The latest issue of Methods in Ecology and Evolution is now online!

Senior Editor Bob O’Hara has selected five Featured Articles this month, including methods for predicting pollinator abundance, evaluating species distribution modelling applications and accelerating image‐based ecological surveys using interactive machine learning – find out about all of them below.

We also have 12 articles that are free to read, including five Applications and two Practical Tools articles – no subscription required!

Featured Articles

Scenarios for valuing sample information in natural resources (open access) Uncertainty is ubiquitous in natural resource systems, science and management. Sample data are obtained in order to reduce uncertainty, thereby increasing knowledge and improving resource management, but sampling always comes at a cost of some sort. In this paper, Williams & Brown describe five scenarios for analysing the value of sample information, showing their usefulness for guiding design of data collection and selecting management actions.

Evaluation method for species distribution modelling applications The area under the curve (AUC) of the receiving‐operating characteristic is almost universally used to assess the performance of species distribution models (SDMs), despite the well‐recognised problems encountered with this approach, mainly present when dealing with presence‐only data. Here Jiménez & Soberón present a probabilistic treatment of the presence‐only problem, and derive a method to assess the performance of SDMs based on the analysis of an area‐presence plot and the SDM outputs represented in both geographic and environmental spaces.

Reliably predicting pollinator abundance (open access) Many models exist which predict pollinator abundance, but few have been calibrated against observational data from multiple habitats to ensure their predictions are accurate. Here, Gardner et al. calibrate the most advanced process‐based pollinator abundance model available for bumblebees and solitary bees using survey data. They compare three versions of the model, which all show significant agreement with the survey data, demonstrating this model’s potential to reliably map pollinator abundance, but there are significant differences between the nesting/floral attractiveness scores obtained by the two calibration methods and from the original expert opinion scores.

The bioseq package (free access) With the democratisation of molecular biology, increasingly more ecologists are required to analyse complex datasets including biological sequences. Here, François Keck presents the package bioseq, a free, comprehensive toolset for handling biological sequences in R. The package implements three classes to work with DNA, RNA and amino acid sequences, and includes a collection of functions for performing basic editing operations on sequences and biological conversion among classes.

Annotation Interface for Data‐driven Ecology (open access) Ecological surveys increasingly rely on large‐scale image datasets, resulting in volumes of photo‐interpretation labour. Here, Kellenberger et al. present the Annotation Interface for Data‐driven Ecology (AIDE), an open‐source web framework designed to alleviate the task of image annotation for ecological surveys. AIDE employs an easy‐to‐use and customisable labelling interface that supports multiple users and closely integrates users and machine learning models into a feedback loop, where user‐provided annotations are employed to re‐train the model, and the latter is applied over unlabelled images.

Applications and Practical Tools

We have five Applications and two Practical Tools articles in this month’s issue. Two of them were selected for our Featured Articles, but read about the others below.


Refined Shortest Paths (Free Access) Acoustic telemetry enables spatial ecologists to collect movement data from a variety of aquatic species but in estuaries and rivers, accounting for the complex shape of water bodies is challenging. Here, Niella et al. present RSP (Refined Shortest Paths), a new R package for analysing the movements of animals tracked with acoustic transmitters in environments constrained by landmasses. Showcased examples demonstrate how RSP can be used to analyse intra‐ and interspecific movement patterns; determine similarities in habitat use; identify the environmental conditions responsible for influencing the size of the space use areas; and assess levels of spatial overlap between different species.

Artificial intelligence for imperfect detection (free access) Partially observable Markov decision processes (POMDPs) have been applied in conservation, applied ecology and natural resource management to solve problems such as deciding when to stop managing or surveying threatened species that are difficult to detect. However, POMDPs remain inaccessible to most applied ecologists. Here, Pascal et al. present the shiny R package smsPOMDP, which solves the problem of ‘When to stop managing or surveying cryptic threatened species?’

DeepForest (Free Access) Remote sensing of forested landscapes can transform the speed, scale and cost of forest research. The delineation of individual trees in remote sensing images is an essential task in forest analysis. Here, Weinstein et al. introduce DeepForest, a new Python package that detects individual trees in high resolution RGB imagery using deep learning. The authors illustrate the workflow of DeepForest using data from the National Ecological Observatory Network, a tropical forest in French Guiana, and street trees from Portland, Oregon.

Practical Tools

Tensor decomposition for infectious disease incidence data (open access) Seasonality in infectious disease transmission can result from climatic forces, variation in contact rates, e.g. as a result of migration, or temporary surges in birth rates. Tensor decomposition has been used in many disciplines to uncover dominant trends in multi‐dimensional data. Here, Korevaar et al. introduce tensors as a novel method for decomposing oscillatory infectious disease time series. The method is able to isolate variation in disease seasonality as a result of variation in demographic rates, allowing them to discern variation in the strength of such signals by space and population size.

Artificial seeds (free access) Seed beetle model systems are used in a variety of ecological and evolutionary research studies, and one of their strengths is the use of artificial seeds to remove experimental confounds. However, they require many artificial seeds, and current methods of producing them are laborious, limiting their application. Here, Holmes et al. develop an efficient method for producing artificial seeds. They outline steps to produce artificial seeds and describe a new technique for transferring beetle eggs laid on natural seeds to artificial seeds.

The Walrus on the Cover

This issue’s cover shows a female Pacific walrus on an ice floe in the Chukchi Sea. Walrus habitat is remote and difficult to access, making it challenging to study the life history of these iconic Arctic mammals. In their article, Clark et al. explore the use of strontium and barium in walrus teeth as indicators of weaning age. Pacific walruses are an important food resource for Russian and Alaska Native communities, and walrus teeth are collected during subsistence harvests to monitor the age structure of hunted animals. Growth layers in teeth archive a lifetime record of trace element concentrations in an animal’s body, and specific patterns of accumulation of strontium and barium have been associated with nursing and weaning in some terrestrial mammals. Age‐at‐weaning is reflective of maternal investment, which is linked to the health and nutritional status of the mother. The ability to determine weaning age by examining patterns in walrus tooth cementum adds a valuable tool to the arsenal of wildlife managers, and may provide important insight into the status of walrus populations as the Arctic continues to change. Credit: U.S. Fish and Wildlife Service, Casey Clark.