A Method of Multi-Stage Reservoir Water Level Forecasting Systems: A Case Study of Techi Hydropower in Taiwan

Tsao, Hao Han; Leu, Yih Guang; Chou, Li Fen; Tsao, Chao Yang

doi:10.3390/en14123461

Cited by 4 publications

(1 citation statement)

References 32 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The most commonly used features in the literature are precipitation (17%), LWL, and evaporation [20]. Other major features used by researchers include discharge [38], temperature [39], inflow [40], streamflow and humidity [41], wind speed and solar radiation [42], and volume and area [43].…”

Section: Dataset Descriptionmentioning

confidence: 99%

Prediction of Water Level in Lakes by RNN-Based Deep Learning Algorithms to Preserve Sustainability in Changing Climate and Relationship to Microcystin

Ozdemir,

Ozkan Yildirim

2023

Sustainability

View full text Add to dashboard Cite

In recent years, intensive water use combined with global climate change has increased fluctuations in freshwater lake levels, hydrological characteristics, water quality, and water ecosystem balance. To provide a sustainable management plan in the long term, deep learning models (DL) can provide fast and reliable predictions of lake water levels (LWLs) in challenging future scenarios. In this study, artificial neural networks (ANNs) and four recurrent neural network (RNN) algorithms were investigated to predict LWLs that were applied in time series such as one day, five days, ten days, twenty days, one month, two months, and four months ahead. The results show that the performance of the Long Short-Term Memory (LSTM) model with a prediction of 60 days is in the very good range and outperforms the benchmark, the Naïve Method, by 78% and the ANN at the significance level (p < 0.05) with an RMSE = 0.1762 compared to other DL algorithms. The RNN-based DL algorithms show better prediction performance, specifically, for long time horizons, 57.98% for 45 days, 78.55% for 60 days, and 58% for 120 days, and it is better to use a prediction period of at least 20 days with an 18.45% performance increase to take advantage of the gated RNN algorithms for predicting future water levels. Additionally, microcystin concentration was tightly correlated with temperature and was most elevated between 15 and 20 m water depths during the summer months. Evidence on LWL forecasting and microcystin concentrations in the context of climate change could help develop a sustainable water management plan and long-term policy for drinking water lakes.

show abstract

Section: Dataset Descriptionmentioning

confidence: 99%

Prediction of Water Level in Lakes by RNN-Based Deep Learning Algorithms to Preserve Sustainability in Changing Climate and Relationship to Microcystin

Ozdemir,

Ozkan Yildirim

2023

Sustainability

View full text Add to dashboard Cite

show abstract

A systematic literature review on lake water level prediction models

Özdemir

Yaqub

Yıldırım

2023

Environmental Modelling & Software

View full text Add to dashboard Cite

WSI: A New Early Warning Water Survival Index for the Domestic Water Demand

Shih

Liao

et al. 2022

Mathematics

View full text Add to dashboard Cite

A reservoir is an integrated water resource management infrastructure that can be used for water storage, flood control, power generation, and recreational activities. Predicting reservoir levels is critical for water supply management and can influence operations and intervention strategies. Currently, the water supply monitoring index is used to warn the water level of most reservoirs. However, there is no precise calculation method for the current water supply monitoring index to warn about the adequacy of the domestic water demand. Therefore, taking Feitsui Reservoir as an example, this study proposes a new early warning water survival index (WSI) to warn users whether there is a shortage of domestic water demand in the future. The calculation of WSI was divided into two stages. In the first stage, the daily rainfall, daily inflow, daily outflow, and daily water level of the Feitsui Reservoir were used as input variables to predict the water level of the Feitsui Reservoir by the machine learning method. In the second stage, the interpolation method was used to calculate the daily domestic water demand in Greater Taipei. Combined with the water level prediction results of the Feitsui Reservoir in the first stage, the remaining estimated days of domestic water supply from the Feitsui Reservoir to Greater Taipei City were calculated. Then, the difference between the estimated remaining days of domestic water demand and the moving average was converted by the bias ratio to obtain a new WSI. WSI can be divided into short-term bias ratios and long-term bias ratios. In this study, the degree of the bias ratio of WSI was given in three colors, namely, condition blue, condition green, and condition red, to provide users with a warning of the shortage of domestic water in the future. The research results showed that compared with the existing water supply monitoring index, the new WSI proposed in this study can faithfully present the warning of the lack of domestic water demand in the future.

show abstract

A Method of Multi-Stage Reservoir Water Level Forecasting Systems: A Case Study of Techi Hydropower in Taiwan

Cited by 4 publications

References 32 publications

Prediction of Water Level in Lakes by RNN-Based Deep Learning Algorithms to Preserve Sustainability in Changing Climate and Relationship to Microcystin

Prediction of Water Level in Lakes by RNN-Based Deep Learning Algorithms to Preserve Sustainability in Changing Climate and Relationship to Microcystin

A systematic literature review on lake water level prediction models

WSI: A New Early Warning Water Survival Index for the Domestic Water Demand

Contact Info

Product

Resources

About