Prediction of Water Level Using Time Series, Wavelet and Neural Network Approaches

To control water resources in many domains such as agriculture, flood forecasting, and hydro-electrical dams, forecasting water level needs to predict. In this article, a new computational approach using a data driven model and time series is proposed to calculate the forecast water level in short time. Concretely, wavelet-artificial neural network (WAANN) and time series (TS) are combined together called WAANN-TS that encourages the advantage of each model. For this real time project work, Yen Bai station, Northwest Vietnam was chosen as an experimental case study to apply the proposed model. Input variables into the Wavelet-ANN structure is water level data. Time series and ANN models are built, and their performances are compared. The results indicate the greater accuracy of the proposed models at Hanoi station. The final proposal WAANN−TS for water level forecasting shows good performance with root mean square error (RMSE) from 10−10 to 10−11.

Timeline Visualization Uncovers Gaps in Archived Tsunami Water Level Data

We demonstrate that data abstraction via a timeline visualization is highly effective at allowing one to discover patterns in the underlying data. We describe the rapid identification of data gaps in the archival time-series records of deep-ocean pressure and coastal water level observations collected to support the NOAA Tsunami Program and successful measures taken to rescue these data. These data gaps had persisted for years prior to the development of timeline visualizations to represent when data were collected. This approach can be easily extended to all types of time-series data and the author recommends this type of temporal visualization become a routine part of data management, whether one collects data or archives data.

Vulnérabilité De La Commune Urbaine De Mopti Aux Inondations

La commune urbaine de Mopti, particulièrement la ville du même nom, du fait de son positionnement géographique (à la confluence du fleuve Niger et de son principal affluent, le Bani) est exposée aux épisodes d’inondation. L’objectif de cette recherche est de montrer la vulnérabilité de la commune aux évènements pluviométriques et hydriques extrêmes et de proposer des pistes de solutions en vue de prévenir les risques d’inondation. La démarche méthodologique a consisté à analyser les données pluviométriques et hydriques (données de crues et de hauteurs d’eau) journalières de la station de Mopti à l’aide des logiciels Excel et XLSTAT. Les analyses portent sur le calcul des indices de précipitations et hydriques extrêmes et la détermination de leur période de retour. Les résultats font ressortir que la fréquence des évènements pluviométriques et hydriques dans la commune a augmenté depuis la moitié des années 2000, occasionnant des inondations faisant de plus en plus de victimes et d’importants dégâts en raison notamment des problèmes d’aménagement de la commune. Face à ce défi, faudra-t-il la prise en compte des risques climatiques dans les documents de planification locale, une large sensibilisation des populations et le strict respect de la réglementation en vigueur. The urban commune of Mopti, particularly the city of the same name, due to its geographical location (at the confluence of the Niger River and its main tributary, the Bani) is exposed to flooding episodes. The objective of this research is to show the vulnerability of the town to extreme rainfall and water events and to propose possible solutions to prevent flood risks. The methodological approach consisted in analysing daily rainfall and water data (flood and water level data) from the Mopti station using Excel and XLSTAT software. The analyses focus on the calculation of extreme rainfall and water indices and the determination of their return period. The results show that the frequency of rainfall and water events in the commune has increased since the mid-2000s, causing floods with an increasing number of victims and significant damage, due in particular to the commune's development problems. Faced with this challenge, one should take in to consideration of climate risks in local planning documents, a broad awareness of the population and strict compliance with the regulations in force.

CNN-BiLSTM water level prediction method with attention mechanism

Hydrological time series data is stochastic and complex, and the importance of its historical features is different. A single model is difficult to overcome its own limitations when dealing with hydrological time series prediction problems, and the prediction accuracy of a single model can be further improved. According to the characteristics of hydrological time series data, a CNN-BiLSTM water level prediction method with attention mechanism is proposed. In this paper, CNN extracts the spatial characteristics of water level data and BiLSTM learns the time period characteristics by combining the past and future sequence information, attention mechanism is introduced to focus the salient features in the sequence. Taking the hourly water level data of Pinghe basin in China as experimental basis, experimental result shows that this method is more accuracy than Support Vector Machine (SVM), Temporal Convolutional Neural network (TCN), and Bidirectional Long Short-Term Memory network (BiLSTM) model.

Deteksi Level Ketinggian Air Dengan Nikelin, Encoder dan Sensor Tekanan Untuk Sistem Peringatan Dini Banjir

Floods and their problems show an increasing indication when rainfall is high. Data from BNPB shows that floods, landslides and tornadoes contributed to the total disasters in Indonesia in a decade. The existence of an early warning flood disaster can help evacuate before a disaster strikes. The system requires a water level detector as the basic data for determining flood predictions. In order to get the water level value, a touch water method can be used using electrodes or without touching the water with the help of pressure sensors, ultrasonic and imaging. Each method has advantages over the other. In this study, the effectivity and accuracy of detecting water levels were investigated using 3 methods: the direct touch of water through nickel wire, buoys with encoder, and pressure sensors. Detection of water levels can be used as a reference to obtain river water level data which is then connected via an IoT or internet connection as a reference for the Early Warning System for the arrival of floods. This study found that changes in water level of less than 30 cm can utilize buoys and encoders with an accuracy of detecting 5 to 6 counts per 1 mm increase in water level. Meanwhile, the measurement of less than 30 cm water level using nickel wire resulted in a non-linear value. The utilization of nickel wire can be used for a height of more than 30 cm where the change in resistivity has started to be linear. ADC change value is 2.93 mV/cm using 10 bit ADC at 5 Volt reference voltage. For water level heights of 50 cm and above, a pressure sensor can use a pressure sensor that can detect changes in pressure of 0.002 in Hg/mm or 0.05 mmHg/mm.

Study on the effects of wave-induced setup on coastal evolution of the Cua Dai beach, Hoi An

Over the past years, there have been several studies on the hydrodynamic regime, beach erosion, and accretion at the Cua Dai beach in Hoi An city. However, there is still a lack of in-depth research on the effects of hydrodynamic factors on beach evolution in extreme weather conditions such as a storm event or during the Northeast monsoons, characterized by large waves mainly, especially. The wave set-up directly impacts on the evolution of upper beaches and coastal dunes, consequently causing beach erosion. This paper presents the results of nearshore wave propagation and transformation and the distribution of wave set-up during storms in the coastal area of Cua Dai, Hoi An, using the SWAN model and the XBEACH model. The models have been calibrated and validated using measured wave and water level data observed in the study area in October 2016. The simulation results have shown the overall picture of the influence of wave set-up on the morphology evolution of beach profiles in the study area.

Quali-quantitative considerations on low-flow well purging and sampling

This article deals with both the main advantages and issues related to groundwater purging and sampling that are usually carried out through the so-called low-flow methodology or with the method based on the purging of 3-5 well volumes, which is still widely used in environmental monitoring. A review of the recent literature concerning the technical characteristics, innovations and modelling related to low-flow sampling is presented. The aim is to provide to the reader a broad overview on this specific field application and offer a new vision, which considers two aspects: 1. The qualitative aspect, relating to the representativeness of the sample taken through a correct purging of the monitoring well and the consequent correct interpretation of hydrochemical data; 2. The quantitative aspect, related to the possibility of using water level data during purging and low-flow sampling operations to estimate the soil horizontal hydraulic conductivity, without further investigations. Low-flow sampling methodology can be very useful especially for alluvial aquifers, providing representative samples of groundwater and hydrodynamic characteristics of the aquifer, with reduced costs and times. These two aspects are both important in the context of an environmental monitoring plan for a potentially contaminated site.

Long-Term Dataset of Tidal Residuals in New South Wales, Australia

Continuous water level records are required to detect long-term trends and analyse the climatological mechanisms responsible for extreme events. This paper compiles nine ocean water level records from gauges located along the New South Wales (NSW) coast of Australia. These gauges represent the longest and most complete records of hourly—and in five cases 15-min—water level data for this region. The datasets were adjusted to the vertical Australian Height Datum (AHD) and had the rainfall-related peaks removed from the records. The Unified Tidal Analysis and Prediction (Utide) model was subsequently used to predict tides for datasets with at least 25 years of records to obtain the associated tidal residuals. Finally, we provide a series of examples of how this dataset can be used to analyse trends in tidal anomalies as well as extreme events and their causal processes.

Identification of Hydrological Droughts in Lithuanian Rivers

Globally, hydrological droughts are most commonly identified based on various indices calculated from water flow values. However, the water flow rate is calculated from a flow rate curve that needs to be updated constantly, so it takes a long time to resolve its true value. For this reason, the possibility of identifying a hydrological drought on the basis of hourly and prompt treated water levels seems much more attractive. 8 water gauging stations (WGS) operating along 7 important rivers and covering the hydrological areas of visas in the Lithuanian region were selected for the study. In this study, a modified SPI function of the R programming language SPEI package (traditionally used to calculate the standardized precipitation index, SPI) was applied for the streamflow drought index (SDI) calculations. Given how it was applied to the SDI calculation, just like the baseline data, this was the ten-day mean water flow and then the water level. The suitability of water level data for SDI calculations was assessed by analyzing the relationships between SWLI (Standartized Water Level Index) calculated from water level data and SDI calculated from water flow information. SWLI and SDI in all 8 WGS are closely interconnected. It was found that the possibility of recurrence of droughts of different severity identified by both methods is significantly influenced by the profile of the river bed in a specific section. In areas where riverbanks have steeper slopes, the SWLI and SDI similarly describes the water situation and the recurrence of droughts. It is believed that a modified SDI methodology (SWLI), which is based on water level data, may become a good alternative in our country for identifying hydrological droughts. Keywords: Lithuanian rivers, hydrological drought, identification of droughts, water level, SDI, SWLI.