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

2019 ◽  
Vol 14 (2) ◽  
pp. 260-268 ◽  
Author(s):  
Shuichi Tsuchiya ◽  
◽  
Masaki Kawasaki
Keyword(s):  
Data Assimilation ◽  
Prediction Model ◽  
Water Level ◽  
River Water ◽  
Channel Model ◽  
Prediction Method ◽  
Water Levels ◽  
Using Data ◽  
Data Assimilation Technique ◽  
Water Level Prediction

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.

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

2021 ◽  
Vol 10 (1) ◽  
pp. 104
Author(s):  
Hasan Al Banna ◽  
Bayu Dwi Apri Nugroho
Keyword(s):  
Neural Network ◽  
Artificial Neural Network ◽  
Prediction Model ◽  
Water Level ◽  
Rain Gauge ◽  
Water Levels ◽  
Weather Station ◽  
Automatic Weather Station ◽  
Artificial Neural ◽  
Water Level Prediction

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

EXAMINATION OF SHORT-TERM WATER LEVEL PREDICTION MODEL IN LOW-LYING LAKES USING MACHINE LEARNING

2020 ◽  
Vol 76 (2) ◽  
pp. I_439-I_444
Author(s):  
Masaomi KIMURA ◽  
Takahiro ISHIKAWA ◽  
Naoto OKUMURA ◽  
Issaku AZECHI ◽  
Toshiaki IIDA
Keyword(s):  
Machine Learning ◽  
Prediction Model ◽  
Water Level ◽  
Short Term ◽  
Water Level Prediction

scholarly journals RIVER WATER LEVEL PREDICTION FROM RAINFALL

2010 ◽  
Vol 66 (1) ◽  
pp. 93-98
Author(s):  
Toru HIRAOKA ◽  
Masataka IKARI ◽  
Hiromi YUKI
Keyword(s):  
Water Level ◽  
River Water ◽  
Water Level Prediction

scholarly journals Simultaneous state-parameter estimation of rainfall-induced landslide displacement using data assimilation

2019 ◽  
Author(s):  
Jing Wang ◽  
Guigen Nie ◽  
Shengjun Gao ◽  
Changhu Xue
Keyword(s):  
Parameter Estimation ◽  
Data Assimilation ◽  
Prediction Method ◽  
State Parameter ◽  
Joint Estimation ◽  
Model Parameters ◽  
Displacement Estimation ◽  
Landslide Stability ◽  
Landslide Displacement Prediction ◽  
Using Data

Abstract. Landslide displacement prediction has great practical engineering significance to landslide stability evaluation and early warning. The evolution of landslide is a complex dynamic process, applying classical prediction method will result in significant error. Data assimilation method offers a new way to merge multi-source data with the model. However, data assimilation is still deficient in the ability to meet the demand of dynamic landslide system. In this paper, simultaneous state-parameter estimation (SSPE) using particle filter-based data assimilation is applied to predict displacement of the landslide. Landslide SSPE assimilation strategy can make use of time-series displacements and hydrological information for the joint estimation of landslide displacement and model parameters, which can improve the performance considerably. We select Xishan Village, Sichuan province, China as experiment site to test SSPE assimilation strategy. Based on the comparison of actual monitoring data with prediction values, results strongly suggest the effectiveness and feasibility of SSPE assimilation strategy in short-term landslide displacement estimation.

scholarly journals HURRICANE WATER LEVEL PREDICTION USING SURROGATE MODELING

2018 ◽  
pp. 57
Author(s):  
Jeffrey A. Melby ◽  
Fatima Diop ◽  
Norberto Nadal-Caraballo ◽  
Alex Taflanidis ◽  
Victor Gonzalez
Keyword(s):  
Water Level ◽  
Water Levels ◽  
High Fidelity ◽  
Forward Speed ◽  
Efficient Design ◽  
Total Water ◽  
Training Set ◽  
Kriging Approach ◽  
Total Water Level ◽  
Water Level Prediction

For this study, the surrogate was constructed using kriging (Jia et al. 2015). The high fidelity coupled surge and wave numerical modelling for the Gulf of Mexico was used as the training set. The numerical model was either ADCIRC and STWAVE or ADCIRC and SWAN in the nearshore. The surrogate models were trained using tropical storm parameters (latitude, longitude, central pressure, radius to maximum wind speed, storm heading, and forward speed) at a specific location as inputs and individual responses (e.g. surge) as outputs. Tide was computed separately using ADCIRC and linearly superimposed with surge to get total water level. The regional surrogates accurately reproduced both peaks and time series of water levels for historical storms. An extensive validation was conducted to determine the optimal application of the kriging approach. In this paper we will report the efficient design-of-experiments approach, surrogate training and validation.

scholarly journals Deep Learning Semantic Segmentation for Water Level Estimation Using Surveillance Camera

2021 ◽  
Vol 11 (20) ◽  
pp. 9691
Author(s):  
Nur Atirah Muhadi ◽  
Ahmad Fikri Abdullah ◽  
Siti Khairunniza Bejo ◽  
Muhammad Razif Mahadi ◽  
Ana Mijic
Keyword(s):  
Deep Learning ◽  
Water Level ◽  
River Water ◽  
Correlation Coefficient ◽  
Rank Order ◽  
Measurement Data ◽  
Strong Relationship ◽  
Semantic Segmentation ◽  
Water Levels ◽  
Surveillance Systems

The interest in visual-based surveillance systems, especially in natural disaster applications, such as flood detection and monitoring, has increased due to the blooming of surveillance technology. In this work, semantic segmentation based on convolutional neural networks (CNN) was proposed to identify water regions from the surveillance images. This work presented two well-established deep learning algorithms, DeepLabv3+ and SegNet networks, and evaluated their performances using several evaluation metrics. Overall, both networks attained high accuracy when compared to the measurement data but the DeepLabv3+ network performed better than the SegNet network, achieving over 90% for overall accuracy and IoU metrics, and around 80% for boundary F1 score (BF score), respectively. When predicting new images using both trained networks, the results show that both networks successfully distinguished water regions from the background but the outputs from DeepLabv3+ were more accurate than the results from the SegNet network. Therefore, the DeepLabv3+ network was used for practical application using a set of images captured at five consecutive days in the study area. The segmentation result and water level markers extracted from light detection and ranging (LiDAR) data were overlaid to estimate river water levels and observe the water fluctuation. River water levels were predicted based on the elevation from the predefined markers. The proposed water level framework was evaluated according to Spearman’s rank-order correlation coefficient. The correlation coefficient was 0.91, which indicates a strong relationship between the estimated water level and observed water level. Based on these findings, it can be concluded that the proposed approach has high potential as an alternative monitoring system that offers water region information and water level estimation for flood management and related activities.

scholarly journals Water Level Prediction of Emergency Groundwater Source and Its Impact on the Surrounding Environment in Nantong City, China

Water ◽  
2020 ◽  
Vol 12 (12) ◽  
pp. 3529
Author(s):  
Jinbang Cai ◽  
Ping Wang ◽  
Huan Shen ◽  
Yue Su ◽  
Yong Huang
Keyword(s):  
Water Level ◽  
Small Deviation ◽  
Water Levels ◽  
Initial Water ◽  
Surrounding Environment ◽  
Pumping Wells ◽  
Using Data ◽  
Depression Cone ◽  
Groundwater Source ◽  
Short Time

Based on the geological and hydrogeological conditions, and in situ hydrogeological tests of the emergency groundwater source in Nantong City, China, a 3D numerical model of the heterogeneous anisotropy in the study area was established and calibrated using data from pumping and recovery tests. The calibrated model was used to simulate and predict the water level of the depression cone during the emergency pumping and water level recovery. The results showed that after seven days of pumping, the water level in the center of the depression cone ranged from −51 m to −55 m, and compared with the initial water level, the water level dropped by 29 m to 32 m. The calculated water level has a small deviation compared with that of the analytical solution, which indicates the reliability and rationality of the numerical solution. Furthermore, during water level recovery, the water level of pumping wells and its surroundings rose rapidly, which was a difference of about 0.28 m from the initial water level after 30 days, indicating that the groundwater level had recovered to the state before pumping. Due to the emergency pumping time is not long, the water levels of Tonglu Canal, surrounding residential wells, and other aquifers will not be affected. After stopping pumping, the water level recovers quickly, so the change of water level in a short time will not lead to large land subsidence and has little impact on the surrounding environment.

Sign in / Sign up

Export Citation Format

Share Document