Dynamic species classification of microorganisms across time, abiotic and biotic environments—A sliding window approach

Abstract

The development of video-based monitoring methods allows for rapid, dynamic and accurate monitoring of individuals or communities, compared to slower traditional methods, with far reaching ecological and evolutionary applications. Large amounts of data are generated using video-based methods, which can be effectively processed using machine learning (ML) algorithms into meaningful ecological information. ML uses user defined classes (e.g. species), derived from a subset (i.e. training data) of video-observed quantitative features (e.g. phenotypic variation), to infer classes in subsequent observations. However, phenotypic variation often changes due to environmental conditions, which may lead to poor classification, if environmentally induced variation in phenotypes is not accounted for. Here we describe a framework for classifying species under changing environmental conditions based on the random forest classification. A sliding window approach was developed that restricts temporal and environmentally conditions to improve the classification. We tested our approach by applying the classification framework to experimental data. The experiment used a set of six ciliate species to monitor changes in community structure and behavior over hundreds of generations, in dozens of species combinations and across a temperature gradient. Differences in biotic and abiotic conditions caused simplistic classification approaches to be unsuccessful. In contrast, the sliding window approach allowed classification to be highly successful, as phenotypic differences driven by environmental change, could be captured by the classifier. Importantly, classification using the random forest algorithm showed comparable success when validated against traditional, slower, manual identification. Our framework allows for reliable classification in dynamic environments, and may help to improve strategies for long-term monitoring of species in changing environments. Our classification pipeline can be applied in fields assessing species community dynamics, such as eco-toxicology, ecology and evolutionary ecology.

Warming reduces the effects of enrichment on stability and functioning across levels of organisation in an aquatic microbial ecosystem

“…Morphology and movement traits were used to classify individuals into the two consumer species using random forest classification (Pennekamp et al . ). Filtering removed spurious trajectories due to background motion.…”

“…Consumer abundance was quantified with video‐microscopy techniques (Pennekamp & Schtickzelle ; Pennekamp et al . , ). For each sample, the microcosm vessel was gently agitated, and 700 μL subsample was mounted onto a glass slide and covered with a glass lid.…”

Biodiversity increases and decreases ecosystem stability

“…We sampled each experimental unit every day for the first 7 days, then 3 times per week for the following 50 days and a final sampling 7 days later, resulting in time series of 27 time points over a 57-days period. We used video sampling techniques to count and measure individual ciliates in all communities 33 . For sampling, microcosms were taken out of the incubator, gently stirred to homogenize the culture and a sample was pipetted into a counting chamber.…”

Linking intraspecific trait variation to community abundance dynamics improves ecological predictability by revealing a growth–defence trade‐off

“…These traits were examined as they are likely to influence the strength of species interactions, by modifying the rate of predation or energetic content and handling time of prey. The automated video‐based counting and measurement pipeline have been carefully tested and shown to give unbiased estimates of Colpidium abundance and morphology (Pennekamp et al., , ).…”