Water Level Prediction Model Research Articles

Real-Time and Intelligent Flood Forecasting Using UAV-Assisted Wireless Sensor Network

The Wireless Sensor Network (WSN) is a promising technology that could be used to monitor rivers’ water levels for early warning flood detection in the 5G context. However, during a flood, sensor nodes may be washed up or become faulty, which seriously affects network connectivity. To address this issue, Unmanned Aerial Vehicles (UAVs) could be integrated with WSN as routers or data mules to provide reliable data collection and flood prediction. In light of this, we propose a fault-tolerant multi-level framework comprised of a WSN and a UAV to monitor river levels. The framework is capable to provide seamless data collection by handling the disconnections caused by the failed nodes during a flood. Besides, an algorithm hybridized with Group Method Data Handling (GMDH) and Particle Swarm Optimization (PSO) is proposed to predict forthcoming floods in an intelligent collaborative environment. The proposed water-level prediction model is trained based on the real dataset obtained from the Selangor River in Malaysia. The performance of the work in comparison with other models has been also evaluated and numerical results based on different metrics such as coefficient of determination (), correlation coefficient (), Root Mean Square Error (), Mean Absolute Percentage Error (), and are provided.

Evaluation of Real-Time Water Level Prediction Technology Using Statistical Models for Reducing Urban Flood Risk

The frequency of localized short-term torrential rains that exceed the planned rainfall is increasing along with inundation damage due to inland flooding. Stepwise inundation measures utilizing existing stock and disaster prevention/mitigation for excessive rainfall are required. In this study, we describe the results of empirical research using a statistical model constructed based on rainfall and water level observation data as a highly accurate water level prediction method suitable for real-time prediction. This is aimed at application in flood control activities and operation support of pump facilities. By comparing and verifying the prediction accuracy between the water level prediction model and the statistical model by Convolutional Neural Network (CNN), which is generally used as an image recognition technology, the usefulness of the statistical model was confirmed. Further improvement in accuracy and widespread use of these water level prediction models are expected.

MODEL PREDIKSI LEVEL AIR DI LAHAN PERKEBUNAN KELAPA SAWIT DENGAN JARINGAN SARAF TIRUAN BERDASARKAN PENGUKURAN SENSOR RAIN GAUGE DAN ULTRASONIK

Monitoring and regulating water levels in oil palm swamps has an essential role in providing sufficient water for crops and conserving the land to not easily or quickly deteriorate. Presently, water level is still manual and has weaknesses, one of which is the accuracy of the data taken depending on the observer. Technology such as sensors integrated with artificial neural network is expected to observe and regulate water levels. This study aims to build a prediction model of water levels in oil palm plantations with artificial neural networks based on the rain gauge and ultrasonic sensors installed on Automatic Weather Station (AWS). The obtained results showed that the prediction model runs well with an R2 value of 0,994 and RMSE 1,16 cm. The water level prediction model in this research then tested for accuracy to prove the model's success rate. Testing the water level prediction model's accuracy in the dry season obtained an R2 value of 0,96 and an RMSE of 1,99 cm. Testing the water level prediction model's accuracy in the rainy season obtained an R2 value of 0,85 and an RMSE value of 4,2 cm. Keywords : artificial neural network, automatic weather station, palm oil, water level

Research on stage-divided water level prediction technology of rivers-connected lake based on machine learning: a case study of Hongze Lake, China

The rivers-connected lake involved in the “River–Lake-Reservoir” hydrological complex system and it's water level fluctuations are more severe than those of other lakes, which challenges the scientific management of lakes. Therefore, to improve the accuracy of water level prediction for the rivers-connected lake, taking Hongze Lake as an example, we used the BFAST algorithm to analyze the inconsistency of the lake's inter-annual water level and selected a stable stage for water level prediction research. Next, considering the lake basin shape, based on the Stage-discharge relationship curve, the fluctuation process of the lake's inter-annual water level was divided into four periods: the discharge period, the early period of storage, the later period of storage, and the balance period. Then, the NARX model was used to build the water level prediction model for different periods. Finally, the wavelet analysis and KNN algorithm were introduced into the water level prediction model for input data pre-process and result post-processing, respectively. The result shows that: (1) There are significant differences in the mechanism of water level regime modification in different periods. The outflowing runoff is the main driving factor for the water level regime modification in most times; (2) Coupling multiple machine learning methods is an effective way to improve the accuracy of the lake water level prediction; (3) The combination of the staged-divided water level prediction method and the hybrid machine learning models can further improve the accuracy of the water level prediction.

The prediction of water level based on support vector machine under construction condition of steel sheet pile cofferdam

SummaryAlthough the construction of steel sheet pile cofferdam has good practicability in the process of water conservancy project construction, the construction period of the water project is long due to the large amount of work, and the cofferdam itself is greatly affected by the water level, topography, geological period, and other factors. With the continuation of time and the change of complex hydrogeological environment, it is easy to cause the accumulation of hidden safety hazards in the construction of the project during the construction period, and the unreasonable and untimely risk warning and control have led to some major construction accidents. In this paper, the SVM (Support Vector Machine) medium‐ and short‐term water level prediction model is established. The SVM tool is used to establish a prediction model that takes complex hydrological scenes and weather changes into account comprehensively, so that the medium‐ and short‐term water level can be predicted more accurately, thus achieving dynamic adjustment and better adapting to the actual requirements of steel sheet pile cofferdam construction. The results show that there is a good co‐integration relationship between the prediction factors selected by the medium‐ and short‐term water level prediction model, which proves the rationality of the multivariable predictions selected in this paper. At the same time, in the precipitation concentration period, the relative error of the SVM prediction model is relatively small, and it can achieve dynamic water level prediction with the update of the medium‐ and short‐term weather forecast, which can meet the requirements of engineering construction and accuracy.

Real-time water level prediction of cascaded channels based on multilayer perception and recurrent neural network

Water level prediction is crucial to water diversion through cascaded channels, and the prediction accuracies are still unsatisfying due to the difficulties and challenges caused by complex interactions and relations among cascaded channels. We adopt two kinds of neural networks to build our water level prediction models for cascaded channels 2/4/6 h ahead with high prediction accuracy. First, the raw hydrological data of cascaded channels are augmented using spatial and temporal windows, which produces data sets with high-dimensional features. Then, Multilayer Perceptron (MLP) and Recurrent Neural Network (RNN) are adopted to build the water level prediction model with the help of the augmented data containing the implicit correlation among multiple channels in spatial dimension and multiple data records in temporal dimension. China’s South-to-North Water Diversion Project is taken as the case study. Experimental results show that our models outperform Support Vector Machine (SVM) by 34.78%, 44.53%, 1.32% and 9.198% in terms of Root Mean Square Error (RMSE), Mean Absolute Error (MAE), Pearson Correlation Coefficient (PCC) and Nash’ Sutcliffe Efficiency(NSE), respectively. The accuracies of our models with prediction deviations less than 1 cm, 2 cm, and 3 cm can reach as high as 81.36%, 94.09%, and 97.05%, respectively.

Water level prediction of Lake Poyang based on long short-term memory neural network

湖泊水位是维持其生态系统结构、功能和完整性的基础.鄱阳湖受流域五河和长江来水双重影响，水位变化复杂.为了准确预测鄱阳湖水位变化，采用长短时记忆神经网络方法（LSTM）构建了鄱阳湖水位预测模型.该模型以赣江、抚河、信江、饶河和修水五河入湖流量和长江干流流量作为输入条件，预测鄱阳湖湖区不同代表站（湖口、星子、都昌、吴城和康山）的水位过程.研究以1956-1980年的水文时间序列数据作为训练集，1981-2000年作为验证集，探讨了LSTM模型输入时间窗、隐藏神经元数目、初始学习率等模型参数对预测精度的影响，并确定了鄱阳湖水位预测模型的最优参数.结果表明，采用LSTM神经网络方法可基于流域五河和长江来水量历时数据合理预测鄱阳湖不同湖区的水位过程，五站水位预测的均方根误差为0.41~0.50 m，纳什效率系数和决定系数达0.96~0.98.为考察模型训练数据集对鄱阳湖水位预测结果的影响，进一步选取了随机5年（1956-1960年）的资料和5个典型水文年（1954年、1973年、1974年、1977年和1978年）的日均流量资料来训练模型.结果显示随机5年资料作为训练数据的预测精度要差于典型年水文资料训练得到的模型，尤其是洪、枯水位的预测；由于典型水文年数据量仍远低于20年的资料，故其总体预测精度要略低于采用20年资料训练的模型.建议应用这类基于数据驱动的模型时，应该尽可能多选取具有代表性的资料来训练.;Lake water level is the basis for maintaining the structure, function, and integrity of its ecosystem. The water level change of Lake Poyang is complicated as it was affected by five rivers within the basin and the Yangtze River. To accurately predict the water level change of Lake Poyang, the long short-term memory (LSTM) is used to construct the water level prediction model of Lake Poyang. The model uses the flows of the Ganjiang River, Fuhe River, Xinjiang River, Raohe River, Xiushui River and the mainstream of the Yangtze River as input conditions to predict the water level process of different representative stations in the Lake Poyang area (Hukou, Xingzi, Duchang, Wucheng and Kangshan). The hydrological time series data from 1956 to 1980 is used as the training set, and data from 1981 to 2000 was used as the verification set. The influence of model parameters such as input time window, hidden neuron nodes and initial learning rate on prediction accuracy is discussed. The optimal parameters of the Lake Poyang water level prediction model are determined. The results show that the LSTM can accurately predict the water level at different parts of Lake Poyang based on the water flow from the five rivers and the Yangtze River. The RMSE value of the five stations is 0.41-0.50 m, and the NSE and R² are 0.96-0.98. In order to investigate the impact of the model training set on the water level prediction results of Lake Poyang, the study further selects data from 5 random years (1956-1960) and 5 typical hydrological years (1954, 1973, 1974, 1977 and 1978) daily average flow data to train the model. The results show that the prediction accuracy of random 5 years data as training set is worse than that of typical annual hydrological data training, especially the prediction of flood and dry water level; since the typical hydrological data volume is still much lower than 20 years of data, the overall prediction accuracy is slightly lower than the model with 20 years of data training. Therefore, representative data should be selected as much as possible for training, when applying such a data-driven LSTM neural network model.

Water Level Prediction Model Based on GRU and CNN

Massive amount of water level data has been collected by using Internet of Things (IoT) techniques in the Yangtze River and other rivers. In this paper, utilizing these data to construct deep neural network models for water level prediction is focused. To achieve higher accuracy, both the factors of time and locations of data collection sensors are considered to perform prediction. And the network structures of gated recurrent unit (GRU) and convolutional neural network (CNN) are combined to build a CNN-GRU model in which the GRU part learns the changing trend of water level, and the CNN part learns the spatial correlation among water level data observed from adjacent water stations. The CNN-GRU model that using data from multiple locations to predict the water level of the middle location has higher accuracy than the model only based on GRU and other state-of-the-art methods including autoregressive integrated moving average model (ARIMA), wavelet-based artificial neural network (WANN) and long-short term memory model (LSTM), because of its ability to decrease the affections of abnormal value and data randomness of a single water station to some extent. The results are verified on an experiment dataset that including 30-year observed data of water level at several collection stations in the Yangtze River. For forecasting the 8-o'clock water levels of future 5 days, accuracy of the CNN-GRU model is better than that of ARIMA, WANN and LSTM models with three evaluation factors including Nash-Sutcliffe efficiency coefficient (NSE), average relative error (MRE) and root mean square error (RMSE).

Development of Water Level Prediction Models Using Machine Learning in Wetlands: A Case Study of Upo Wetland in South Korea

Wetlands play a vital role in hydrologic and ecologic communities. Since there are few studies conducted for wetland water level prediction due to the unavailability of data, this study developed a water level prediction model using various machine learning models such as artificial neural network (ANN), decision tree (DT), random forest (RF), and support vector machine (SVM). The Upo wetland, which is the largest inland wetland in South Korea, was selected as the study area. The daily water level gauge data from 2009 to 2015 were used as dependent variables, while the meteorological data and upstream water level gauge data were used as independent variables. Predictive performance evaluation using RF as the final model revealed 0.96 value for correlation coefficient (CC), 0.92 for Nash–Sutcliffe efficiency (NSE), 0.09 for root mean square error (RMSE), and 0.19 for persistence index (PI). The results indicate that the water level of the Upo wetland was well predicted, showing superior results compared to that of the ANN, which was used in a previous study. The results intend to provide basic data for development of a wetland management method, using water levels of previously ungauged areas.

Development of a Practical River Water Level Prediction Method Using Data Assimilation Technique

With the aim of accurately predicting river water levels a few hours ahead in the event of a flood, we created a river water level prediction model consisting of a runoff model, a channel model, and data assimilation technique. We also developed a cascade assimilation method that allows us to calculate assimilations of water levels observed at multiple points using particle filters in real-time. As a result of applying the river water level prediction model to Arakawa Basin using the assimilation technique, it was confirmed that reproductive simulations that produce results very similar to the observed results could be achieved, and that we would be able to predict river water levels less affected by the predicted amount of rainfall.

A novel flood defense decision support system for smart urban management based on classification and regression tree

With the development of the internet of things technology and awareness technology, all kinds of big data in the city have started to emerge. Under the background in internet plus era, using big data to effectively forecast urban flood disaster, formulating the flood control and disaster mitigation countermeasures in time, is an important subject of urban flood control and research. In this paper, a novel flood defense decision support system (NFDDSS) is proposed. Using historical hydrology data in Hangzhou, this paper proposed a comprehensive consideration of time correlation and spatial correlation of water level prediction model based on classification and regression tree. This model can predict the water level in one to six hours effectively. With this system, supervisors can get timely and effective guidance of flood control and disaster mitigation when the flood season comes.

Fuzzy logic based flood forecasting model for the Kelantan River basin, Malaysia

Among other flood forecasting tools, fuzzy logic is one of a simple and flexible approach which can be implemented in river basins where adequate hydrologic data is available and not good enough to use in a more sophisticated model. This paper assesses the potential of fuzzy logic approach for real time flood forecasting using the minimum implication function type Mamdani fuzzy inference system by applying the model to the Kelantan River basin in Malaysia. The developed models were tested for forecasting the downstream water levels of Guilemard and Kuala Krai stations using upstream hourly telemetric water levels of Dabong and Tualang stations. The membership functions (MFs) of triangular shapes with several fuzzy rule sets were utilized to check the efficiency of the fuzzy logic approach for the Kelantan River flood forecasting. For the Guilemard station, models of 8, 10 and 15 rules' sets were tested. In the calibration and validation events, the Guilemard station models' achieved MAE, ranges 0.35–0.45 m, N–S coefficient, ranges 0.87 – 0.89 and Coefficient of Determination ranges, R2 ranges 0.91–0.95. The water level prediction model developed for the Kuala Krai station consisted of 19 rules with triangular shape MFs. It shows the ranges for MAE: 0.26–0.76 m, N–S coefficient: 0.78–0.93 and R2: 0.91–0.96 in calibration and validation periods. The efficiencies of the developed models show acceptable levels according to the tested performance indicators implying the potential of establishing a flood forecasting system by using the fuzzy logic approach in the Kelantan River basin, Malaysia.

Research of the Underground Water Level Prediction Model in Deep Foundation Pit Engineering

The effect such as ion exchange, precipitation, corrosion and consolidation can occur between groundwater and rock mass, it will cause a variety of adverse effects on deep foundation pit engineering. Prediction of the underground water level and take corresponding precipitation control measures is very important. Underground water level deformation is a complicated ,nonlinear and stochastic problem, it is unable to establish accurate mathematical model. An underground water level deformation prediction model based on BP neural network was constructed in this paper. Five closely related factors in underground water level deformation are river flow, temperature, saturation deficit, rainfall and evaporation, they were selected as input vector of BP neural network, underground water level measured value as a model target output. In Matlab 2011b simulation software, 24 groups observation data for underground water level and five closely related factors of a underground parking lot deep foundation pit engineering in Jilin as the sample set,19 groups were randomly selected as the training sample set , other 5 groups were used as the testing sample set .The simulation result shows that testing value is very close to the true value in this method and the average relative error was 2.9708%.The method in this paper can achieve higher accuracy of groundwater level prediction in deep foundation pit engineering.

하천 수위예보를 위한 신경망-유전자알고리즘 결합모형의 실무적 적용성 검토

As a national river remediation project has been completed, this study has a special interest on the capabilities to predict water levels at various points of the Geum River. To be endowed with intelligent forecasting capabilities, the author formulate the neuro-genetic algorithm associated with the short-term water level prediction model. The results show that neuro-genetic algorithm has considerable potentials to be practically used for water level forecasting, revealing that (1) model optimization can be obtained easily and systematically, and (2) validity in predicting one- or two-day ahead water levels can be fully proved at various points.