AI Detection Method for River Water Level Based on Image Segmentation Processing

The monitoring and analysis of the water level in the Mekong River is of major importance in water resources security, management, and geostrategic cooperation. This study proposed a new approach for monitoring and analysis of changes in water level of the Mekong River by using ICESat-2 spaceborne laser altimetry. River water levels were extracted from ICESat-2 inland water level data (ATL13). Then, the remote-sensed water level was quantitatively compared with the in situ water level measured by hydrological stations. Finally, the responses of water level to natural and anthropogenic factors were explored. The results showed that the ATL13 products provided river water level data with a high precision (root mean square error (RMSE) = 0.24 m, bias = −0.11 m) and a low measurement uncertainty (median of standard deviations (MSD) = 0.04). The analysis indicated that ATL13 products under different beam intensities and acquisition times can be applied to derive river water level. However, the use of nighttime measurements achieved slightly higher accuracies. The seasonal characteristics of river water level (flooding season from May to October and dry season from November to April of the next year) were because of natural factors, such as upstream flow and rainfall. A comparison of water level changes among different periods showed that hydropower development generally decreased the range of water level in the flooding season and increased water level in the dry season, thereby mitigating the current uneven spatial and temporal distribution characteristics of water resources in Mekong basin.

The developed method for predicting the flood water level allows to analyze statistical data from meteorological stations (precipitation, humidity deficit and wind speed) to predict the water level in rivers during floods.The method for constructing approximating curves was performed on the basis of statistical data on the Prut River level and meteorological data (precipitation amount, air humidity and wind speed) from meteorological stations in the cities of Yaremcha, Kolomyia and Chernivtsi during the flood waters from 24.07.08/03 to 25.07.08/15.The obtained results and the proposed method will allow to predict flood waters, and the more data from meteorological stations the more accurate the weather forecast that will allow to reduce economic costs and avoid casualties during flood waters.Currently, studies of the influence of one meteorological data on the other, and their impact on rising the water level in rivers using contingency factor are carried out.Having revealed the correlation of data from meteorological stations and data on the water rise level, further studies will be directed at determining the model adequacy. However, the proposed model has confirmed the fact that the 100 m/house and more [18] cause catastrophic river water level rise, and also gives grounds to confirm the model adequacy.

Climate change has exacerbated severe rainfall events, leading to rapid and unpredictable fluctuations in river water levels. This environment necessitates the development of real-time, automated systems for water level detection. Due to degradation, traditional methods relying on physical river gauges are becoming progressively unreliable. This paper presents an innovative methodology that leverages ResNet-50, a Convolutional Neural Network (CNN) model, to identify distinct water level features in Closed-Circuit Television (CCTV) river imagery of the Chengmei Bridge on the Keelung River in Neihu District, Taiwan, under various weather conditions. This methodology creates a virtual water gauge system for the precise and timely detection of water levels, thereby eliminating the need for dependable physical gauges. Our study utilized image data from 1 March 2022 to 28 February 2023. This river, crucial to the ecosystems and economies of numerous cities, could instigate a range of consequences due to rapid increases in water levels. The proposed system integrates grid-based methods with infrastructure like CCTV cameras and Raspberry Pi devices for data processing. This integration facilitates real-time water level monitoring, even without physical gauges, thus reducing deployment costs. Preliminary results indicate an accuracy range of 83.6% to 96%, with clear days providing the highest accuracy and heavy rainfall the lowest. Future work will refine the model to boost accuracy during rainy conditions. This research introduces a promising real-time river water level monitoring solution, significantly contributing to flood control and disaster management strategies.

Remote sensing reconstruction of long-term water level and storage variations of a poorly-gauged river in the Tibetan Plateau

This article presents the results of the analysis of modern water levels of the upper reaches of the largest river named Prut in the mountain landscape of Chornohora for the period from 2010 to 2019, based on data from own long-term hydro-meteorological observations on the basis of Landscape Monitoring Laboratory of Ivan Franko National University. The studied river is characterized by a dense river network, a peculiar hydrological regime and periodic formation of heavy floods, as well as the presence in its basin of valuable landscape complexes and environmental facilities, high landscape diversity and recreational and tourist potential, which determines the relevance of this study. As a result of the study, the peculiarities of the formation and modern features of the hydro network of the Prut river basin were established, its heterogeneity in the mid-mountain and high-mountain landscape tiers was characterized. It is established that during the period 2010-2019 in the upper reaches of the Prut River there was an increase in river water levels, as well as identified the main factors and their impact on current changes in the hydrological regime of the river. The annual changes in the water level in the upper reaches of the Prut River for the period 2010-2019 were also analyzed and it was found that its mountainous nature causes high dynamics of river water levels at different times of the year and in certain months. It was important to identify the relationships between their indicators and the characteristics of the annual distribution of precipitation and snowmelt during studying the annual cycles of water level fluctuations. Particular attention is paid to the study of the formation and spread of floods as the most dangerous hydrological phenomenon of the upper reaches of the Prut River, characterized by a sharp rise in water levels, high erosion capacity, etc. The study found that more than 75 % of floods occur during the spring snowmelt in April and May where the average daily river water levels usually do not exceed 60-70 cm. The analysis of flood rises in terms of years and months shows that the most severe catastrophic floods are formed in November-December due to heavy rains, which cause the formation of powerful destructive water flows and catastrophic growth of river water levels over 90-100 cm. The total annual number of flood rises in the Prut River was also analyzed according to certain categories of indicators (over 60 cm, 70 cm, etc.) and it was found that the total number of floods in the upper reaches of the river is increasing.

This wireless monitoring system is developed to alert and warn the resident regarding the upcoming flood. Due to the floods that occur every year, especially during the monsoon season, the loss and damage done by this disaster are uncontrollable. When the water level rise-up above the safe ground, it may hit the communication substation, as well as the power tower. In most cases, many residents are not alert with their surroundings because there is no alert system that can remind them regarding to the issues that will arise. By not preparing themselves for the upcoming nature disaster, it could endanger themselves and destroy their property. Thus, this project focus on monitoring a real-time river water level system for flood prediction purposes which utilize three devices connected together in a centralized system. By having this system, people will be notified about the current situation and the water level of the river near to them via Internet of Things (IoT) such as Blynk application. ESP32 and ESP32-Cam are used as the main microcontroller to control the system. The sensor used to detect the water level at the river is TF Mini Lidar and ultrasonic sensor for the water level detection of the rain gauge. The ESP32-cam are used to monitor the surrounding area at the river. The combination of these three systems is used to monitor and predict the flood occurrence.

The water level of a river needs to be monitored to anticipate the occurrence of flooding. People who live in flood prone areas should know the height of the river water level early enough before flooding occurs. This study had designed and developed a river water level monitoring systems using ultrasonic sensors and a microcontroller-based Android smartphone. The sensor system sends information about the river water level continuously to the microcontroller. The microcontroler analyzes the information and the analysis results are disseminated to the public by means of the Android smartphone equipped with the flood detection application. The test results on the performance of ultrasonic sensors show an average error rate of 1.121 % and an error rate on the speed of change in the water level of 1 cm. Sending SMS on smartphones gets the average delivery time of 5.414 s. For further research, we will design a system monitoring the water level of the river using wireless ultrasonic sensor network as a flood early warning system based on microcontroller and Android smartphone.

The exploitation of rivers and hydropower reservoirs involves daily monitoring of  the water resources, the meteorological conditions, the status of  the river banks, the flood areas, etc. As maximum river discharge often results in flooding, it is of importance to provide with timely and reliable forecasts of discharge and water levels. Predicting river discharge and water levels has been a subject of hydrological modelling and a topic of serious research. However, only in recent years scholars and practitioners have turned to consider earth observation data for their studies, mainly to compare evidence of flood mapping. We present an approach of using earth observation data to feed AI architectures – EO4AI – and produce forecasts for discharge and water level with significant degrees of accuracy.  Our starting point is that river discharge and water levels depend on a variety of meteorological and environmental factors like precipitations, snow cover, soil moisture, vegetation index and satellite data offer rich variety of datasets, supplying this information. We adopt a pipeline of deep learning architectures consisting of GAN, CNN, LSTM and EA to actually generate forecasts for river discharge and water level by using historic satellite data of the meteorological features listed above, and in-situ measurements for water level and discharge. The satellite data are provided by ADAM  via the NoR service of ESA. ADAM provides data access to satellite datasets from different satellites with semantic relevance for the construction of sediment transport and deposition forecast model as discussed above.  We explain the purpose of the pipeline components. Our forecast models are calibrated for 3, 5, 7, 30 days ahead, and our experiments provide predictions for one year ahead with each of the calibrated models. We discuss experiment results carried out with data from the Danube and Arda rivers, including three dams from cascade Arda and compare them with predictions derived with other methods. We demonstrate the viability of the approach and the reliability of the forecasting results. We further show how the forecasts can be used in hydrodynamic modelling context, for early warning applications and for routine water resources management and monitoring tasks.

Diffusion coupling model based on neural oscillation synchronization theory, which can extract different targets with different gray levels from one, has been an important way for realizing image segmentation. This paper describes the diffusion coupling model and its algorithm and process for image segmentation. Simulation programs for supplementing this algorithm were compiled based on MATLAB platform. Experimental results on synthetic images, infrared images and brain magnetic resonance images show that, by setting reasonable algorithm parameters, the target image extraction and segmentation of different elements can be achieved. This image segmentation algorithm exhibits wide applications in medical image diagnosis, satellite image processing, traffic control, biometrics and others.

Indonesia is a country with high rainfall. The rainy season can last for four months of the year. Development in urban areas in increasing resulting, resulting in reduced water absorption areas. People's habit of throwing garbage in waterways is also one of the factors that cause flooding. The current obstacle is the difficulty of monitoring water levels when heavy rains cause water to overflow onto roads and residents' houses. Checking the water level is still done manually, only looking at the measuring limit or ruler found on the river and not giving warning messages when the water level rises and it rains. Devices are needed to monitor water levels during heavy rains and send alerts to officers when it rains and the water level has exceeded the limit. Researchers found the idea to make a water level monitor and rain detector using the Wemos D1 R2 Mini microcontroller, supported by the HC-SR04 sensor and Internet of Things (IoT) based rain sensor. The Blynk application receives data from Wemos to be forwarded as a notification to officers. This system provides real-time information about river water levels and conditions when it rains to help avoid or reduce losses due to flooding. The accuracy value generated by the ultrasonic sensor reaches 99.89%, while from the rain sensor, it reaches 100%.

Inter-comparison study of water level estimates derived from hydrodynamic–hydrologic model and satellite altimetry for a complex deltaic environment

A numerical analysis on the stability of soil–cement column-reinforced riverbank along a river delta region in Viet Nam is presented in this paper. The numerical analyses based on the limit equilibrium method (LEM) were performed to assess the safety factor of the column-reinforced riverbank system under various river water level (RWL) conditions. Several factors influencing the riverbank slope stability including the position, length, quantity of soil–cement columns, and RWL changes were investigated. The simulated results showed that the riverbank stability is improved with an increase in the column quantity and the column length when subjected to a constant RWL. Moreover, the predicted results by LEM indicated that the column location and the RWL change significantly influence the stability of riverbank with column reinforcement. The column location between the middle and the slope toe had a significant improvement of the riverbank slope stability, where an initial drawdown of RWL resulted in a notable reduction of the riverbank slope safety factor. These factors should be taken into consideration in the design of a riverbank slope, reinforced with columns, under variable RWL. It is worth mentioning that the use of soil–cement column-reinforced riverbank could be a practical and possible engineering countermeasure to prevent a steep riverbank slope under RWL variations from sliding failure.

Detection of water level in silty soils can be complicated because of capillary action. In this study, the water level in a silty soil sample was detected using Ground Penetrating Radar (GPR) technique in the laboratory. The soil sample has dimensions of 62 cm × 48 cm × 46 cm and was kept in a clear Plexiglas container which facilitated water level measurements. Two ground‐coupled antennas with frequencies of 900 MHz and 1,500 MHz were used in this study. The soil sample was dry at the beginning of the experiment. The water level in the soil sample was raised to a pre‐determined level and radar readings were taken at different times over 24 hours. The moisture content in the soil sample above the water level increased with time due to capillary action. At the end of the experiment, the variation of moisture content with depth of the sample was experimentally determined. The GPR observations were compared with measured water depth in the soil sample. The paper presents the comparison of water level as determined by GPR with the variation of experimentally determined moisture content in the silty soil sample. This study includes an investigation on the effects of capillary action on GPR measurements.

A stand alone ultrasonic ranging system (SAURS) was designed and applied in hydrological measurements of water levels in rivers, lakes and water reservoirs. Water level ranging is carried out through air by an electrostatic ultrasonic transducer which is controlled by a microprocessor based system. The data is collected in a 64 kByte EPROM cassette. The problems associated with temperature correction were studied theoretically and experimentally. The results suggest that the main temperature effect is related to the temperature dependence of sound velocity in air. It was found that a precision of 1 cm at a distance of 600 cm can be readily obtained provided that air temperature is measured to within 1 degrees C. Level measurements carried out by the SAURS were found to be in excellent agreement with measurement made by a mechanical float-type water level recorder. The advantages of remote water level measurement, as compared to direct contact methods, is examined and discussed. >

The influence of river discharge in the marine environment is expressed in several time scales, but in long time scales it tends to control the residual pattern of behavior of these ecosystems. Studies on the dynamics of the Patos Lagoon, located in the extreme south of Brazil, are limited to considering the effect of wind and river discharge on synoptic time scales. In this sense, the objective of the study is to investigate the time variability scale of the dominant processes over the long term in river discharge and water levels in Patos Lagoon. Several time series of river discharge, water levels and Southern Oscillation Index were used to perform the study. A polynomial model based on the least squares method was used to re-construct series of water levels and statistical analysis methods were used to determine the main cycles of variability and their possible cause and effect relationship in the variables analyzed. The time series analysis suggests that on a scale of years, the river discharge accounts for over 80% of the variability in the lagoonal portion of Patos Lagoon. The river discharge in the main tributaries and the water levels in Patos lagoon are influenced on interannual scales (cycles between 3.3 and 5 years) by El Nino Southern Oscillation. The river discharge and the water levels in the region also follow a pattern of temporal variability with a decadal scale (10.8 year cycle)., which may have been associated with El Nino Southern Oscillation events, or with other oceanic and atmospheric processes of climatic kind on global scales