Forecasting of Extreme Storm Tide Events Using NARX Neural Network-Based Models

An optimized NARX-based model for predicting thermal dynamics and heatwaves in rivers

The thermal dynamics within river ecosystems represent critical areas of study due to their profound impact on overall aquatic health. With the rising prevalence of heatwaves in rivers, a consequence of climate change, it is imperative to deepen our understanding through comprehensive research efforts. Despite this urgency, there remains a noticeable dearth in studies aimed at refining modeling techniques to precisely characterize the duration and intensity of these events. In response to this gap, the present study endeavors to augment the NARX-based model (Nonlinear Autoregressive network with Exogenous Inputs) to enhance predictive capabilities regarding thermal dynamics and river heatwaves. The optimized NARX-based model included the Bayesian Optimization (BO) algorithm, which allows fine-tuning the number of NARX hidden nodes and lagged input/target values, and the Bayesian Regularization (BR) backpropagation algorithm to improve the NARX calibration process. A long-term dataset spanning from 1991 to 2021, encompassing 18 rivers across the expansive Vistula River Basin, one of Europe's largest river systems, was employed for this study. The performance of the BO-NARX-BR model was compared with that of the widely utilized air2stream model for modeling river water temperature (RWT). The results unequivocally demonstrated the superior performance of the NARX-based model across the calibration and validation periods, and four heatwave years. In the context of river heatwaves, the study revealed an escalating frequency and intensity within the Vistula River Basin. Furthermore, the NARX-based model exhibited superior proficiency in characterizing river heatwaves compared to the air2stream model. This study, as the inaugural examination of river heatwaves in Poland and one of the few globally, furnishes crucial reference points for subsequent research endeavors on this phenomenon.

Short-term forecasts of streamflow in the UK based on a novel hybrid artificial intelligence algorithm

In recent years, the growing impact of climate change on surface water bodies has made the analysis and forecasting of streamflow rates essential for proper planning and management of water resources. This study proposes a novel ensemble (or hybrid) model, based on the combination of a Deep Learning algorithm, the Nonlinear AutoRegressive network with eXogenous inputs, and two Machine Learning algorithms, Multilayer Perceptron and Random Forest, for the short-term streamflow forecasting, considering precipitation as the only exogenous input and a forecast horizon up to 7 days. A large regional study was performed, considering 18 watercourses throughout the United Kingdom, characterized by different catchment areas and flow regimes. In particular, the predictions obtained with the ensemble Machine Learning-Deep Learning model were compared with the ones achieved with simpler models based on an ensemble of both Machine Learning algorithms and on the only Deep Learning algorithm. The hybrid Machine Learning-Deep Learning model outperformed the simpler models, with values of R² above 0.9 for several watercourses, with the greatest discrepancies for small basins, where high and non-uniform rainfall throughout the year makes the streamflow rate forecasting a challenging task. Furthermore, the hybrid Machine Learning-Deep Learning model has been shown to be less affected by reductions in performance as the forecasting horizon increases compared to the simpler models, leading to reliable predictions even for 7-day forecasts.

Forecasting groundwater level of karst aquifer in a large mining area using partial mutual information and NARX hybrid model

Predicting the groundwater level of karst aquifers in North China Coalfield is essential for early warning of mine water hazards and regional water resources management. However, the dynamic changes of strata structure and hydrogeological parameters driven by coal mining activity cause challenges to the process-oriented groundwater model. In order to achieve accurate prediction of groundwater level in large mining areas, this study was the first to use the data-driven Nonlinear Autoregressive with External Input (NARX) model to predict the groundwater level of six karst aquifer observation wells in Pingshuo Mining Area. Three variable input scenarios were set up, solely considering meteorological factors, anthropogenic disturbance factors, and considering both meteorological and anthropogenic disturbance factors. The novel partial mutual information (PMI) screening algorithm was adopted to determine optimized input variables in each scenario. The input and feedback delay coefficients of NARX model were determined by using Seasonal-trend Decomposition Procedure Based on Loess (STL) algorithm and auto- and cross-correlation functions. The results showed that PMI algorithm can effectively screen out the optimal input variables for predicting groundwater level, the NSE coefficients of the PMI-NARX models under the three scenarios were 38.81%, 4.26% and 41.46% higher than those of the corresponding control experiments, respectively. In addition, the prediction performance of the PMI-NARX built on the basis of meteorological factors is poor (NSE <0.63). However, in scenarios which solely use anthropogenic disturbance factors and both use meteorological and anthropogenic disturbance factors, the PMI-NARX coupling models exhibit good prediction performance (NSE and R² are all greater than 0.8). Especially under solely considering anthropogenic disturbance factors scenario, the model still exhibited good prediction accuracy with a negligible number of input variables. The results can provide technical and theoretical support for the prediction of groundwater level in other mining areas.

A Case Study of Tidal Analysis Using Theory-Based Artificial Intelligence Techniques for Disaster Management in Taehwa River, South Korea

Monitoring tidal dynamics is imperative to disaster management because it requires a high level of precision to avert possible dangers. Good knowledge of the physical drivers of tides is vital to achieving such a precision. The Taehwa River in Ulsan City, Korea experiences tidal currents in the estuary that drains into the East Sea. The contribution of wind to tide prediction is evaluated by comparing tidal predictions using harmonic analysis and three deep learning models. Harmonic analysis is conducted on hourly water level data from 2010–2021 using the commercial pytides toolbox to generate constituents and predict tidal elevations. Three deep learning models of long short-term memory (LSTM), gated recurrent unit (GRU), and bi-directional lstm (BiLSTM) are fitted to the water level and wind speed to evaluate wind and no-wind scenarios. Results show that Taehwa tides are categorized as semidiurnal tides based on a computed form ratio of 0.2714 in a 24-h tidal cycle. The highest tidal range of 0.60 m is recorded on full moon spring tide indicating the significant lunar pull. Wind effect improved tidal prediction NSE of optimal LSTM model from 0.67 to 0.90. Knowledge of contributing effect of wind will inform flood protection measures to enhance disaster preparedness.

A nonlinear autoregressive exogenous (NARX) model to predict nitrate concentration in rivers

Forecasting nitrate concentration in rivers is essential for environmental protection and careful treatment of drinking water. This study shows that nonlinear autoregressive with exogenous inputs neural networks can provide accurate models to predict nitrate plus nitrite concentrations in waterways. The Susquehanna River and the Raccoon River, USA, were chosen as case studies. Water discharge, water temperature, dissolved oxygen, and specific conductance were considered exogenous inputs. The forecasting sensitivity to changes in the exogenous input parameters and time series length was also assessed. For Kreutz Creek at Strickler station (Pennsylvania), the prediction accuracy increased with the number of exogenous input variables, with the best performance achieved considering all the variables (R² = 0.77). The predictions were accurate also for the Raccoon River (Iowa), although only the water discharge was considered exogenous input (South Raccoon River at Redfield-R² = 0.94). Both short- and long-term predictions were satisfactory.

Storm Surge Forecasting along Korea Strait Using Artificial Neural Network

Typhoon attacks on the Korean Peninsula have recently become more frequent, and the strength of these typhoons is also gradually increasing because of climate change. Typhoon attacks cause storm surges in coastal regions; therefore, forecasts that enable advanced preparation for these storm surges are important. Because storm surge forecasts require both accuracy and speed, this study uses an artificial neural network algorithm suitable for nonlinear modeling and rapid computation. A storm surge forecast model was created for five tidal stations on the Korea Strait (southern coast of the Korean Peninsula), and the accuracy of its forecasts was verified. The model consisted of a deep neural network and convolutional neural network that represent the two-dimensional spatial characteristics. Data from the Global Forecast System numerical weather model were used as input to represent the spatial characteristics. The verification of the forecast accuracy revealed an absolute relative error of ≤5% for the five tidal stations. Therefore, it appears that the proposed method can be used for forecasts for other locations in the Korea Strait. Furthermore, because accurate forecasts can be computed quickly, the method is expected to provide rapid information for use in the field to support advance preparation for storm surges.

Precipitation Forecasting in Northern Bangladesh Using a Hybrid Machine Learning Model

Precipitation forecasting is essential for the assessment of several hydrological processes. This study shows that based on a machine learning approach, reliable models for precipitation prediction can be developed. The tropical monsoon-climate northern region of Bangladesh, including the Rangpur and Sylhet division, was chosen as the case study. Two machine learning algorithms were used: M5P and support vector regression. Moreover, a novel hybrid model based on the two algorithms was developed. The performance of prediction models was assessed by means of evaluation metrics and graphical representations. A sensitivity analysis was also carried out to assess the prediction accuracy as the number of exogenous inputs reduces and lag times increases. Overall, the hybrid model M5P-SVR led to the best predictions among used models in this study, with R2 values up to 0.87 and 0.92 for the stations of Rangpur and Sylhet, respectively.

Development of Deep Learning Models to Improve the Accuracy of Water Levels Time Series Prediction through Multivariate Hydrological Data

Since predicting rapidly fluctuating water levels is very important in water resource engineering, Long Short-Term Memory (LSTM) and Gated Recurrent Unit (GRU) were used to evaluate water-level-prediction accuracy at Hangang Bridge Station in Han River, South Korea, where seasonal fluctuations were large and rapidly changing water levels were observed. The hydrological data input to each model were collected from the Water Resources Management Information System (WAMIS) at the Hangang Bridge Station, and the meteorological data were provided by the Seoul Observatory of the Meteorological Administration. For high-accuracy high-water-level prediction, the correlation between water level and collected hydrological and meteorological data was analyzed and input into the models to determine the priority of the data to be trained. Multivariate input data were created by combining daily flow rate (DFR), daily vapor pressure (DVP), daily dew-point temperature (DDPT), and 1-hour-max precipitation (1HP) data, which are highly correlated with the water level. It was possible to predict improved high water levels through the training of multivariate input data of LSTM and GRU. In the prediction of water-level data with rapid temporal fluctuations in the Hangang Bridge Station, the accuracy of GRU’s predicted water-level data was much better in most multivariate training than that of LSTM. When multivariate training data with a large correlation with the water level were used by the GRU, the prediction results with higher accuracy (R2=0.7480–0.8318; NSE=0.7524–0.7965; MRPE=0.0807–0.0895) were obtained than those of water-level prediction results by univariate training.

Prediction of spring flows using nonlinear autoregressive exogenous (NARX) neural network models

In the Mediterranean area, climate changes have led to long and frequent droughts with a drop in groundwater resources. An accurate prediction of the spring discharge is an essential task for the proper management of the groundwater resources and for the sustainable development of large areas of the Mediterranean basin. This study shows an unprecedented application of non-linear AutoRegressive with eXogenous inputs (NARX) neural networks to the prediction of spring flows. In particular, discharge prediction models were developed for 9 monitored springs located in the Umbria region, along the carbonate ridge of the Umbria-Marche Apennines. In the modeling, the precipitation was also considered as an exogenous input parameter. Good performances were achieved for all the springs and for both short-term and long-term predictions, passing from a lag time equal to 1 month (R² = 0.9012-0.9842, RAE = 0.0933-0.2557) to 12 months (R² = 0.9005-0.9838, RAE = 0.0963-0.2409). The forecasting sensitivity to changes in the temporal resolution, passing from weekly to monthly, was also assessed. The good results achieved recommend the use of the NARX network for spring discharge prediction in other areas characterized by karst aquifers.

Tide Prediction in the Venice Lagoon Using Nonlinear Autoregressive Exogenous (NARX) Neural Network

In the Venice Lagoon some of the highest tides in the Mediterranean occur, which have influenced the evolution of the city of Venice and the surrounding lagoon for centuries. The forecast of “high waters” in the lagoon has always been a matter of considerable practical interest. In this study, tide prediction models were developed for the entire lagoon based on Nonlinear Autoregressive Exogenous (NARX) neural networks. The NARX-based model development was performed in two different stages. The first stage was the training and testing of the NARX network, performed on data collected in a given time interval at the tide gauge of Punta della Salute, at the end of Canal Grande. The second stage consisted of a comprehensive validation of the model in the entire Venice Lagoon, with a detailed analysis of data from three measuring stations located in points of the lagoon with different characteristics. Good predictions were achieved regardless of whether the meteorological parameters were considered among input parameters, even with considerable time advance. Furthermore, the forecasting model based on NARX has proved capable of predicting even exceptional high tides. The proposed model could be a useful support tool for the management of the MOSE system, which will protect Venice from high waters.