Flood Monitoring System Research Articles

Designing Deep-Based Learning Flood Forecast Model With ConvLSTM Hybrid Algorithm

Efficient, robust, and accurate early flood warning is a pivotal decision support tool that can help save lives and protect the infrastructure in natural disasters. This research builds a hybrid deep learning (ConvLSTM) algorithm integrating the predictive merits of Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) Network to design and evaluate a flood forecasting model to forecast the future occurrence of flood events. Derived from precipitation dataset, the work adopts a Flood Index ( I <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</sub> ), in form of a mathematical representation, to capture the gradual depletion of water resources over time, employed in a flood monitoring system to determine the duration, severity, and intensity of any flood situation. The newly designed predictive model utilizes statistically significant lagged I <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</sub> , improved by antecedent and real-time rainfall data to forecast the next daily I <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</sub> value. The performance of the proposed ConvLSTM model is validated against 9 different rainfall datasets in flood prone regions in Fiji which faces flood-driven devastations almost annually. The results illustrate the superiority of ConvLSTM-based flood model over the benchmark methods, all of which were tested at the 1-day, 3-day, 7-day, and the 14-day forecast horizon. For instance, the Root Mean Squared Error (RMSE) for the study sites were 0.101, 0.150, 0.211 and 0.279 for the four forecasted periods, respectively, using ConvLSTM model. For the next best model, the RMSE values were 0.105, 0.154, 0.213 and 0.282 in that same order for the four forecast horizons. In terms of the difference in model performance for individual stations, the Legate-McCabe Efficiency Index (LME) were 0.939, 0.898, 0.832 and 0.726 for the four forecast horizons, respectively. The results demonstrated practical utility of ConvLSTM in accurately forecasting I <sub xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">F</sub> and its potential use in disaster management and risk mitigation in the current phase of extreme weather events.

Flood Warning and Monitoring System (FWMS) using GSM Technology

Floods are natural disasters that occur due to climate factors. The impact of floods on property and lives can be too high, resulting in the need to establish a monitoring system. FWMS is a personal flood monitoring system that has the ability to call and send warning via SMS. The warning was sent to not only system users, but also directly to the Fire and Rescue Station as floodwaters rose rapidly to dangerous levels. FWMS is developed using Arduino Uno microcontroller, ultrasonic sensor (HC-SR04) and GSM SIM900A module. Using FWMS, users can apply for flood status in their area in real time via SMS. In FWMS, there are three different levels of flood warning system. The first is the "normal" level, when the situation is normal. The second is the "warning" level, where an SMS will be sent to the users each time a flood is detected. Meanwhile, the third is known as the "danger" level, which will be sent when the depth of the flood that occurs is detected to be higher. For both levels of “warning” and “danger”, a loud buzzer will be issued as a warning sound notification to users. Three types of tests were performed on the FWMS to measure its level of performance. These tests were functional tests, prototype system tests, and GSM network performance tests. They were done to ensure that FWMS can be used and function properly as required. The tests have produced positive results and it is potentially to be further enhanced.

Spatial evaluation of satellite-retrieved extreme rainfall rates in the Upper Awash River Basin, Ethiopia

Understanding the performance of satellite-retrieved extreme rainfall rates is a prerequisite for developing appropriate flood and drought monitoring systems in a region where rain gauge data are sparse and unevenly distributed. In this study, seven satellite rainfall estimates (SREs) that primarily use the infrared (PERSIANN, PERSIANN-CDR, and TAMSATv3) and the microwave (CMORPHv1, TRMM 3B42RT, TRMM 3B42v7 and IMERG-v06B) data were evaluated in the highland and lowland regions of Upper Awash Basin, Ethiopia, from 2003 to 2015. Three categorical error metrics, seven extreme precipitation indices, and the Empirical Cumulative Distribution Function (ECDF) plot were used to compare satellite retrieved extreme rainfall rates against rain gauge observations using a pixel-to-point approach. Results showed that TAMSATv3 outperformed all the remaining SREs in detecting and estimating low rainfall in both the highlands (elevation>2000 m) and lowlands (elevation<2000 m) of the basin. For high rainfall, the IMERG-v06B followed by TRMM 3B42v7 and TRMM 3B42RT products relatively produced the best result in both regions. Overall, the performance of SREs in detecting and estimating extreme rainfall rates was better in the highlands than in the lowlands, and this may be associated with the density of rain gauge networks. Additionally, all seven SREs can correctly detect low rainfall but their performances tend to worsen as the extreme precipitation quantile increases. In both regions, on average, the microwave-based SREs showed the highest result in capturing high rainfall. In contrast, the infrared-based SREs had a better performance for low rainfall. This study suggests that TAMSATv3 product can be used for drought monitoring studies in the basin; however, a lot of effort (e.g. bias-adjustment, and improvements of SREs algorithm) could be needed to integrate SREs into hydrological models for flood forecasting and early warning purposes.

An IoT and AI based Flood Monitoring and Rescue System

An IoT and AI based Flood Monitoring and Rescue System

Causative factors of landslides 2019: case study in Malappuram and Wayanad districts of Kerala, India

Several landslides and floods were triggered by unprecedented, incessant heavy monsoon rainfall from 4 August 2019 to 8 August 2019, along the northern slopes, at Kavalappara, in the Malappuram district and Puthumala, in the Wayanad district of Kerala, India. The geological and geomorphological field settings were analyzed within the sub-basin wide catchment areas, for a preliminary evaluation of the causative factors of the landslides. This paper provides insights into the causative factors of landslides, together with suggestions on appropriate land use planning and deployment of real-time flood and landslide monitoring systems, besides building an adaptable community resilience model in high landslide-prone areas. The structurally disturbed weakened bedrocks and generally incompetent residual alteration products, exacerbated by nonchalant human interventions, reduction of cohesive strength, on super-saturation of underlying earth material, were inferred to be the primary causes of major landslides, triggered during 5 days of excessively heavy rainfall (400% over the normal average). Additionally, massive toe erosion was observed by streams gushing with course clastic sediments and debris. The destructive nature of such multi-hazards was evoked by unscientific modifications of slopes, mismanagement of water drainage, unplanned residential developments, across the channel courses and within active floodplain of rivers, and lack of early warning schemes for landslide.

Real-Time Flood Monitoring System Using Raspberry PI

Flood has been a major concern for a very long time and the inability to monitor it in real-time has been a major disadvantage in maintaining a healthy hydrologic process. The main problem in monitoring flood is the amount of time taken for data to reach users and how long the data is relevant for as in monitoring flood, timing is the crucial key. This research proposes a Real-Time Flood Monitoring System that can aid in monitoring flood more efficiently. The system utilizes a set of sensors connected to a single-board computer that determines values in which is vital in monitoring flood. To ensure a fast transmission of data, the values are transferred over Wide Area Network (WAN) to host these values on a remote server. The remote server hosts these data on a website and application which is made accessible for the public with an ease of access. As a result, it can be viewed by users who wish to know the necessary values in determining danger level and further actions can be taken in ensuring their safety. Data which is transferred on real-time allow less time to be taken in order for the news to spread around as time is very crucial in saving people from natural disasters. These data also have a great importance for safety enforcement to be used in determining safety precautions that can be taken in order to ensure the safety of people around a particular area.

Image Segmentation Methods for Flood Monitoring System

Flood disasters are considered annual disasters in Malaysia due to their consistent occurrence. They are among the most dangerous disasters in the country. Lack of data during flood events is the main constraint to improving flood monitoring systems. With the rapid development of information technology, flood monitoring systems using a computer vision approach have gained attention over the last decade. Computer vision requires an image segmentation technique to understand the content of the image and to facilitate analysis. Various segmentation algorithms have been developed to improve results. This paper presents a comparative study of image segmentation techniques used in extracting water information from digital images. The segmentation methods were evaluated visually and statistically. To evaluate the segmentation methods statistically, the dice similarity coefficient and the Jaccard index were calculated to measure the similarity between the segmentation results and the ground truth images. Based on the experimental results, the hybrid technique obtained the highest values among the three methods, yielding an average of 97.70% for the dice score and 95.51% for the Jaccard index. Therefore, we concluded that the hybrid technique is a promising segmentation method compared to the others in extracting water features from digital images.

Designing Early Warning Flood Detection and Monitoring System via IoT

Flooding is one of the biggest natural disasters that occurs frequently around the world. It can occur without warning and the after effect of it leaves great damage to the surrounding environment and exposes life threatening to citizen. Therefore, early flood detection and monitoring system with the implementation of Internet of Things and Global Positioning System is proposed in order to reduce the risks that may cause flooding. The aim of this project is to provide the information of a current water level in a drain. When water level increases to a certain level, the system will send a warning notification to users indicating three categories of water level, which are safe, warning and critical level. This system contains an ultrasonic sensor to detect the current water level and at the same time allows users to observe the period of the water level from their phone so that users are more aware of when flooding ought to happen. Moreover, the system consists of a flooding avoidance method that requires the usage of a solenoid as a shutter valve of the drain and water pump to pump out excessive water flow to a suitable place for water release purposes.

An Autonomous Low-Power LoRa-Based Flood-Monitoring System

The development of Internet of Things (IoT) systems is a rapidly evolving scenario, thanks also to newly available low-power wide area network (LPWAN) technologies that are utilized for environmental monitoring purposes and to prevent potentially dangerous situations with smaller and less expensive physical structures. This paper presents the design, implementation and test results of a flood-monitoring system based on LoRa technology, tested in a real-world scenario. The entire system is designed in a modular perspective, in order to have the capability to interface different types of sensors without the need for making significant hardware changes to the proposed node architecture. The information is stored through a device equipped with sensors and a microcontroller, connected to a LoRa wireless module for sending data, which are then processed and stored through a web structure where the alarm function is implemented in case of flooding.

Flood and Notification Monitoring System using Ultrasonic Sensor Integrated with IoT and Blynk Applications: Designed for Vehicle Parking

Terengganu received heavy rainfall during the Northeast monsoon which strikes between October and March thus can leads to severe floods almost every year all over the state. The floods around Dungun area of Terengganu state was due to the combination of physical factors such as elevation and its close proximity to the sea apart from heavy rainfall received during the monsoon period. A flood warning system is designed to warn and alert the owners of the vehicle about the flood immediately. The system will detect water level through an ultrasonic sensor and will automatically send a notification via IoT technology to the owner’s smartphone through the Blynk Application. A water level sensor will be set at two points which is at 0.05m and 0.09m from ground level. When the water reaches this point, it will light on LED and trigger buzzer that acts as an alarm to alert both owner and authorities. Alerting signs of water level are notified on the Blynk application that was connected through ESP8266 Wi-Fi module via IoT teechnology.

Role of IoT devices in Flood Monitoring System using Social Networking Sites

Each country has a natural disaster, but catastrophe losses can't be avoided. The loss of human life, damage to the environment, infrastructure degradation, etc. Which in turn affects the country's development facing the disaster's wrath? In this analysis, we discuss the various methods available in the literature to reduce the losses in flood-related natural disasters. There are four major steps in the prevention of disaster losses, including preparedness, response, recovery and mitigation. Existing methods that address the above steps and all the current methods have certain limitations and are therefore not all sufficient to minimize losses due to flooding. In order to overcome all the deficiencies in the exit method, we propose an IoT devices based algorithm to get the number of victims and survivors due to flood and reduce the flood losses model using social networking sites.

Utilizing the Internet of Things (IoT) to Develop a Remotely Monitored Autonomous Floodgate for Water Management and Control

In recent years, floods have increased in frequency and intensity, causing tremendous hardship. In badly affected regions, mostly the rural areas, Weir-type floodgates are the only measure against floods. However, these manually operated gates are numerous and scattered over vast areas. This makes flood mitigation efforts very challenging, which causes severe devastation. Current solutions to automate the floodgates are expensive, black-boxed, and focused on individual gates. In this paper, we present a Centralized Flood Monitoring and Coordination System developed through the Internet of Things (IoT) and other open-source technologies. For this work, we developed a working prototype of an autonomous floodgate that opens/closes according to the level of water. We also developed the required program to allow the gate controller to publish its data through the IoT gateway to the cloud. The data was then captured and viewed on a number of IoT clients, both for individuals and groups of floodgates, in real time. The developed system proved successful as the autonomous gates were monitored remotely through the established IoT framework, with room for future development and improvement. This paper serves as a proof of concept and a preparation for real, on-site implementation of the IoT-floodgates.

A performance analysis for real-time flood monitoring using image-based processing

&lt;span style="font-size: 9pt; font-family: 'Times New Roman', serif;"&gt;Nowadays, various image-based methods have been used in the area of monitoring. Whereas the precision of detection objects and real-time processing are the key issues for many applications. Considering the limitation of the working environment, the higher correctness and faster operating time can guarantee the work efficiency. In this paper, the image-based methods have been studied to monitoring the state of the flood in the real-time system. The performance of each image processing technique has been evaluated based on accuracy and processing time. In the flood monitoring system, the variation of important parameters can cause the change of performance and the effect of the variable parameters has been demonstrated from the experiment results. After comparing to the other image-based techniques, canny edge detection presents the best one, which also has better repeatability with the source image from different locations. Consequently, the improved canny edge detection method has been proved that can work very well on the real hardware in the outdoor environment.&lt;/span&gt;

Model development of flood control system for sluice

Along with technological developments, the agricultural sector should also integrate it into agricultural systems. Problems with regulating water and monitoring the amount of water are often difficult and eventually lead to flooding. The aims of this research is to develop a model for a real time wireless flood control and monitoring system for sluice in “subak” area in Bali using the ultrasonic waves. This model development and integration is supported by the advance of electronics and information technology, have built a system which can automatically sense the water level at a sluice and then send these values to the control circuit through connecting cable. The ultrasonic module HC - SR04 is used as a distance sensor for detecting water level by measuring distance between sensor and water surfaces. This sensor placed above the sluice gate and gives electric input to the sluice drive electric motor. This model also equipped with LCD screen to displays the measurement data. Then depending on the measurements, the LCD screen show that the current status of water level in the sluice. The result of this research shows good agreement for the application of ultrasonic waves device for flood controlling and monitoring system for sluice.

Smart IoT Flood Monitoring System

Flood is one of the natural disasters that cannot be avoided. It happens too fast and affected so many lives and properties. Before this, most of the existing system that has been developed are only focus on certain areas. Other than that, majority of the public cannot monitor and have no idea when the flood going to be happened since they do not have any information and data about the weather condition. By having Smart IoT Flood Monitoring System, this will solve all the drawbacks of the existing system. The proposed system is suitable for cities and village areas. Furthermore, if the public has an internet access, they can monitor what is happening and predict if there is any upcoming flood at the web server. The proposed system is a low cost in design and easy for maintenance. This project will update the water level at the web server and the system will issue an alert signal to the citizens for evacuation so that fast necessary actions can be taken.

A Literature survey on Internet of Things based Flood Detection and Monitoring System Using Raspberry Pi

A Literature survey on Internet of Things based Flood Detection and Monitoring System Using Raspberry Pi

Applicability of HEC-RAS 2D and GFMS for flood extent mapping: a case study of Sangam area, Prayagraj, India

Catastrophic floods cause losses to millions of lives and property damages every year. The situation is more precarious particularly in countries lacking advanced tools and early warning systems for quick disaster management and mitigation. This article presents a study conducted to develop and understand methodology for delineation of flood extent and identification of various flood risk zones in Prayagraj, India at the confluence of River Ganga and Yamuna (sangam). In this study, a well-established hydraulic model (HEC-RAS 5.0.7 (2D)) and Global Flood Monitoring System (GFMS) tools were utilized. The methodology solves two glitches related to flood studies, i.e., capability of HEC-RAS 2D flood model and GFMS discharge for 1D and 2D flood modeling and secondly using the output of the model, development of a methodology for the identification of various flood risk zones. The modeled and observed data were in close agreement indicating a successful application of HEC-RAS and GFSM data/tools. Using the methodology of this study, various flood modeling and delineation of risk zones can be made for various flood-affected areas in India and worldwide. These tools can also be used for making guidelines for emergency response in flood-affected areas.

Flood Warning and Monitoring System Utilizing Internet of Things Technology

Flooding is one of the major disasters occurring in various parts of the world including Malaysia. To reduce the effect of the disaster, a flood warning and monitoring are needed to give an early warning to the victims at certain place with high prone to flood. By implementing Internet of Thing technology into the system, it could help the victim to get an accurate status of flood in real-time condition. This paper is develop a real-time flood monitoring and early warning system using wireless sensor node at a high prone area of flood. This system is based on NodeMCU based technology integrated using Blynk application. The wireless sensor node can help the victims by detecting the water levels and rain intensity while giving an early warning when a flood or heavy rain occurs. Basically, the sensor node consists of ultrasonic sensor and rain sensor controlled by NodeMCU as the microcontroller of the system which placed at the identified flood area. Buzzer and LED started to trigger and alert the victim when the flood had reached certain level of hazard. Data detected from the sensors are sent to the Blynk application via wireless connection. Victim will get to know the current status of flood and rain by viewing the interface and receiving push notification that available in Blynk application via IOS or Android smartphones. The flood level’s data sent to the email could help various organizations for further improvement of the system and flood forecasting purposes. After a test had been conducted, it was found that this prototype can monitor, detect and give warning with notification to the victim earlier before the occurrence of floods.

Implementation of GSM Communication on Flood Monitoring Systems Based on Multiple Locations Visualization

Flooding is one of the national disaster tragedies that currently often occurs in various countries. Therefore the government encourages various government, private and community institutions to develop disaster mitigation systems. Disaster mitigation systems are short-term programs aimed at reducing disaster victims. Therefore, this paper aims to describe the results of research in building flood monitoring information systems by developing flood data visualization systems in many locations. The system as a whole consists of two systems namely a flood detection system as a client and a flood monitoring information system as a server. the two systems communicate in sending flood data using GSM services, namely SMS. Flood detection systems are designed using ultrasonic sensors, temperature sensors, rain sensors, Arduino Uno microcontrollers and GSM modules. While the flood monitoring information system server was designed using a GSM modem, web server application, mySQL database, PHP engine and Gammu. The results showed that the flood detection system can send flood data consisting of flood locations, water levels, temperatures and rain conditions to the flood monitoring information system using SMS. SMS data received can already be converted by a flood monitoring information system server to a flood visualization-based interface for many locations in real time.

Evaluation of real-time global flood modeling with satellite surface inundation observations from SMAP

Improving flood modeling accuracy is crucial for real-time flood monitoring and early warning systems. Knowing the sources, patterns and driving factors of model uncertainty aids the development of more accurate flood predictions. This study investigates the consistency of two global flood inundation products, i.e., the Soil Moisture Active Passive (SMAP) satellite based fractional water (Fw) cover and the Global Flood Monitoring System (GFMS) modeled flood inundation. Using Pearson's correlation coefficient (r) as the indicator of the SMAP-GFMS model consistency, this research documents the spatial and temporal patterns of the correlations between the two flood products, and investigates factors affecting these relationships, including climate, land cover, hydrology and terrain distributions. Results reveal that globally, 64% locations have moderate to strong SMAP-GFMS correlation (r ≥ 0.4). Locations that are dry and have low biomass and high seasonal flood variability tend to have high correlation; for example, 47% locations with r ≥ 0.4 occur in tropical and arid climate zones, and 43% locations with r ≥ 0.4 are observed in Barren, Evergreen Broadleaf Forest, Grasslands, Open Shrubland and Savannahs. Also, larger rivers have higher correlation, and in each Strahler stream order there are 60% to 65% locations having r ≥ 0.4. Larger watersheds show higher SMAP-GFMS consistency in particular watersheds between 1000 and 40,000 km2. Regions with greater urban infrastructure tend to have lower correlation, while locations with lower elevations and relatively flat topography have higher SMAP-GFMS consistency. This study indicates that GFMS and SMAP provide complementary information on surface water storage variations influencing precipitation driven runoff and flooding, which may enable enhanced global flood predictions.