Snowmelt-Driven Streamflow Prediction Using Machine Learning Techniques (LSTM, NARX, GPR, and SVR)

Thapa, Samit; Zhao, Zebin; Li, Bo; Lu, Lu; Fu, Donglei; Shi, Xiaofei; Tang, Bo; Qi, Hong

doi:10.3390/w12061734

Cited by 53 publications

(27 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Several kinds of machine learning model that can be used to attain a precise estimation on the short-term runoff have been shown in several pieces of research. For example, the support vector machine [16][17][18] and the random forest regressor [19,20]. As a subset of machine learning, deep learning, which is mainly represented by the artificial neural network (ANN) techniques, is of great interest nowadays due to the booming computer science and algorithms [21].…”

Section: Introductionmentioning

confidence: 99%

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

Wang

Liu

Yue

et al. 2020

Water

View full text Add to dashboard Cite

A gated recurrent unit (GRU) network, which is a kind of artificial neural network (ANN), has been increasingly applied to runoff forecasting. However, knowledge about the impact of different input data filtering strategies and the implications of different architectures on the GRU runoff forecasting model’s performance is still insufficient. This study has selected the daily rainfall and runoff data from 2007 to 2014 in the Wei River basin in Shaanxi, China, and assessed six different scenarios to explore the patterns of that impact. In the scenarios, four manually-selected rainfall or runoff data combinations and principal component analysis (PCA) denoised input have been considered along with single directional and bi-directional GRU network architectures. The performance has been evaluated from the aspect of robustness to 48 various hypermeter combinations, also, optimized accuracy in one-day-ahead (T + 1) and two-day-ahead (T + 2) forecasting for the overall forecasting process and the flood peak forecasts. The results suggest that the rainfall data can enhance the robustness of the model, especially in T + 2 forecasting. Additionally, it slightly introduces noise and affects the optimized prediction accuracy in T + 1 forecasting, but significantly improves the accuracy in T + 2 forecasting. Though with relevance (R = 0.409~0.763, Grey correlation grade >0.99), the runoff data at the adjacent tributary has an adverse effect on the robustness, but can enhance the accuracy of the flood peak forecasts with a short lead time. The models with PCA denoised input has an equivalent, even better performance on the robustness and accuracy compared with the models with the well manually filtered data; though slightly reduces the time-step robustness, the bi-directional architecture can enhance the prediction accuracy. All the scenarios provide acceptable forecasting results (NSE of 0.927~0.951 for T + 1 forecasting and 0.745~0.836 for T + 2 forecasting) when the hyperparameters have already been optimized. Based on the results, recommendations have been provided for the construction of the GRU runoff forecasting model.

show abstract

Section: Introductionmentioning

confidence: 99%

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

Wang

Liu

Yue

et al. 2020

Water

View full text Add to dashboard Cite

show abstract

“…These features provide LSTM networks with more powerful processing capabilities for abnormal fluctuations and gives them smaller prediction errors than SVR networks. Studies in a number of fields, including stock premium [70], snowmelt driven stream flow [71], and traffic flow prediction [69] have shown the superiority of LSTM networks relative to SVR networks in processing time-series data.…”

Section: Discussionmentioning

confidence: 99%

Real-time liver tracking algorithm based on LSTM and SVR networks for use in surface-guided radiation therapy

Wang

et al. 2021

Radiat Oncol

View full text Add to dashboard Cite

Background Surface-guided radiation therapy can be used to continuously monitor a patient’s surface motions during radiotherapy by a non-irradiating, noninvasive optical surface imaging technique. In this study, machine learning methods were applied to predict external respiratory motion signals and predict internal liver motion in this therapeutic context. Methods Seven groups of interrelated external/internal respiratory liver motion samples lasting from 5 to 6 min collected simultaneously were used as a dataset, Dv. Long short-term memory (LSTM) and support vector regression (SVR) networks were then used to establish external respiratory signal prediction models (LSTMpred/SVRpred) and external/internal respiratory motion correlation models (LSTMcorr/SVRcorr). These external prediction and external/internal correlation models were then combined into an integrated model. Finally, the LSTMcorr model was used to perform five groups of model updating experiments to confirm the necessity of continuously updating the external/internal correlation model. The root-mean-square error (RMSE), mean absolute error (MAE), and maximum absolute error (MAX_AE) were used to evaluate the performance of each model. Results The models established using the LSTM neural network performed better than those established using the SVR network in the tasks of predicting external respiratory signals for latency-compensation (RMSE < 0.5 mm at a latency of 450 ms) and predicting internal liver motion using external signals (RMSE < 0.6 mm). The prediction errors of the integrated model (RMSE ≤ 1.0 mm) were slightly higher than those of the external prediction and external/internal correlation models. The RMSE/MAE of the fifth model update was approximately ten times smaller than that of the first model update. Conclusions The LSTM networks outperform SVR networks at predicting external respiratory signals and internal liver motion because of LSTM’s strong ability to deal with time-dependencies. The LSTM-based integrated model performs well at predicting liver motion from external respiratory signals with system latencies of up to 450 ms. It is necessary to update the external/internal correlation model continuously.

show abstract

“…It is a kernel based probabilistic model and can be viewed as a Bayesian version of SVM models. The GP regression models are robust against the model overfitting problem (Thapa et al ., 2020). The model can be summarized as follows.…”

Section: Methodsmentioning

confidence: 99%

Regional frequency analysis of annual daily rainfall maxima in Skåne, Sweden

Hassan

Noreen

Ahmed

2021

Intl Journal of Climatology

View full text Add to dashboard Cite

Extreme daily rainfall events are critical for the urban drainage system, human life, agriculture and small catchments. The information about extreme rainfall magnitudes and frequencies is immensely important for civil engineers, city planners, scientists related to water management, rescue operations and flood control works. This study illustrates the results of regional frequency analysis (RFA) of annual maximum daily rainfall (AMDR) of Skåne County, Sweden. L-moments based heterogeneity measure (H) reveals that the Skåne County is a homogeneous region. Based on the L-moment ratio diagram and Z Dist statistic results, the generalized normal (GNO) distribution is selected as the most suitable regional distribution. The accuracy measures used in K-fold cross validation indicate that support vector machine (SVM) model is an appropriate model to find the index rainfall at ungauged sites in the region. The sites characteristics, elevation and latitude are identified as the most important variables to explain the variation in mean annual maximum daily rainfall (MAMDR). Finally, spatial maps of predicted MAMDR for different return periods are constructed by using index rainfall combined with regional quantiles. Spatial maps offer an overall view of the expected MAMDR in the region that is helpful for multiple decision makers including infrastructure planners, city planners, emergency managers, engineers and many others. K E Y W O R D S K-fold cross validation, L-moments, Monte Carlo simulation, quantile estimates, regional frequency analysis, spatial map 1 | INTRODUCTION Daily extreme rainfall is one of the utmost environmental events which cause sizeable damages throughout the world. The rainfall recorded in the last century was the highest over the past 8,500 years (Hong et al., 2014). A reliable estimate of extreme rainfall magnitude is important for flood management, irrigation, rescue operations, water management, construction of urban drainage systems and many other purposes. Skåne is the tenth largest county of Sweden. It has the best agricultural land and is known as a breadbasket of Sweden. It stands for about half of Sweden's food production (Skåne Region, 2014). Rainfall is an important factor for agriculture in Skåne. Skåne agriculture and food industries are highly dependent on this hydrological

show abstract

Snowmelt-Driven Streamflow Prediction Using Machine Learning Techniques (LSTM, NARX, GPR, and SVR)

Cited by 53 publications

References 45 publications

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

Impact of Input Filtering and Architecture Selection Strategies on GRU Runoff Forecasting: A Case Study in the Wei River Basin, Shaanxi, China

Real-time liver tracking algorithm based on LSTM and SVR networks for use in surface-guided radiation therapy

Regional frequency analysis of annual daily rainfall maxima in Skåne, Sweden

Contact Info

Product

Resources

About