impact of fungi on soil protist communities in European cereal croplands.

Protists, a crucial part of the soil food web, are increasingly acknowledged as significant influencers of nutrient cycling and plant performance in farmlands. While topographical and climatic factors are often considered to drive microbial communities on a continental scale, higher trophic levels like heterotrophic protists also rely on their food sources. In this context, bacterivores have received more attention than fungivores. Our study explored the connection between the community composition of protists (specifically Rhizaria and Cercozoa) and fungi across 156 cereal fields in Europe, spanning a latitudinal gradient of 3000 km. We employed a machine-learning approach to measure the significance of fungal communities in comparison to bacterial communities, soil abiotic factors, and climate as determinants of the Cercozoa community composition. Our findings indicate that climatic variables and fungal communities are the primary drivers of cercozoan communities, accounting for 70% of their community composition. Structural equation modelling (SEM) unveiled indirect climatic effects on the cercozoan communities through a change in the composition of the fungal communities. Our data also imply that fungivory might be more prevalent among protists than generally believed. This study uncovers a hidden facet of the soil food web, suggesting that the benefits of microbial diversity could be more effectively integrated into sustainable agriculture practices.

Elevated levels of antibiotic resistance genes as a factor of human-caused global environmental change.

Antibiotic resistance genes (ARGs) have moved into focus as a critically important response variable in global change biology, given the increasing environmental and human health threat posed by these genes. However, we propose that elevated levels of ARGs should also be considered a factor of global change, not just a response. We provide evidence that elevated levels of ARGs are a global change factor, since this phenomenon is linked to human activity, occurs globally, and affects biota. We explain why ARGs could be considered the global change factor, rather than the organisms containing them; and we highlight the difference between ARGs and the presence of antibiotics, which are not necessarily linked since elevated levels of ARGs are caused by multiple factors. Importantly, shifting the perspective to elevated levels of ARGs as a factor of global change opens new avenues of research, where ARGs can be the experimental treatment. This includes asking questions about how elevated ARG levels interact with other global change factors, or how ARGs influence ecosystem processes, biodiversity or trophic relationships. Global change biology stands to profit from this new framing in terms of capturing more completely the real extent of human impacts on this planet.

Prediction of future microplastic accumulation in agricultural soils.

This study shows the general exponential rise in microplastic accumulation in agricultural soils, with fertilizer application speeding up this increase, and future predictions of microplastic concentrations. Utilizing data from the Broadbalk winter wheat experiment at Rothamsted Research, UK, from 1846 to 2022, Poisson regression models were applied to microplastic counts under different soil treatments, including farmyard manure, inorganic fertilizers, and control conditions. A mass conversion factor was applied to obtain the w/w relationship. Results indicated a significant annual increase in microplastic concentrations across all treatments, with fertilized soils showing a notably higher accumulation rate. Our study forecasts that, in 50 and 100 years from now, soils treated with fertilizers are expected to reach microplastic concentrations of 168.9 mg kg-1 (95% CI: 60.32-473.09) and 1159 mg kg-1 (95% CI: 200.49-6699.8) respectively, levels converging on those used in many experiments. This highlights the urgent need for strategies to mitigate microplastic pollution in agricultural fields. The results also help to choose predicted concentrations in global change experiments, as well as to motivate further research to explore the mechanisms of microplastic accumulation and the integration of these insights into broader agricultural and ecological models to guide sustainable practices and environmental conservation.

Moving restoration ecology forward with combinatorial approaches.

Our current planetary crisis, including multiple jointly acting factors of global change, moves the need for effective ecosystem restoration center stage and compels us to explore unusual options. We here propose exploring combinatorial approaches to restoration practices: management practices are drawn at random and combined from a locally relevant pool of possible management interventions, thus creating an experimental gradient in the number of interventions. This will move the current degree of interventions to higher dimensionality, opening new opportunities for unlocking unknown synergistic effects. Thus, the high dimensionality of global change (multiple jointly acting factors) would be more effectively countered by similar high-dimensionality in solutions. In this concept, regional restoration hubs play an important role as guardians of locally relevant information and sites of experimental exploration. Data collected from such studies could feed into a global database, which could be used to learn about general principles of combined restoration practices, helping to refine future experiments. Such combinatorial approaches to exploring restoration intervention options may be our best hope yet to achieve decisive progress in ecological restoration at the timescale needed to mitigate and reverse the most severe losses caused by global environmental change.

Towards establishing a fungal economics spectrum in soil saprobic fungi.

Trait-based frameworks are promising tools to understand the functional consequences of community shifts in response to environmental change. The applicability of these tools to soil microbes is limited by a lack of functional trait data and a focus on categorical traits. To address this gap for an important group of soil microorganisms, we identify trade-offs underlying a fungal economics spectrum based on a large trait collection in 28 saprobic fungal isolates, derived from a common grassland soil and grown in culture plates. In this dataset, ecologically relevant trait variation is best captured by a three-dimensional fungal economics space. The primary explanatory axis represents a dense-fast continuum, resembling dominant life-history trade-offs in other taxa. A second significant axis reflects mycelial flexibility, and a third one carbon acquisition traits. All three axes correlate with traits involved in soil carbon cycling. Since stress tolerance and fundamental niche gradients are primarily related to the dense-fast continuum, traits of the 2nd (carbon-use efficiency) and especially the 3rd (decomposition) orthogonal axes are independent of tested environmental stressors. These findings suggest a fungal economics space which can now be tested at broader scales.

Fungal traits help to understand the decomposition of simple and complex plant litter.

Litter decomposition is a key ecosystem process, relevant for the release and storage of nutrients and carbon in soil. Soil fungi are one of the dominant drivers of organic matter decomposition, but fungal taxa differ substantially in their functional ability to decompose plant litter. Knowledge is mostly based on observational data and subsequent molecular analyses and in vitro studies have been limited to forest ecosystems. In order to better understand functional traits of saprotrophic soil fungi in grassland ecosystems, we isolated 31 fungi from a natural grassland and performed several in vitro studies testing for i) leaf and wood litter decomposition, ii) the ability to use carbon sources of differing complexity, iii) the enzyme repertoire. Decomposition strongly varied among phyla and isolates, with Ascomycota decomposing the most and Mucoromycota decomposing the least. The phylogeny of the fungi and their ability to use complex carbon were the most important predictors for decomposition. Our findings show that it is crucial to understand the role of individual members and functional groups within the microbial community. This is an important way forward to understand the role of microbial community composition for the prediction of litter decomposition and subsequent potential carbon storage in grassland soils.

Drought induces moderate, diverse changes in the odour of grassland species.

Plants react to drought stress with numerous changes including altered emissions of volatile organic compounds (VOC) from leaves, which provide protection against oxidative tissue damage and mediate numerous biotic interactions. Despite the share of grasslands in the terrestrial biosphere, their importance as carbon sinks and their contribution to global biodiversity, little is known about the influence of drought on VOC profiles of grassland species. Using coupled gas chromatography-mass spectrometry, we analysed the odorants emitted by 22 European grassland species exposed to an eight-week-lasting drought treatment (DT; 30% water holding capacity, WHC). We focused on the odorants emitted during the light phase from whole plant shoots in their vegetative stage. Emission rates were standardised to the dry weight of each shoot. Well-watered (WW) plants (70% WHC) served as control. Drought-induced significant changes included an increase in total emission rates of plant VOC in six and a decrease in three species. Diverging effects on the number of emitted VOC (chemical richness) or on the Shannon diversity of the VOC profiles were detected in 13 species. Biosynthetic pathways-targeted analyses revealed 13 species showing drought-induced higher emission rates of VOC from one, two, three, or four major biosynthetic pathways (lipoxygenase, shikimate, mevalonate and methylerythritol phosphate pathway), while six species exhibited reduced emission rates from one or two of these pathways. Similarity trees of odorant profiles and their drought-induced changes based on a biosynthetically informed distance metric did not match species phylogeny. However, a phylogenetic signal was detected for the amount of terpenoids released by the studied species under WW and DT conditions. A comparative analysis of emission rates of single compounds released by WW and DT plants revealed significant VOC profile dissimilarities in four species only. The moderate drought-induced changes in the odorant emissions of grassland species are discussed with respect to their impact on trophic interactions across the food web. (294 words).

How widespread use of generative AI for images and video can affect the environment and the science of ecology.

Generative artificial intelligence (AI) models will have broad impacts on society including the scientific enterprise; ecology and environmental science will be no exception. Here, we discuss the potential opportunities and risks of advanced generative AI for visual material (images and video) for the science of ecology and the environment itself. There are clearly opportunities for positive impacts, related to improved communication, for example; we also see possibilities for ecological research to benefit from generative AI (e.g., image gap filling, biodiversity surveys, and improved citizen science). However, there are also risks, threatening to undermine the credibility of our science, mostly related to actions of bad actors, for example in terms of spreading fake information or committing fraud. Risks need to be mitigated at the level of government regulatory measures, but we also highlight what can be done right now, including discussing issues with the next generation of ecologists and transforming towards radically open science workflows.

A slow-fast trait continuum at the whole community level in relation to land-use intensification.

Organismal functional strategies form a continuum from slow- to fast-growing organisms, in response to common drivers such as resource availability and disturbance. However, whether there is synchronisation of these strategies at the entire community level is unclear. Here, we combine trait data for >2800 above- and belowground taxa from 14 trophic guilds spanning a disturbance and resource availability gradient in German grasslands. The results indicate that most guilds consistently respond to these drivers through both direct and trophically mediated effects, resulting in a 'slow-fast' axis at the level of the entire community. Using 15 indicators of carbon and nutrient fluxes, biomass production and decomposition, we also show that fast trait communities are associated with faster rates of ecosystem functioning. These findings demonstrate that 'slow' and 'fast' strategies can be manifested at the level of whole communities, opening new avenues of ecosystem-level functional classification.