More Like this

1. A deep-learning model for rapid spatiotemporal prediction of coastal water levels

   https://doi.org/10.1016/j.coastaleng.2024.104504  

   Shahabi, Ali; Tahvildari, Navid (June 2024, Coastal Engineering)

   With the increasing impact of climate change and relative sea level rise, low-lying coastal communities face growing risks from recurrent nuisance flooding and storm tides. Thus, timely and reliable predictions of coastal water levels are critical to resilience in vulnerable coastal areas. Over the past decade, there has been increasing interest in utilizing machine learning (ML) based models for emulation and prediction of coastal water levels. However, flood advisory systems still rely on running computationally demanding hydrodynamic models. To alleviate the computational burden, these physics-based models are either run at small scales with high resolution or at large scales with low resolution. While ML-based models are very fast, they face challenges in terms of ensuring reliability and ability to capture any surge levels. In this paper, we develop a deep neural network for spatiotemporal prediction of water levels in coastal areas of the Chesapeake Bay in the U.S. Our model relies on data from numerical weather prediction models as the atmospheric input and astronomical tide levels, while its outputs are time series of predicted water levels at several tide gauge locations across the Chesapeake Bay. We utilized a CNN-LSTM setting as the architecture of the model. The CNN part extracts the features from a sequence of gridded wind fields and fuses its output to several independent LSTM units. The LSTM units concatenate the atmospheric features with respective astronomical tide levels and produce water level time series. The novel contribution of the present work is in spatiotemporality and in prioritization of the physical relationships in the model to maintain a high analogy to hydrodynamic modeling, either in the network architecture or in the selection of predictors and predictands. The results show that this setting yields a strong performance in predicting coastal water levels that cause flooding from minor to major levels. We also show that the model stands up successfully to the rigorous comparison with a high-fidelity ADCIRC model, yielding mean RMSE and correlation coefficient of 14.3 cm and 0.94, respectively, in two extreme cases, versus 12.30 cm and 0.96 for the ADCIRC model. The results highlight the practical feasibility of employing fast yet inexpensive data-driven models for resilient coastal management. 

   more » « less
2. The Performance of LSTM and BiLSTM in Forecasting Time Series

   https://doi.org/10.1109/BigData47090.2019.9005997  

   Siami-Namini, Sima; Tavakoli, Neda; Namin, Akbar Siami (December 2019, 2019 IEEE International Conference on Big Data (Big Data))

   Machine and deep learning-based algorithms are the emerging approaches in addressing prediction problems in time series. These techniques have been shown to produce more accurate results than conventional regression-based modeling. It has been reported that artificial Recurrent Neural Networks (RNN) with memory, such as Long Short-Term Memory (LSTM), are superior compared to Autoregressive Integrated Moving Average (ARIMA) with a large margin. The LSTM-based models incorporate additional “gates” for the purpose of memorizing longer sequences of input data. The major question is that whether the gates incorporated in the LSTM architecture already offers a good prediction and whether additional training of data would be necessary to further improve the prediction. Bidirectional LSTMs (BiLSTMs) enable additional training by traversing the input data twice (i.e., 1) left-to-right, and 2) right-to-left). The research question of interest is then whether BiLSTM, with additional training capability, outperforms regular unidirectional LSTM. This paper reports a behavioral analysis and comparison of BiLSTM and LSTM models. The objective is to explore to what extend additional layers of training of data would be beneficial to tune the involved parameters. The results show that additional training of data and thus BiLSTM-based modeling offers better predictions than regular LSTM-based models. More specifically, it was observed that BiLSTM models provide better predictions compared to ARIMA and LSTM models. It was also observed that BiLSTM models reach the equilibrium much slower than LSTM-based models. 

   more » « less
3. ML-Based Streamflow Prediction in the Upper Colorado River Basin Using Climate Variables Time Series Data

   https://doi.org/10.3390/hydrology10020029  

   Hosseinzadeh, Pouya; Nassar, Ayman; Boubrahimi, Soukaina Filali; Hamdi, Shah Muhammad (February 2023, Hydrology)

   Streamflow prediction plays a vital role in water resources planning in order to understand the dramatic change of climatic and hydrologic variables over different time scales. In this study, we used machine learning (ML)-based prediction models, including Random Forest Regression (RFR), Long Short-Term Memory (LSTM), Seasonal Auto- Regressive Integrated Moving Average (SARIMA), and Facebook Prophet (PROPHET) to predict 24 months ahead of natural streamflow at the Lees Ferry site located at the bottom part of the Upper Colorado River Basin (UCRB) of the US. Firstly, we used only historic streamflow data to predict 24 months ahead. Secondly, we considered meteorological components such as temperature and precipitation as additional features. We tested the models on a monthly test dataset spanning 6 years, where 24-month predictions were repeated 50 times to ensure the consistency of the results. Moreover, we performed a sensitivity analysis to identify our best-performing model. Later, we analyzed the effects of considering different span window sizes on the quality of predictions made by our best model. Finally, we applied our best-performing model, RFR, on two more rivers in different states in the UCRB to test the model’s generalizability. We evaluated the performance of the predictive models using multiple evaluation measures. The predictions in multivariate time-series models were found to be more accurate, with RMSE less than 0.84 mm per month, R-squared more than 0.8, and MAPE less than 0.25. Therefore, we conclude that the temperature and precipitation of the UCRB increases the accuracy of the predictions. Ultimately, we found that multivariate RFR performs the best among four models and is generalizable to other rivers in the UCRB. 

   more » « less
4. Dual‐Transformer Deep Learning Framework for Seasonal Forecasting of Great Lakes Water Levels

   https://doi.org/10.1029/2024JH000519  

   Chen, Yi; Xue, Pengfei (June 2025, Journal of Geophysical Research: Machine Learning and Computation)

   Abstract The Great Lakes of North America form one of the largest freshwater systems on Earth, and their lake‐wide average water levels (lake levels) can fluctuate by more than 0.5 m on a seasonal scale. These fluctuations pose substantial challenges for coastal resilience, flood risk management, and navigation planning. Accurate seasonal forecasting of lake levels using traditional mechanistic models is challenging due to the complex physical mechanisms and coupled hydroclimatic processes involved. Recently, deep learning has gained prominence in geoscience applications for its ability to recognize intricate patterns within multiphysical data sets. Here, we introduce a novel Dual‐Transformer deep learning framework, tested on the Great Lakes. This architecture integrates two modified Transformer models: the Prophet, which predicts underlying trends, and the Critic, which refines the Prophet's predictions. The final lake level prediction is derived by weighting the outputs of both models through a multi‐layer perceptron, jointly trained with the Prophet and Critic to enhance overall accuracy. Our results demonstrate that the innovative learning framework achieves the highest prediction accuracy compared to established deep learning models when using identical input features. It attains a root mean square error of 4–7 cm in predicting lake levels up to 6 months in advance across the lakes. Additionally, the Dual‐Transformer model runs six orders of magnitude faster than conventional mechanistic models, producing results in less than one second on a typical personal computer. These findings suggest that our deep learning framework has strong potential to advance lake level prediction and carries important implications for water management and disaster mitigation, thereby enhancing the quality of life in coastal regions. 

   more » « less
5. Probabilistic hierarchical interpolation and interpretable neural network configurations for flood prediction

   https://doi.org/10.5194/hess-30-371-2026  

   Saberian, Mostafa; Samadi, Vidya; Popescu, Ioana (January 2026, Hydrology and Earth System Sciences)

   Abstract. The past few years have witnessed the rise of neural networks (NNs) applications for hydrological time series modeling. By virtue of their capabilities, NN models can achieve unprecedented levels of performance when learning how to solve increasingly complex rainfall-runoff processes via data, making them pivotal for the development of computational hydrologic tasks such as flood predictions. The NN models should, to be considered practical, provide a probabilistic understanding of the model mechanisms and predictions and hints on what could perturb the model. In this paper, we developed two NN models, i.e., Neural Hierarchical Interpolation for Time Series Forecasting (N-HiTS) and Network-Based Expansion Analysis for Interpretable Time Series Forecasting (N-BEATS) with a probabilistic multi-quantile objective and benchmarked them with long short-term memory (LSTM) for flood prediction across two headwater streams in Georgia and North Carolina, USA. To generate a probabilistic prediction, a Multi-Quantile Loss was used to assess the 95th percentile prediction uncertainty (95 PPU) of multiple flooding events. Extensive experiments demonstrated the advantages of hierarchical interpolation and interpretable architecture, where both N-HiTS and N-BEATS provided an average accuracy improvement of ∼ 5 % over the LSTM benchmarking model. On a variety of flooding events, both N-HiTS and N-BEATS demonstrated significant performance improvements over the LSTM benchmark and showcased their probabilistic predictions by specifying a likelihood objective. 

   more » « less