Tree size thresholds produce biased estimates of forest biomass dynamics

- Large trees have been widely used to assess temporal changes in forest biomass.
- Productivity is underestimated when sampling only large trees.
- Biomass loss is underestimated when sampling only large trees.
- Sampling biases were particularly significant in young stands.
- Temporal trends assessed by large trees may produce bias.

Studies that examine forest biomass dynamics often rely on long-term, spatially extensive, repeatedly measured permanent sample plots. Due to the intensive cost of sampling all trees within these plots, an arbitrary size threshold is typically imposed, which leads to only larger trees being sampled. However, it remains unclear whether the sampling of only large trees is representative of the entirety of stands of diverse sizes; the sampling of only large trees may produce biased estimates of biomass dynamics (growth, ingrowth, and mortality). Using a network of 141 permanent sample plots from Manitoba, Canada, with all trees of >1.3 m in height repeatedly measured, we constructed three distinct data sets, with 10 cm, 5 cm, and no diameter at breast height threshold, to illustrate that total productivity and mortality are increasingly underestimated with increasingly larger diameter at breast height thresholds. This effect is particularly significant in young stands, where productivity estimates peak at least 20 years earlier than the determined estimates under large thresholds. We highlight the need to account for smaller trees in long-term observational studies to ensure unbiased estimates of stand level aboveground biomass productivity and loss.