The ingredients of this study are classic in soil ecology and in the study of belowground-aboveground interactions: the presence of plants, draught and mineral fertilization (for the experimental treatments) and microbial carbon, microbial nitrogen, microbial phosphorus, substrate-induced respiration, cumulative extracellular enzyme activity, nitrogen mineralization potential, nitrification potential, denitrification potential (as a result of the treatments). It is interesting and useful to have tested all the combinations of the three treatments and the height variables (also in the form of a soil multifunctionality index) in the same study and to have been able to express hypotheses on the underlying mechanisms of interaction.

A key result is that mineral fertilization can reduce the soil ability to withstand draughts in terms of soil multifunctionality. This effect would be due to the increase in plant growth associated with fertilization, which reduces the availability of soil resources. This subsequently affects microbial diversity and soil multifunctionality. This confirms that the interactions between plants and soil microorganisms are complex and relevant for understanding and predicting the impact of climate and fertilization on soil functioning and the sustainability of plant-soil systems.

Although the study is rather fundamental, it has been designed to be relevant to grassland management and points to very general mechanisms that are likely to be relevant to arable land management. It would therefore be useful to repeat this work for interactions between a crop and its soil. Finally, it would be crucial to test the impact of heavy fertilization in intensive cropping systems on the resistance and resilience of soil functions to climate variability and climate changes.

A slightly disturbing fact is that the underlying interactions are probably so complicated that it seems so far impossible to me to make predictions about the ranking of the height combinations of treatments on each soil variable. But this complexity is clearly inherent to ecology and, in particular, plant-soil interactions.

References

Gabin Piton, Arnaud Foulquier, Lionel Bernard, Aurelie Bonin, Thomas Pommier, Sandra Lavorel, Roberto Geremia, Jean Christophe Clement (2025) Mineral fertilization reduces the drought resistance of soil multifunctionality in a mountain grassland system through plant-soil interactions. bioRxiv, ver.2 peer-reviewed and recommended by PCI Ecology https://doi.org/10.1101/2024.09.19.613911

Animal behavior, like other kinds of phenotypic plasticity, is crucial for survival and reproduction in environments that vary over space and time. Behaviors themselves may need to be flexible when the distributions of environmental conditions themselves change; for example, short-term weather patterns and long-term climate conditions are changing due to human activity, and behavioral flexibility will likely be key to some population persisting during these changes and others going extinct. Thus, measuring this flexibility is key to understanding which species may be resilient to climate change.

Measuring behavioral flexibility is tricky as different studies may define and measure it differently and yet other studies may measure similar kinds of flexibility yet call them different things. This so-called "jingle-jangle" issue suggests that studies can more robustly measure a behavioral trait when they use multiple behavioral tests. An additional issue is that measuring behavioral traits that vary between individuals due to genetic or development effects, often referred to as "personality" traits, requires that those trait differences be repeatable across time and between individuals. 

With these issues in mind, McCune et al. (2019) presented a preregistration for experiments using a population of great-tailed grackles to investigate how behavioral flexibility relates to other important traits that are known to vary across individuals including exploratory behavior, boldness, and persistence and motor diversity in accessing a new food source. Behavioral flexibility is measured by the rate of learning a color associated with reward after first learning an association with a different color. That preregistration was recommended by PCI Ecology (Van Cleve, 2019). Now, McCune et al. (2025) present results from this study and find that only exploration of a novel environment and persistence were statistically repeatable behaviors. Both behaviors were not significantly correlated with behavioral flexibility. However, grackles that were trained to perform better in the color reversal learning task were more exploratory. This association between behavioral flexibility and exploratory tendencies may have evolved in grackles to help them survive in new environments, which they have proven very capable of doing as they have expanded their range in North American over the last 140 years (Wehtje, 2003).

There are a few key features of McCune et al. (2025) to merit recommendation. First, the authors are intent on demonstrating careful behavioral research practices including, as evidenced above, preregistering their hypotheses and predictions and making available both the preregistered and final analysis code. Second, the study demonstrates a thorough attempt to address two aspects that bedevil behavioral research, namely the "jingle-jangle" issue and repeatability of traits across individuals. Even after measuring multiple features of boldness, exploratory, persistence, McCune et al. (2025) find that only a subset of the measured behaviors are repeatable and only a subset of those are associated with behavioral flexibility. This suggests that only thorough studies like McCune et al. (2025) can start to probe difficult to measure behavioral associations that may be key to understanding how species will respond to our changing world.

References

McCune K, Lukas D,  MacPherson M, Logan CJ (2025) Behavioral flexibility is related to exploration, but not boldness, persistence or motor diversity. EcoEvoRxiv, ver.2 peer-reviewed and recommended by PCI Ecology https://doi.org/10.32942/X2H33F

Van Cleve, J. (2019) Probing behaviors correlated with behavioral flexibility. PCI Ecology, 100020. https://doi.org/10.24072/pci.ecology.100020

McCune K, Rowney C, Bergeron L, Logan CJ. (2019) Is behavioral flexibility linked with exploration, but not boldness, persistence, or motor diversity? (http://corinalogan.com/Preregistrations/g_exploration.html) In principle acceptance by PCI Ecology of the version on 27 Mar 2019

Wehtje, W. (2003) The range expansion of the great-tailed grackle (Quiscalus mexicanus Gmelin) in North America since 1880. Journal of Biogeography 30:1593–1607 https://doi.org/10.1046/j.1365-2699.2003.00970.x.

Although artificial intelligence (AI) offers a powerful solution to the bottleneck in processing camera-trap imagery, ecological researchers have long struggled with the practical application of such tools. The complexity of development, training, and deploying deep learning models remains a significant barrier for many conservationists, ecologists, and citizen scientists who lack formal training in computer science. While platforms like Wildlife Insights (Ahumada et al. 2020), MegaDetector (Beery et al. 2019), and tools such as ClassifyMe (Falzon et al. 2020) have laid critical groundwork in AI-assisted wildlife monitoring, these solutions either remain opaque, lack customisability, or are often locked behind commercial or infrastructural limitations. Others, like Sherlock (Penn et al., 2024), while powerful, are not always deployable without significant local expertise. A notable example of a more open and collaborative approach is the DeepFaune initiative, which provides a free, high-performance tool for the automatic classification of European wildlife in camera-trap images, highlighting the growing importance of locally relevant, user-friendly AI solutions developed through broad partnerships (Rigoudy et al. 2022).

It is in this context that Brook et al. (2025) makes a compelling and timely contribution. The authors present an elegant, open-source AI pipeline—MEWC (Mega-Efficient Wildlife Classifier)—that bridges the gap between high-performance image classification and usability by non-specialists. Combining deep learning advances with user-friendly software engineering, MEWC enables users to detect, classify, and manage wildlife imagery without advanced coding skills or reliance on high-cost third-party infrastructures.

What makes MEWC particularly impactful is its modular and accessible architecture. Built on Docker containers, the system can run seamlessly across different operating systems, cloud services, and local machines. From image detection using MegaDetector to classifier training via EfficientNet or Vision Transformers, the pipeline maintains a careful balance between technical flexibility and operational simplicity. This design empowers ecologists to train their own species-specific classifiers and maintain full control over their data—an essential feature given the increasing scrutiny around data sovereignty and privacy.

The practical implications are impressive. The case study provided—focused on Tasmanian wildlife—demonstrates not only high accuracy (up to 99.6%) but also remarkable scalability, with models trainable even on mid-range desktops. Integration with community tools like Camelot (Hendry and Mann 2018)and AddaxAI (Lunteren 2023) further enhances its utility, allowing rapid expert validation and facilitating downstream analyses.

Yet the article does not shy away from discussing the limitations. As with any supervised system, MEWC’s performance is only as good as the training data provided. Class imbalances, rare species, or subtle morphological traits can challenge even the best classifiers. Moreover, the authors caution that pre-trained models may not generalise well across regions with different fauna, requiring careful curation and expert tagging for local deployments.

One particularly exciting future direction briefly mentioned—and worth highlighting—is MEWC’s potential application to behavioural and cognitive ecology (Sueur et al. 2013; Battesti et al. 2015; Grampp et al. 2019). Studies in these domains underscore the need for scalable tools to quantify social dynamics in real time. By assisting with individual identification and the detection of postures or spatial configurations, MEWC could significantly enhance the throughput, reproducibility, and objectivity of such research.

This opens the door to even richer applications. Behavioural ecologists might use MEWC for fine-grained detection tasks such as individual grooming interactions, kin proximity analysis, or identification of tool-use sequences in wild primates. Similarly, for within-species classification (e.g. sex, reproductive state, or disease symptoms), MEWC's modular backbone and compatibility with transfer learning architectures like EfficientNet or ViT make it a suitable candidate for expansion (Ferreira et al. 2020; Clapham et al. 2022).

In conclusion (Brook et al. 2025) have delivered more than a tool—they've designed an ecosystem. MEWC lowers the technical barrier to AI in ecology, promotes open science, and enables tailored workflows for a wide variety of conservation, research, and educational contexts. For anyone interested in democratising ecological AI and reclaiming control over wildlife-monitoring data, this article and its associated software are essential resources.

References

Ahumada JA, Fegraus E, Birch T, et al (2020) Wildlife Insights: A Platform to Maximize the Potential of Camera Trap and Other Passive Sensor Wildlife Data for the Planet. Environmental Conservation 47:1–6. https://doi.org/10.1017/S0376892919000298

Battesti M, Pasquaretta C, Moreno C, et al (2015) Ecology of information: social transmission dynamics within groups of non-social insects. Proceedings of the Royal Society of London B: Biological Sciences 282:20142480. https://doi.org/10.1098/rspb.2014.2480

Beery S, Morris D, Yang S, et al (2019) Efficient pipeline for automating species ID in new camera trap projects. Biodiversity Information Science and Standards 3:e37222. https://doi.org/10.3897/biss.3.37222

Barry W. Brook, Jessie C. Buettel, Peter van Lunteren, Prakash P. Rajmohan, R. Zach Aandahl (2025) MEWC: A user-friendly AI workflow for customised wildlife-image classification. EcoEvoRxiv, ver.3 peer-reviewed and recommended by PCI Ecology https://doi.org/10.32942/X2ZW3D

Clapham M, Miller E, Nguyen M, Van Horn RC (2022) Multispecies facial detection for individual identification of wildlife: a case study across ursids. Mamm Biol 102:921–933. https://doi.org/10.1007/s42991-021-00168-5

Falzon G, Lawson C, Cheung K-W, et al (2020) ClassifyMe: A Field-Scouting Software for the Identification of Wildlife in Camera Trap Images. Animals 10:58. https://doi.org/10.3390/ani10010058

Ferreira AC, Silva LR, Renna F, et al (2020) Deep learning-based methods for individual recognition in small birds. Methods in Ecology and Evolution 11:1072–1085. https://doi.org/10.1111/2041-210X.13436

Grampp M, Sueur C, van de Waal E, Botting J (2019) Social attention biases in juvenile wild vervet monkeys: implications for socialisation and social learning processes. Primates 60:261–275 https://doi.org/10.1007/s10329-019-00721-4​

Hendry H, Mann C (2018) Camelot—intuitive software for camera-trap data management. Oryx 52:15–15. https://doi.org/10.1017/S0030605317001818

Lunteren P van (2023) AddaxAI: A no-code platform to train and deploy custom YOLOv5 object detection models. Journal of Open Source Software 8:5581. https://doi.org/10.21105/joss.05581

Rigoudy N, Dussert G, Benyoub A, et al (2022) The DeepFaune initiative: a collaborative effort towards the automatic identification of the French fauna in camera-trap images. bioRxiv 2022–03

Sueur C, MacIntosh AJJ, Jacobs AT, et al (2013) Predicting leadership using nutrient requirements and dominance rank of group members. Behav Ecol Sociobiol 67:457–470. https://doi.org/10.1007/s00265-012-1466-5