Predicting how aquatic ecosystems will respond to increasing pressures — from changing climate to increasing demands for ecosystem services — is extremely challenging, due to complexities of aquatic ecosystems themselves, as well as their interactions with adjacent ecosystems and exogenous forcing.
By putting boundaries on an aquatic ecosystem, we can quantify inputs, outputs and storage - an overall mass balance. Only by using such a process-based mass balance, we are able to answer research questions about interactions and fluxes inside the ecosystem.
Process-based aquatic ecosystem models are powerful tools to simulate long-term ecosystem processes due to their low computational and input data need. Scientists and managers utilize process-based models to simulate how future climatic conditions would affect water quality or to forecast ecological processes in near-time. Using standardized workflows, as well as ensemble modeling and intercomparison studies, we can address model uncertainty and provide stakeholders with advanced information.
As process-based models have shortcomings regarding their performance, a recent stride in modeling is to combine mechanistic knowledge of ecosystem processes with monitoring data from long-term monitoring and high-frequency measurements in a data-driven deep learning model. The new paradigm of Knowledge-guided machine learning (KGML) aims to improve ecosystem projections while still providing outputs that are ecologically and physically valid.
Main research themes
The timings of biotic activity and physical events define a lake's phenology. But as our planet and our climate are rapidly changing, mismatches between phenological events will happen. My research aims to quantify how these temporal and spatial matches/mismatches between biotic (ecosystem metabolism, phytoplankton succession, zooplankton grazing) and abiotic processes (stratification, ice formation, nutrient runoffs) will change how an aquatic ecosystem functions.
Take a look at Ladwig et al. (2022)
Process-based models to simulate water quality and ecosystem dynamics are powerful tools to explore feedbacks within aquatic ecosystems and to explore climate change scenarios. To ease model application and development, I focus on (a) developing standardized modeling workflows, and (b) conducting inter-model comparison studies to quantify performance and uncertainty. A standardized ensemble modeling methodology is important to assess climate change impacts on our precious freshwater resources.
Take a look at: Ladwig et al. (2021)
Knowledge-Guided Machine Learning
Merging process-based modeling with deep learning shows promising results on how to improve lake modeling by training deep learning models on synthetic and observed data. Still such hybrid models have not yet widely been developed and tested for ecological research question. Developing novel hybrid models could revolutionize our applications of aquatic ecosystem models by providing improved projections that are still ecologically and physically valid.
Take a look at: Ladwig et al. (2023).
"The purpose of computing is insight, not numbers."
- Richard W. Hamming