Search for: All records

Physics-based models are often used to study engineering and environmental systems. The ability to model these systems is the key to achieving our future environmental sustainability and improving the quality of human life. This article focuses on simulating lake water temperature, which is critical for understanding the impact of changing climate on aquatic ecosystems and assisting in aquatic resource management decisions. General Lake Model (GLM) is a state-of-the-art physics-based model used for addressing such problems. However, like other physics-based models used for studying scientific and engineering systems, it has several well-known limitations due to simplified representations of the physical processes being modeled or challenges in selecting appropriate parameters. While state-of-the-art machine learning models can sometimes outperform physics-based models given ample amount of training data, they can produce results that are physically inconsistent. This article proposes a physics-guided recurrent neural network model (PGRNN) that combines RNNs and physics-based models to leverage their complementary strengths and improves the modeling of physical processes. Specifically, we show that a PGRNN can improve prediction accuracy over that of physics-based models (by over 20% even with very little training data), while generating outputs consistent with physical laws. An important aspect of our PGRNN approach lies in its ability to incorporate the knowledge encoded in physics-based models. This allows training the PGRNN model using very few true observed data while also ensuring high prediction accuracy. Although we present and evaluate this methodology in the context of modeling the dynamics of temperature in lakes, it is applicable more widely to a range of scientific and engineering disciplines where physics-based (also known as mechanistic) models are used. 

Rivers and streams contribute to global carbon cycling by decomposing immense quantities of terrestrial plant matter. However, decomposition rates are highly variable and large-scale patterns and drivers of this process remain poorly understood. Using a cellulose-based assay to reflect the primary constituent of plant detritus, we generated a predictive model (81% variance explained) for cellulose decomposition rates across 514 globally distributed streams. A large number of variables were important for predicting decomposition, highlighting the complexity of this process at the global scale. Predicted cellulose decomposition rates, when combined with genus-level litter quality attributes, explain published leaf litter decomposition rates with high accuracy (70% variance explained). Our global map provides estimates of rates across vast understudied areas of Earth and reveals rapid decomposition across continental-scale areas dominated by human activities. 

Abstract Lakes are biogeochemical hotspots on the landscape, contributing significantly to the global carbon cycle despite their small areal coverage. Observations and models of lake carbon pools and fluxes are rarely explicitly combined through data assimilation despite successful use of this technique in other fields. Data assimilation adds value to both observations and models by constraining models with observations of the system and by leveraging knowledge of the system formalized by the model to objectively fill observation gaps. In this article, we highlight the utility of data assimilation in lake carbon cycling research by using the ensemble Kalman filter to combine simple lake carbon models with observations of lake carbon pools and fluxes. We demonstrate that data assimilation helps reduce uncertainty in estimates of lake carbon pools and fluxes and more accurately estimate the true carbon pool size compared to estimates derived from observations alone. Data assimilation techniques should be embraced as valuable tools for lake biogeochemists interested in learning about ecosystem dynamics and forecasting ecosystem states and processes.