Jared Willard

TL;DR: In this article , the authors demonstrate the use of classical machine learning (ML) models, support vector regression and gradient boosted trees (XGBoost), for monthly water quality prediction in 78 pristine and human-impacted catchments of the Mid-Atlantic and Pacific Northwest hydrologic regions spanning different geologies, climate, and land use.

TL;DR: A physics-guided machine learning approach that combines advanced machine learning models and physics-based models to improve the prediction of water flow and temperature in river networks is proposed and shown to produce better performance when generalized to different seasons or river segments with different streamflow ranges.

TL;DR: In this paper , the authors used a long short-term memory deep learning model and compared to existing process-based and linear regression models to estimate daily surface water temperature, lake metadata, and daily weather conditions for lakes bigger than 4 ha in the conterminous United States.

TL;DR: In this paper, a physics-guided recurrent neural network model (PGRNN) is proposed for modeling the dynamics of temperature in lakes, which combines RNNs and physics-based models to leverage their complementary strengths and improve the modeling of physical processes.

TL;DR: Tayal et al. as discussed by the authors proposed a novel machine learning based approach for integrating static and time-series data in deep recurrent models, which is called Invertibility-Aware-Long Short-Term Memory (IA-LSTM), and demonstrate its effectiveness in predicting lake temperature.