Development of a predictive model for on-demand remote river level nowcasting: Case study in Cagayan River Basin, Philippines

Garcia, Felan Carlo C.; Retamar, Alvin E.; Javier, Joven C.

doi:10.1109/tencon.2016.7848657

Cited by 9 publications

(4 citation statements)

References 6 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Previously, GPRS technology was the most used for the implementation of wireless networks for rainfall monitoring. In ( Garcia et al., 2016 ), a real-time urban flood monitoring system was deployed using the GPRS network in Bulevar España, Manila, Philippines. The system's stations were composed of a soil pressure sensor and a rain gauge connected to a data logger.…”

Section: Review Of Related Workmentioning

confidence: 99%

Communication protocols evaluation for a wireless rainfall monitoring network in an urban area

Ortega-Gonzalez

Acosta-Coll

Piñeres-Espitia

et al. 2021

Heliyon

View full text Add to dashboard Cite

Rainfall monitoring networks are key elements for the development of alerts and prediction models for communities at risk of flooding during high intensity rainfall events. Currently, most of these networks send the precipitation measurement to a data center in real-time using wireless communication protocols, avoiding travel to the measurement site. An Early Warning System (EWS) for pluvial flash floods developed in Barranquilla (Colombia), used the GPRS protocol to send rain gauge data in real-time to a web server for further processing; however, this protocol has a high consumption of energy and also high maintenance costs. This article carried out an evaluation in terms of link budget, link profile, energy consumption and devices costs of three low-power wireless communication protocols, Zigbee, LoRaWAN and Sigfox, to determine which one is the most suitable for the EWS of the city of Barranquilla. To perform the evaluation, a wireless sensor network was designed and characterized for Zigbee and LoRaWAN with Radio Mobile tool taking into account the measurement points implemented with GPRS network. The evaluation included the power consumption of Zigbee, LoRaWAN and Sigfox. From the results of simulations, LoRaWAN and Zigbee network has similar radio signal received and the LoRaWAN network obtains the least losses per path. As for power consumption, the LoRaWAN devices has the lowest energy consumption, as well as, the LoRaWAN network sensor nodes are cheaper. Finally, the protocol with the best general performance was LoRAWAN, since complies with the communication, consumption and cost requirements.

show abstract

Section: Review Of Related Workmentioning

confidence: 99%

Communication protocols evaluation for a wireless rainfall monitoring network in an urban area

Ortega-Gonzalez

Acosta-Coll

Piñeres-Espitia

et al. 2021

Heliyon

View full text Add to dashboard Cite

show abstract

“…The government of the Philippines deployed more than 1,500 hydro-meteorological stations nationwide to provide real-time data for rain and flood event monitoring using two primary sensors, an [17]. For the Cagayan river basin, the Department of Science and Technology (DOST) and the Advanced Science and Technology Institute (DOST-ASTI) developed a predictive model based on the random forest algorithm to provide timely warnings of water level and flood hazard and it becomes in a decision support tool for the local communities.…”

Section: Fluvial Floods Early Warning System Architectures 311 Cagayan River Basin Philippinesmentioning

confidence: 99%

Forecasting and communication key elements for low-cost fluvial flooding early warning system in urban areas

Acosta-Coll

Solano-Escorcia

Ortega-Gonzalez

et al. 2021

IJECE

View full text Add to dashboard Cite

Fluvial flooding occurs when a river overspills its banks due to excessive rainfall, and it is the most common flood event. In urban areas, the increment of urbanization makes communities more susceptible to fluvial flooding since the excess of impervious surfaces reduced the natural permeable areas. As flood prevention strategies, early warning systems (EWS) are used to reduce damage and protect people, but key elements need to be selected. This manuscript proposes the monitoring instruments, communication protocols, and media to forecast and disseminate EWS alerts efficiently during fluvial floods in urban areas. First, we conducted a systematic review of different EWS architectures for fluvial floods in urban areas and identified that not all projects monitor the most important variables related to the formation of fluvial floods and most use communication protocols with high-energy consumption. ZigBee and LoRaWAN are the communication protocols with lower power consumption from the review, and to determine which technology has better performance in urban areas, two wireless sensor networks were deployed and simulated in two urban areas susceptible to fluvial floods using Radio Mobile software. The results showed that although Zigbee technology has better-received signal strength, the difference with LoRAWAN is lower than 2 dBm, but LoRaWAN has a better signal-to-noise ratio, power consumption, coverage, and deployment cost.

show abstract

“…The Random Forest algorithm process as shown below, Random Forest works by building decision trees from a bootstrapped sample taken from a training set. This process is repeated B several times where B is the desired number of trees generated for the forest [6], [7]. During the construction of a tree, a node is split based on the best among the random subset of the features Algorithm: Random Forest Decision Tree Input: Let X be the training data consisting of L variable feature vectors.…”

Section: Training and Testmentioning

confidence: 99%

Predicting River Pollution Using Random Forest Decision Tree with GIS Model: A Case Study of MMORS, Philippines

Victoriano¹,

Lacatan²,

Vinluan³

2020

IJESD

View full text Add to dashboard Cite

This study aims to predict the pollution level that threatens the Marilao-Meycauayan-Obando River System (MMORS), located in the province of Bulacan, Philippines. The inhabitants of this area are now being exposed to pollution. Contamination of this waterway comes from both formal and informal industries, such as a used lead-acid battery, open dumpsites metal refining, and other toxic metals. Using various water quality parameters like Dissolved Oxygen (DO), Potential of Hydrogen (pH), Biochemical Oxygen Demand (BOD), Total Suspended Solids (TSS), Nitrate, Phosphate, and Coliform are the basis for predicting the pollution level. Base on the sample data collected from January 2013 to May 2018. These are used as a training data and test results to predict the river condition with its corresponding pollution level classification indicated. Random Forest decision tree model got an accuracy of 99.38% with a Kappa value of 0.8303 interpreted as "Strong" in terms of the level of agreement and GIS model shows the heat map of the different water quality parameter and Water Quality Index (WQI) spatial distribution, the majority of the sampling station are greatly polluted provided that they have "Poor" and "Very Poor." Index Terms-Machine learning, river pollution, random forest and GIS.

show abstract

Development of a predictive model for on-demand remote river level nowcasting: Case study in Cagayan River Basin, Philippines

Cited by 9 publications

References 6 publications

Communication protocols evaluation for a wireless rainfall monitoring network in an urban area

Communication protocols evaluation for a wireless rainfall monitoring network in an urban area

Forecasting and communication key elements for low-cost fluvial flooding early warning system in urban areas

Predicting River Pollution Using Random Forest Decision Tree with GIS Model: A Case Study of MMORS, Philippines

Contact Info

Product

Resources

About