Ecosystems

Forecasting changes to ecological communities is one of the central challenges in ecology. However, nonlinear dependencies, biotic interactions and data limitations have limited our ability to assess how predictable communities are. Here, we used a machine learning approach and environmental monitoring data (biological, physical and chemical) to assess the predictability of phytoplankton cell density in one lake across an unprecedented range of time‐scales. Communities were highly predictable over hours to months: model R² decreased from 0.89 at 4 hours to 0.74 at 1 month, and in a long‐term dataset lacking fine spatial resolution, from 0.46 at 1 month to 0.32 at 10 years. When cyanobacterial and eukaryotic algal cell densities were examined separately, model‐inferred environmental growth dependencies matched laboratory studies, and suggested novel trade‐offs governing their competition. High‐frequency monitoring and machine learning can set prediction targets for process‐based models and help elucidate the mechanisms underlying ecological dynamics.

Phytoplankton growth depends on various factors, and primarily on nutrient availability, light and watertemperature, whose distributions are largely controlled by hydrodynamics. Our main objective is to analyse thelink between spatial and temporal variability of surface water temperature and algal concentration in a largelake by means of remote sensing and hydrodynamic modelling. We compare ten years of satellite imagesshowing chlorophyll concentrations and surface water temperature of Lake Geneva. Our observations suggestdifferent correlations depending on the season. Elevated chlorophyll concentrations in spring are correlated withwarmer zones. But, in summer, higher chlorophyll concentrations are observed in colder zones. We show with athree-dimensional hydrodynamic model that the spatial variability of the surface water temperature reflects theupwelling and downwelling zones resulting from wind forcing. In springtime, nearshore downwellings inducelocally increased surface temperature and stratification, which are associated with high chlorophyll concentration.In summertime, colder surface temperature area, often interpreted as transient upwellings, representsthe thermal surface signature of wind-induced basin-scale internal waves, bringing either nutrients or phytoplanktonfrom deeper layers to the surface. Our study suggests the latter to be the dominant process, with thebasin-scale internal wave activity and associated transient summertime upwellings and downwellings havinglittle net effects on the algal concentration. This study finally demonstrates the necessity to connect remotesensing retrievals and three-dimensional hydrodynamic modelling to properly understand the dynamic of thelake ecosystems.