Application of Long Short-Term Memory (LSTM) Neural Network for Flood Forecasting

Abstract

Flood forecasting is an essential requirement in integrated water resource management. This paper suggests a Long Short-Term Memory (LSTM) neural network model for flood forecasting, where the daily discharge and rainfall were used as input data. Moreover, characteristics of the data sets which may influence the model performance were also of interest. As a result, the Da River basin in Vietnam was chosen and two different combinations of input data sets from before 1985 (when the Hoa Binh dam was built) were used for one-day, two-day, and three-day flowrate forecasting ahead at Hoa Binh Station. The predictive ability of the model is quite impressive: The Nash–Sutcliffe efficiency (NSE) reached 99%, 95%, and 87% corresponding to three forecasting cases, respectively. The findings of this study suggest a viable option for flood forecasting on the Da River in Vietnam, where the river basin stretches between many countries and downstream flows (Vietnam) may fluctuate suddenly due to flood discharge from upstream hydroelectric reservoirs.

Energy Flexibility Prediction for Data Center Engagement in Demand Response Programs

“…The number of inputs, outputs, hidden layer and neuron types is presented in Table 2. We have considered two types of individual neural network models (i.e., differentiated by the neuron types) as mathematical functions used for regression, aiming to forecast energy values over a future time window: (i) MLP that uses rectified linear units (ReLU) [53] and (ii) LSTM [54]. The MLP has proven its suitability for regression problems because it can be seen as a logistic regressor that is fed through an intermediate layer called "hidden layer" activated by a non-linear function.…”

Realistic River Image Synthesis using Deep Generative Adversarial Networks

“…Again LSTM networks are used to classify flood related tweets from unrelated ones during Hurricane Irma [27]. In other cases, feedforward deep neural networks have been used to improve the robustness of standard weather prediction methods; for example, by inputting infrared satellite imagery, microwave scans, and images from hundreds of satellites orbiting the Earth, scientists can train neural networks to predict the levels of snow over time [28] in areas more prone to map distortion, like at more extreme latitudes present in the North and South poles. Rather than just using one specific variable, like scans from a singular satellite or at a specific wavelength, deep learning enables scientists to consolidate numerous variables and use supervised neural networks and clustering algorithms (K-means) [29] to find novel trends.…”

Levenberg-Marquardt Training Function using on MLP, RNN and Elman Neural Network to Optimize Hourly Forecasting in Tetouan City (Northern Morocco)

“…ENN are generally used to study dynamic systems such as wind. There are many other networks similar to ENN such as the Jordan Neural Network, although there are other types of recurring neural networks such as LSTM (Long Short-Term Memory) [21] and GRU (Gated Recurrent Unit). The Elman network model can expressed as: The expression of output layer at t time is written:…”