Water Gauge Research Articles

Wireless water consumption sensing system for building energy efficiency: A visual-based approach with self-powered operation

The use of smart wireless remote water meters has become popular due to their efficiency in avoiding manual labor and automate meter reading. The current implementation of these measurement instruments often requires expensive external power sources and separate data aggregators, posing challenges for circuit safety and the goal of reducing carbon emissions in aging communities. In response, a novel wireless system has been developed to accurately measure water consumption in buildings. This system incorporates advanced machine learning techniques and utilizes the potential of water-based energy in a seamless manner. This novel methodology utilizes optical sensors to acquire visual data of water gauges and exploits machine learning techniques, specifically the AVSM model also called Advanced Visual Sensing Model (AVSM). This methodology employs a rigorous approach to achieve accurate metric determinations, thereby eliminating the necessity for additional hardware or excessive power configurations. Moreover, an integrated micro water generator has been seamlessly implemented, demonstrating the capability to effectively transfer energy to a lithium battery for the purpose of storage. This implementation guarantees consistent functionality and a significant decrease in reliance on external power supplies. The data augmentation procedure involves the stochastic manipulation of image luminance, resulting in encouraging results when used in conjunction with the AVSM model. Significantly, the dimensions of the model have been significantly decreased, while maintaining a commendable mean average precision (mAP). By leveraging this method and visual-based features, the system can contribute to overall building energy efficiency and reduce the burdens of manual meter reading while supporting CO2 emissions reduction as a feasible and cost-effective solution for building management, promoting sustainability, and advancing energy-efficient practices in old communities. This new wireless system for measuring water usage provides a practical and affordable way to enhance energy efficiency in buildings, lessen the workload of manual meter reading, and help meet carbon emissions reduction goals. As well as optimizing resource and energy use, this method also aligns with eco-friendly solutions to combat global warming and climate change.

Statistical Analysis of the Hydrological and Hydrometeorological Characteristics of the Upper Tisza Basin

Tisza is the largest water base in the eastern part of Szabolcs-Szatmár-Bereg County, in north-eastern Hungary, and its indirect use is mainly associated with agriculture. Our work investigates the hypothesis that decrease in water levels and water discharges of the Upper Tisza in recent decades, together with the incision of the riverbed and the precipitation falling in the area, have an impact on the groundwater level of the Szatmár-Bereg Plain. In our study, data from three water gauges located between the settlements of Tiszaújlak and Vásárosnamény and data from groundwater level monitoring wells (MW) and Hydrometeorological (HMS) stations on the Szatmár-Bereg Plain were compared using statistical methods in Past 4.11 software. The aim of the current study was to identify the strategic steps that need to be taken by the organisations responsible for water management in the Upper Tisza basin in the light of the changes in hydrological, hydrometeorological, and meteorological factors. To ensure that the region has sufficient water supplies for the next decade, appropriate water management and agricultural strategies could be the solution.

Whole Watershed-based Estimation of FEWS Installation Site Using UAV Photogrammetry

For small rivers and reservoirs, a flood early warning system (FEWS) is generally used to prepare for sudden flood events whose impact is augmented from homonized environment and climate change. Currently, a FEWS requires the installation of a water gauge, typically on a bridge. This is a limitation of the FEWS owing to the possibility of existence of areas that are more vulnerable than the bridge. Therefore, to analyze the flood risk over the entire target basin, a procedure to install a FEWS was proposed. First, unmanned aerial vehicle (UAV)-based photogrammetry information is analyzed to preselect flood-prone areas. Second, further investigation including the ground surveying is followed for the preselected areas. Finally, the flood amount is estimated and the UAV photogrammetry information for issuing the alarm levels of the FEWS. For this purpose, Malgol Reservoir, a reservoir with high-risk level from floods, containing residential areas was selected as the current study area. Eleven flood-prone points were identified by analyzing the UAV photogrammetry information. Then, the flooding point with the lowest flood volume among the 11 points was selected as the most vulnerable point; this section was located at 464 m from the Malgol Reservoir spillway in the downstream direction. The warning alarm for the basin-wide FEWS could be issued according to the embankment of the most vulnerable section. This ensured the safety over the entire basin including the reservoir and its downstream area. The proposed procedure can overcome the limitations of the current bridge water level-based analysis by employing UAV-photogrammetry information of the entire basin and considering the entire flood-prone cross-sections.

URBAN ENVIRONMENTAL FLOOD SUSCEPTIBILITY USING A MULTI-LAYERED NEURAL NETWORK MODEL FROM SATELLITE IMAGERY SOURCES

<p>Recently, there has been a rise in research based on data-driven based machine learning models to address the issue of processing speed posed by various physiological simulations. The majority of studies, however, have concentrated on creating models for particular water sources, drainage systems, and gauge stations area. Therefore, unless further data is supplied and the models are subsequently trained, their outcomes cannot be effectively applied to different scenarios. With its excellent spatio-temporal accuracy range with the advanced analytics, the forthcoming Global Navigations Satellite Systems (GNSSs) technology offers a novel method for the monitoring of flood disasters in dynamic manner. This study recommends a Multi-layered Neural Network (MNN) for flood monitoring, which combines a Convolutional Neural Networking (CNN) along with a backward propagation based (BP) learning network. The CNN component is used to obtain the abstracted features from full delay doppler maping images. The BP section is provided with GNSSs characteristics, such as reflection of surface with power range, and also the vegetation attributes from the Soil Moistening Active Passives (SMAP) satellite source data. In comparison to physiologically based models, the results shown that the CNN-oriented system makes accurate predictions on "unseen" areas of catchment with a substantially shorter processing time. The obtained results imply that, with respect to accuracy of prediction, the patch-enabled option is superior to the resizing-based option. Additionally, every experiment has demonstrated that the forecast of flow speed is more precise than the prognosis of water depth, indicating that the water deposition is more complex to information about global level elevations than the flow speed with velocity.</p>

Real-Time Water Level Monitoring Based on GNSS Dual-Antenna Attitude Measurement

Real-time and high-precision water level monitoring is crucial for the fields of hydrology, hydraulic engineering, and disaster prevention and control. The most prevalent method for measuring water level is through the use of water level gauges, which can be costly and have limited coverage. In recent years, Global Navigation Satellite System Reflectometry (GNSS-R) technology has emerged as a promising approach for water level monitoring due to its low cost and high coverage. However, a limitation of current GNSS-R technology is the extended time required to record signals, which hinders its potential for real-time application. This paper introduces a novel real-time water level monitoring method based on GNSS dual-antenna attitude measurement and develops a model to invert water level based on baseline vector. This method uses double-difference observations to eliminate errors caused by various factors, such as satellite and receiver clock, and ionospheric and tropospheric delay. To avoid the impact of detecting and correcting cycle slips during real-time operations, a single-epoch calculation method is introduced. In order to verify the stability and reliability of our method, field tests were carried out at Dongshahe Station in Beijing. We obtained water level data with a time resolution of 1 Hz through field experiments. Experimental data collected from 12 May to 8 June 2022 and from 4 July to 8 August 2022 showed good agreement with on-site water gauge measurements, with root mean square errors of 2.77 cm and 2.54 cm, respectively. Experimental results demonstrate that this method can achieve high-precision, high-temporal-resolution water level monitoring.

Application of Deep Learning Techniques in Water Level Measurement: Combining Improved SegFormer-UNet Model with Virtual Water Gauge

Most computer vision algorithms for water level measurement rely on a physical water gauge in the image, which can pose challenges when the gauge is partially or fully obscured. To overcome this issue, we propose a novel method that combines semantic segmentation with a virtual water gauge. Initially, we compute the perspective transformation matrix between the pixel coordinate system and the virtual water gauge coordinate system based on the projection relationship. We then use an improved SegFormer-UNet segmentation network to accurately segment the water body and background in the image, and determine the water level line based on their boundaries. Finally, we transform the water level line from the pixel coordinate system to the virtual gauge coordinate system using the perspective transformation matrix to obtain the final water level value. Experimental results show that the improved SegFormer-UNet segmentation network achieves an average pixel accuracy of 99.10% and an Intersection Over Union of 98.34%. Field tests confirm that the proposed method can accurately measure the water level with an error of less than 1 cm, meeting the practical application requirements.

Does the osteopathic pedal pump reduce lower limb volume in healthy subjects?

Lymphatic treatments are gentle and passive techniques believed to enhance movement of lymph back into the central circulatory system. Animal studies provide supportive evidence, yet there are few studies in humans. The aim of this study is to investigate whether the osteopathic pedal pump protocol reduces volume in the lower limbs of healthy subjects. A total of 30 first- and second-year medical students were recruited. Subjects were excluded from participating if they had acute asthma, chronic obstructive pulmonary disease (COPD), congestive heart failure, active infections, fractures of the lower extremities, or metastatic cancer. A within-subjects study design with pre- and posttreatment measurement of lower limb volume was utilized. Pretreatment lower limb volume measurements were obtained utilizing a volumetric water gauge prior tomyofascial thoracic inlet release anda 5min pedal lymphatic pump protocol treatment. Posttreatment lower limb measurements were taken immediately following the protocol treatment. A telephone interview was conducted 2-3days after the treatment to assess the participants' experience of the treatment and whether the treatment elicited a subjective change from baseline. A paired t test was utilized to determine the statistical significance of volume displacement posttreatment. The mean change of pretreatment to posttreatment lower limb volume was-45.63mL with a standard deviation of 37.65mL. The change between the pretreatment and posttreatment volume measurements was statistically significant (p<0.001). The minimum displacement was+19mL, and the maximum displacement was-167mL. The majority of participants perceived the treatment as effective and enjoyable, were likely to recommend it to others, and were willing to have it performed on them at routine office visits if there was a need. The osteopathic pedal pump technique, when utilized on those without leg lymphedema, reduces lower limb volume as measured by the volumetric water gauge. Further studies are warranted, especially in persons with excess lower-extremity edema, lymphedema or venous stasis.

Assessment of runoff characteristics changes of small and medium-sized rivers in Central Yakutia under the climate change influence

The response of river catchments located on the territory of Russia to climate change in recent decades has been expressed in the emergence of multidirectional trends in the series of annual runoff, maximum water discharges and the value of winter runoff. However, the response of small and medium-sized rivers to the ongoing climate warming has been poorly studied, in contrast to large rivers. In this paper, a comprehensive analysis of the climatic and hydrological characteristics of small and medium-sized rivers of Central Yakutia as well as an assessment of the climate change impact on the river runoff characteristics in various conditions of the region were carried out. It has been established that the revealed positive trends in temperature correspond to the trends typical for the rest of the Russian Federation. The response of the runoff of small and medium-sized rivers to climate change is most significant in the winter-spring months of the year: there is an increase in runoff in the spring and winter periods and for the year as a whole. A feature of the response of the river catchments of the study area in comparison with the European part of Russia and southern Siberia is the presence of statistically significant trends in the series of annual water discharges for most of the studied water gauges. The most noticeable changes (as a percentage of the base period) occurred in the annual runoff of small rivers, because small rivers respond most quickly to external influences. Its expressiveness is determined not only by the degree of changes in climatic characteristics, but also by the features of runoff formation in the watersheds of the study area, in particular, the presence of permafrost.

ДОВГОСТРОКОВЕ ПРОГНОЗУВАННЯ ДАТИ ПОЧАТКУ ВЕСНЯНОГО ВОДОПІЛЛЯ У ВЕРХІВ’Ї РІЧКИ ПІВДЕННИЙ БУГ ЗА ТЕЛЕКОННЕКЦІЙНИМИ ІНДЕКСАМИ

The start date of spring flood is an important hydrological characteristic. Insufficient attention is paid to its long-term forecasting, which is due to the complexity and unsolved problem in terms of improving the quality of such forecasting. Most often, quantitative methods are used in long-term forecasting. The most used are statistical, correlation, and regression analysis. Recently, teleconnection indices and patterns are increasingly used in hydrological long-term forecasting. At the same time, the basis of the concept of forecasting by the teleconnection connections is the idea of the influence of distant fluctuations of atmospheric circulation on the hydrological event. So, the theteleconnection indices and patterns are used for forecasting and analysis of river flow, atmospheric precipitation, research of snow water equivalent of river basins, forecasting of droughts and ice phenomena. The objective of this of the study is to develop a methodology of the long-term forecast of the spring flood start date in the upper part of the Southern Buh River using teleconnection indices and patterns. The method of long-term forecasting of the start date of spring flood was developed for the Southern Buh River – Lelitka village water gauge. The Southern Buh River – Lelitka village water gauge is located in the forest zone and characterizes homogeneous conditions of the formation of spring flood. Information on the start dates of spring flood for the observation period 1966-2015 and teleconnection indices and patterns were used. The start dates of spring flood at the Southern Buh River near Lelitka village are characterized by significant variability. So, the difference between late and early dates of spring flood is 65 days. 34 teleconnection indices and patterns were used, which the National Oceanic &amp; Atmospheric Administration USA were determined. The best regression relationship with the start dates of spring flood at the South Buh River – Lelitka village water gauge was obtained for the indices WPAC850 in January and AAO in December. The technique corresponds to the “satisfactory” category for the probability of not exceeding the permissible error, which allows it to be used for forecasting. So, the teleconnection indices and patterns can be quite successfully used in the long-term forecasting of the start date of spring flood.

АВТОМАТИЗОВАНА СИСТЕМА «ICE-AUTUMN» ДЛЯ ДОВГОСТРОКОВОГО ПРОГНОЗУВАННЯ ДАТ ПОЯВИ ЛЬОДОВИХ ЯВИЩ ТА ВСТАНОВЛЕННЯ ЛЬОДОСТАВУ НА ВОДОСХОВИЩАХ ДНІПРОВСЬКОГО КАСКАДУ

Long-term forecasting of long-term forecasting of appearance dates of ice phenomena and freeze-up at the Dnipro Cascade reservoirs is important, first of all, of practical importance, since on its basis is planned the work of hydropower, shipping, fisheries, utilities, etc. In the modern world, providing consumers of the predictive hydrological products is done with the help of various automated computer complexes and systems that have a convenient user interface. This approach has become widely used in Ukraine too. Thus, the Ukrainian Hydrometeorological Center uses the automated forecasting and modeling complexes that allow short- and long-term forecasting of streamflow during floods on the rivers of Ukraine. Along with this, the automated system for forecasting the appearance timing of ice regime of rivers and reservoirs of Ukraine was created only for short-term forecasting. The main objective of this research is to create an automated system for long-term forecasting of appearance dates of ice phenomena and freeze-up at the Dnipro Cascade reservoirs for its further use in the operational practice of the Ukrainian Hydrological Center. The software of the automated system “Ice-Autumn” for long-term forecasting of appearance dates of ice phenomena and freeze-up at the Dnipro Cascade reservoirs is written in the C# and C++ programming languages in the Visual Studio 2022 Community Edition frame in the form of Windows forms and console applications. The basis of the system “Ice-Autumn” is predictive dependencies, which were determined by finding the best correlation or regression relationships between dates at indicator gauges and teleconnection indicators, as well as between dates at indicator posts and dates at other gauges of reservoirs. Forecasts can be carried out once a year, namely on October 20 for the appearance dates of ice phenomena and November 1 for the appearance dates of freeze-up. The automated system “Ice-Autumn” allows to carried out the long-term forecasting of appearance dates of ice phenomena and freeze-up at 36 water gauges at the Dnipro Cascade reservoirs. Testing of the “Ice-Autumn” system showed its efficiency and, accordingly, the possibility of its use in the operational work of the Ukrainian Hydrometeorological Center. Instructions for installing the “Ice-Autumn” system on a personal computer and a user manual were developed.

ЙМОВІРНІСНІ ХАРАКТЕРИСТИКИ І СТАТИСТИЧНІ ПАРАМЕТРИ СТРОКІВ НАСТАННЯ ОСНОВНИХ ФАЗ ЛЬОДОВОГО РЕЖИМУ РІЧОК БАСЕЙНУ ПРИП’ЯТІ У МЕЖАХ УКРАЇНИ

Probabilistic characteristics of the water body ice regimes significantly expands knowledge about their variability, magnitudes and appearance timing of main phases. Such knowledge is important for the design and operation of hydraulic structures. Along with this, the probabilistic characteristics of the river ice regimes of Ukraine were calculated in the 70s of the 20th century, including for some rivers of the Pripyat basin. Therefore, the main objective of this research is to determine the probabilistic characteristics and statistical parameters of the appearance dates of main phases of river ice regimes, namely appearance date of ice, date of freeze-up, break-up date (i.e., melt onset), date of ice disappearance in the Prypiat River basin within Ukraine, as well as the analysis of the obtained results. The research was carried out based on the data of 29 water gauges for the period from the beginning of observations to 2020. Such indicators as the multi-annual mean, standard deviation and asymmetry coefficient were used as statistical parameters. The analytical distribution of the appearance dates of main phases of river ice regimes is determined by the Pearson curve of type III, and empirical distribution is determined by the Weibull formula. Statistical series of the appearance dates of main phases of river ice regimes were arranged from early to late dates, namely low probability values were assigned to early dates, and large probability values were assigned to later dates. Pearson probability distribution of type III quite successfully describes the empirical points of main phases of river ice regimes of the Pripyat basin within of Ukraine. Analytical distribution curves have a slight negative asymmetry for the dates of the ice appearance and freeze-up, and a positive asymmetry for the dates of the break-up and ice disappearance. The variability of standard deviation and multi-annual mean of the appearance dates of main phases of river ice regimes is within ±7.5-10 days and 3-4 weeks, respectively. In general, the appearance dates of main phases of river ice regimes, as well as their statistical parameters and probabilistic characteristics have close values that are subject to geographic zoning. The analysis of changes over time in probabilistic characteristics and statistical parameters of the dates of ice appearance and freeze-up showed that the greatest changes have by probabilities that are not repeated often, and the smallest – by multi-annual mean and asymmetry coefficients.

UAV-Based Floodwater-Level Establishment for FEWS for Abrupt River Section Change in Imsan

Flood damage has been increasing owing to climate change; thus, a flood early-warning system (FEWS) has been established to evacuate residents safely in flood-prone areas. The FEWS is a fundamental nonstructural system that reduces human and material damage caused by floods. The damage can be minimized when appropriate settings are used. In general, the need for an early warning is determined using a water gauge installed on a bridge. If there is an abrupt change in the river section near the bridge, an alarm is issued based on the water-level gauge on the bridge. However, some areas may be more vulnerable to flooding than where the bridges exist. In these cases, vulnerable areas can be inundated by floods before a warning alarm is provided. The current study area of the Chogang-cheon River is such an area. Therefore, an unmanned aerial vehicle (UAV)-based remedy is proposed to overcome the discrepancy between the flooding water levels of the gauge location and the vulnerable area. First, spatial information about the river cross section was obtained through a UAV for the study area. As a result of Pix4D processing after river surveying by the UAV, a noticeable abrupt river width change section was confirmed, particularly upstream of the Gwangi Bridge in the middle of the Chogang-cheon River. Then, the level of the bridge and the upstream point of the bridge for the same flow rate were calculated using the Hydrologic Engineering Center River Analysis System (HEC-RAS) program. Through this remedy, the section of the river where flooding occurs first was defined, and an appropriate flood early-warning water level was appropriately estimated. The approach in this study can be widely applied to rivers where a FEWS is needed to determine where rivers change abruptly.

Historic Variability of the Water Inflow to the Lazaro Cardenas Dam and Water Allocation in the Irrigation District 017, Comarca Lagunera, Mexico

An assemblage of tree-ring chronologies for the Nazas (NZW) in the Western Sierra Madre (WSM), Mexico was developed to determine water inflow at the Lazaro Cardenas Dam (LCD), the main source of water for surface irrigation in the Irrigation District 017 (DDR 017), Comarca Lagunera. A Principal Component Analysis of the ring-width chronologies was conducted to determine a common climate signal, and a stepwise model based on selected chronologies of the PC1 (CBA, COC) and PC2 (ARN) were used to develop a water inflow reconstruction to the Lazaro Cardenas Dam (LCD) extending from 1753 to 2003 (251 years), resulting in the following significant findings: the warm phase of the El Niño Southern Oscillation (ENSO) in the winter-spring season had a significant influence (SOI; Dec–Feb = −0.24, p &lt; 0.01), but the North American Monsoon System (NAMS) was the most important in determining the water yield in the summer season (r = 0.48, p &lt; 0.01). Water gauge inflow records (77 years) at the LCD used to determine the annual allocation of water for agriculture in the irrigation district 017 was an average of 1676 × 106 m3, where the maximum annual water outflow allowed of 1100 × 106 m3 for safety reasons, the dam infrastructure was released in 74% of the years and increasing to 78% when considering the reconstructed inflow. Prolonged drought episodes lasting more than 10 consecutive years were detected in the reconstructed inflow, information that could be used by decision makers to establish proper irrigation management strategies to ameliorate the economic and social impact when these extreme hydroclimatic events may occur.

Reconstruction of long-term water temperature indicates significant warming in Polish rivers during 1966–2020

Study regionThe study region comprises 125 water gauges from 70 rivers covering the whole territory of Poland. Study focusThe air2stream model was used to reconstruct daily river water temperature (RWT) from 125 water gauges in 70 Polish rivers for the period 1966–2020 (55 years). Then, the annual and seasonal warming trends of RWT, and a biologically relevant metric (the annual number of days when water temperature exceeded 20 °C) were evaluated. New hydrological insights for the regionThe modelling results showed that the air2stream model performed well for RWT modeling (the averaged Root Mean Square Error (RMSE) values for the calibration and validation periods are 1.21 and 1.32 °C, and Nash-Sutcliffe efficiency coefficient (NSE) for the two periods are 0.96 and 0.95 respectively). Annual averaged RWT of 121 gauges (96.8 % of the 125 gauges) showed clear warming trend in the past 55 years with the warming rate ranging between 0.08 and 0.44 °C/decade (average: 0.25 °C/decade). The warming trends of river waters on the main rivers and their tributaries are spatially differentiated. Seasonal RWT trends showed that summer is warming fastest, followed by spring and then by autumn and winter. Long-term increases in RWT were typically correlated with increases in air temperatures. For the three large rivers (Vistula, Odra, and Warta), the biologically relevant metric (the annual number of days when water temperature exceeded 20 °C) increased synchronously with the warming of RWT. The results reported in this study will be useful to stakeholders and the reconstructed dataset will be useful to the community for the further study of river thermal dynamics and aquatic habitats in Poland.

An Integrated Method for River Water Level Recognition from Surveillance Images Using Convolution Neural Networks

Water conservancy personnel usually need to know the water level by water gauge images in real-time and with an expected accuracy. However, accurately recognizing the water level from water gauge images is still a complex problem. This article proposes a composite method applied in the Wuyuan City, Jiangxi Province, in China. This method can detect water gauge areas and number areas from complex and changeable scenes, accurately detect the water level line from various water gauges, and finally, obtain the accurate water level value. Firstly, FCOS is improved by fusing a contextual adjustment module to meet the requirements of edge computing and ensure considerable detection accuracy. Secondly, to deal with scenes with indistinct water level features, we also apply the contextual adjustment module for Deeplabv3+ to segment the water gauge area above the water surface. Then, the area can be used to obtain the position of the water level line. Finally, the results of the previous two steps are combined to calculate the water level value. Detailed experiments prove that this method solves the problem of water level recognition in complex hydrological scenes. Furthermore, the recognition error of the water level by this method is less than 1 cm, proving it is capable of being applied in real river scenes.

Response of Low Flows of Polish Rivers to Climate Change in 1987–1989

The paper discusses changes in the low-flow regime of rivers in Poland, resulting from climate change that occurred between 1987 and 1989. The low-flow variability of rivers was measured with the use of the number of days with low flows (NDLF) below a threshold value, which was adopted as the 0.1 (10%) percentile (Q10) from the set of daily flows recorded in the multi-annual period 1951–2020 at 140 water gauges on 83 rivers. The analysis of the course of climate change over Poland showed that it was caused by macro-circulation conditions, controlled by changes in the intensity of thermohaline circulation in the North Atlantic (NA THC). Climate change consisted of a sharp increase in sunshine duration and air temperature, and a decrease in relative humidity after 1988. Along with the lack of changes in precipitation totals, characterized by a strong yearly variability, and an increase in field evaporation, it led to noticeable changes in the water balance. As a result, in 1989–2020, there was a significant increase in NDFL detected in about 2/3 of the area of Poland. With the change in the NA THC phase and the macro-circulation conditions, there was also a change in the spatial distribution of areas drained by rivers with increased NDFL. In 1951–1988, these included the eastern parts of Poland, while after the climate change (1989–2020), its western and south-western parts.

A Water Gauge Scale Capturing Method in Tidal Well Based on Image Recognition

Tide level observation data is an important technical support data for the delimitation of warning tide level and disaster prevention. The performance of the tidal well is tested by regularly checking the external water gauge, so as to maintain the tidal follow-up and wave dissipation of the tidal well. The check of water gauge inside and outside the well shall be carried out once a month. It is time-consuming and labour consuming. The paper proposes a real-time borehole water gauge capturing algorithm in tidal well based on image recognition. Experiments have proved that the method can recognize the water gauge scale effectively. The comparison experiments with the other standard measurement method are done. It can be seen from the comparison chart that the error between the water gauge scale and the tide level value is ± 1cm, which meets the national standard.

Water Quality Measurement and Modelling Based on Deep Learning Techniques: Case Study for the Parameter of Secchi Disk.

The Secchi disk is often used to monitor the transparency of water. However, the results of personal measurement are easily affected by subjective experience and objective environment, and it is time-consuming. With the rapid development of computer technology, using image processing technology is more objective and accurate than personal observation. A transparency measurement algorithm is proposed by combining deep learning, image processing technology, and Secchi disk measurement. The white part of the Secchi disk is cropped by image processing. The classification network based on resnet18 is applied to classify the segmentation results and determine the critical position of the Secchi disk. Then, the semantic segmentation network Deeplabv3+ is used to segment the corresponding water gauge at this position, and subsequently segment the characters on the water gauge. The segmentation results are classified by the classification network based on resnet18. Finally, the transparency value is calculated according to the segmentation and classification results. The results from this algorithm are more accurate and objective than that of personal observation. The experiments show the effectiveness of this algorithm.

A Water Level Measurement Approach Based on YOLOv5s.

Existing water gauge reading approaches based on image analysis have problems such as poor scene adaptability and weak robustness. Here, we proposed a novel water level measurement method based on deep learning (YOLOv5s, convolutional neural network) to overcome these problems. The proposed method uses the YOLOv5s to extract the water gauge area and all scale character areas in the original video image, uses image processing technology to identify the position of the water surface line, and then calculates the actual water level elevation. The proposed method is validated with a video monitoring station on a river in Beijing, and the results show that the systematic error of the proposed method is only 7.7 mm, the error is within 1 cm/the error is between 1 cm and 3 cm, and the proportion of the number of images is 95%/5% (daylight), 98%/2% (infrared lighting at night), 97%/2% (strong light), 45%/44% (transparent water body), 91%/9% (rainfall), and 90%/10% (water gauge is slightly dirty). The results demonstrate that the proposed method shows good performance in different scenes, and its effectiveness has been confirmed. At the same time, it has a strong robustness and provides a certain reference for the application of deep learning in the field of hydrological monitoring.

Measuring Water Levels by Handheld Smartphones – A contribution to exploit crowdsourcing in the spatio temporal densification of water gauging networks

Global climate change leads to an increase in local heavy rainfall events causing nearly unpredictable flash floods worldwide. This paper introduces a novel and flexible low-cost water gauging technology, called Open Water Levels, using smartphones as low-cost measuring devices enabling the crowdsourcing of water levels on demand with accuracies of a few centimetres. This merely requires smartphone camera images of a riverbank and approximate values of the camera position and rotation measured by smartphone sensors. The images are analysed for the water line that is further projected into object space and intersected with a 3D model, e.g. from a GIS database, to derive water level information.