Local Variability Mediates Vulnerability of Trout Populations to Land Use and Climate Change

Abstract

Land use and climate change occur simultaneously around the globe. Fully understanding their separate and combined effects requires a mechanistic understanding at the local scale where their effects are ultimately realized. Here we applied an individual-based model of fish population dynamics to evaluate the role of local stream variability in modifying responses of Coastal Cutthroat Trout (Oncorhynchus clarkii clarkii) to scenarios simulating identical changes in temperature and stream flows linked to forest harvest, climate change, and their combined effects over six decades. We parameterized the model for four neighboring streams located in a forested headwater catchment in northwestern Oregon, USA with multi-year, daily measurements of stream temperature, flow, and turbidity (2007-2011), and field measurements of both instream habitat structure and three years of annual trout population estimates. Model simulations revealed that variability in habitat conditions among streams (depth, available habitat) mediated the effects of forest harvest and climate change. Net effects for most simulated trout responses were different from or less than the sum of their separate scenarios. In some cases, forest harvest countered the effects of climate change through increased summer flow. Climate change most strongly influenced trout (earlier fry emergence, reductions in biomass of older trout, increased biomass of young-of-year), but these changes did not consistently translate into reductions in biomass over time. Forest harvest, in contrast, produced fewer and less consistent responses in trout. Earlier fry emergence driven by climate change was the most consistent simulated response, whereas survival, growth, and biomass were inconsistent. Overall our findings indicate a host of local processes can strongly influence how populations respond to broad scale effects of land use and climate change.

Fig 1. Representation of Key Processes in inSTREAM.

We highlight how the daily time series inputs of stream temperature, flow, and turbidity drive individual growth and survival and hence population dynamics including responses of fry emergence and biomass. A more detailed explanation of inSTREAM can be found in [–21].

Fig 2. Differences in Total Summer Biomass of Trout between Scenarios and Baseline.

Difference in mean total summer biomass (g) from the five replicated simulations over time for each scenario of forest harvest (FH), climate change (CC), and their combined effects (FH+CC) compared to baseline, in Gus Creek, Pothole Creek, Rock Creek, and Upper Mainstem (UM). Scenarios include manipulations of stream temperature and flow regimes (see methods narrative for detail). Only significant trends (P < 0.05) for the entire study period have been numerically shown with the slope of the trend (g/decade).

Fig 3. Influence of Flow and Temperature on Trout Biomass within each Scenario.

Boxplots of mean total summer biomass (g) of trout in Gus Creek, Pothole Creek, Rock Creek, and Upper Mainstem (UM) from five replicate simulations over the entire study period. Each boxplot incorporates 63 data points of the mean of every year’s summer biomass per scenario. Gray boxes represent pairwise comparisons of the influence of flow (Q), stream temperature (T), and both (Q+T) within each scenario of forest harvest (FH) and climate change (CC). Baseline and the combined scenarios (FH+CC) are shown for reference. Scenarios include manipulations of stream temperature and flow regimes (see methods narrative for detail). Significant pairwise differences are shown by a horizontal black line (P < 0.05). Significant differences between baseline and each scenario are noted. The point above or below each boxplot corresponds to the 5^th and 95^th percentile.

Fig 4. Trends in Fry Emergence of Trout across Scenarios.

DOY from five replicate simulations when median number of modeled fry had emerged over time in Gus Creek, Pothole Creek, Rock Creek, and Upper Mainstem (UM). Scenarios include manipulations of stream temperature and flow regimes (see methods narrative for detail). Only significant trends (P < 0.05) over time are listed and include the slope of the trend (days per decade). Negative values represent early fry emergence. Gaps in data are due to years with no fry emergence because model thresholds for spawning, egg development, or emergence were not met.