A Review of Flood Mitigation Literature: A Case Study of Sidoarjo Regency, Indonesia DOI Creative Commons

Fifiet Koerniawan,

Muhammad Ikhsan Setiawan, Grida Saktian Laksito

et al.

International Journal of Industrial Engineering Technology & Operations Management, Journal Year: 2023, Volume and Issue: 1(2), P. 73 - 79

Published: Dec. 31, 2023

Sidoarjo is a buffer city in Surabaya and comfortable livable city. To become city, needs several life-supporting infrastructures, including drainage infrastructure. A system that managed maintained properly can carry out its functions optimally. But of course, many housing developments do not pay attention to the system, which cause problems such as flooding. Floods are most frequent natural disasters Indonesia. Flooding situation where an area inundated with large amounts water. The occurrence floods be predicted by paying amount rainfall water discharge. However, strong winds or leaking embankments sudden usually called flash floods. causes flooding include heavy rain. earth's surface lower than sea level. This delta has low absorption capacity. Construction buildings along riverbanks. river flow uneven because it blocked rubbish lack land cover upstream areas. Even if you live flood-free area, everyone should aware potential for this disaster. release relatively larger usual, resulting overflowing fills inundates low-lying

Language: Английский

Assessment of surrogate models for flood inundation: The physics-guided LSG model vs. state-of-the-art machine learning models DOI Creative Commons
Niels Fraehr, Quan J. Wang, Wenyan Wu

et al.

Water Research, Journal Year: 2024, Volume and Issue: 252, P. 121202 - 121202

Published: Jan. 24, 2024

Hydrodynamic models can accurately simulate flood inundation but are limited by their high computational demand that scales non-linearly with model complexity, resolution, and domain size. Therefore, it is often not feasible to use high-resolution hydrodynamic for real-time predictions or when a large number of needed probabilistic design. Computationally efficient surrogate have been developed address this issue. The recently Low-fidelity, Spatial analysis, Gaussian Process Learning (LSG) has shown strong performance in both efficiency simulation accuracy. LSG physics-guided simulates first using an extremely coarse simplified (i.e. low-fidelity) provide initial estimate inundation. Then, the low-fidelity upskilled via Empirical Orthogonal Functions (EOF) analysis Sparse accurate predictions. Despite promising results achieved thus far, benchmarked against other models. Such comparison fully understand value guidance future research efforts simulation. This study compares four state-of-the-art assessed ability temporal spatial evolution events within beyond range used training. evaluated three distinct case studies Australia United Kingdom. found be superior accuracy extent water depth, including applied outside training data used, while achieving efficiency. In addition, play crucial role overall model.

Language: Английский

Citations

31
Forecasting Multi-Step-Ahead Street-Scale nuisance flooding using seq2seq LSTM surrogate model for Real-Time applications in a Coastal-Urban city DOI Creative Commons
Binata Roy, Jonathan L. Goodall, Diana McSpadden

et al.

Journal of Hydrology, Journal Year: 2025, Volume and Issue: unknown, P. 132697 - 132697

Published: Jan. 1, 2025

Language: Английский

Citations

6
Flood Forecasting by Using Machine Learning: A Study Leveraging Historic Climatic Records of Bangladesh DOI Open Access
Adel Rajab, Hira Farman, Noman Islam

et al.

Water, Journal Year: 2023, Volume and Issue: 15(22), P. 3970 - 3970

Published: Nov. 15, 2023

Forecasting rainfall is crucial to the well-being of individuals and significant everywhere in world. It contributes reducing disastrous effects floods on agriculture, human life, socioeconomic systems. This study discusses challenges effectively forecasting necessity combining data with flood channel mathematical modelling forecast floodwater levels velocities. research focuses leveraging historical meteorological find trends using machine learning deep approaches estimate rainfall. The Bangladesh Meteorological Department provided for study, which also uses eight algorithms. performance models examined evaluation measures like R2 score, root mean squared error validation loss. According this research’s findings, polynomial regression, random forest long short-term memory (LSTM) had highest levels. Random regression have an value 0.76, while LSTM has a loss 0.09, respectively.

Language: Английский

Citations

40
How effective is twitter (X) social media data for urban flood management? DOI
Shan‐e‐hyder Soomro, Muhammad Waseem Boota, Haider M. Zwain

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 634, P. 131129 - 131129

Published: March 28, 2024

Language: Английский

Citations

11
A Systematic Literature Review on Classification Machine Learning for Urban Flood Hazard Mapping DOI
Maelaynayn El Baida,

Mohamed Hosni,

Farid Boushaba

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(15), P. 5823 - 5864

Published: Aug. 3, 2024

Language: Английский

Citations

5
Use of Artificial Intelligence Modelling for the Dynamic Simulation of Urban Catchment Runoff DOI Creative Commons
Harshanth Balacumaresan, Monzur Alam Imteaz, Md. Abdul Aziz

et al.

Water Resources Management, Journal Year: 2024, Volume and Issue: 38(10), P. 3657 - 3683

Published: April 2, 2024

Abstract The complex topography and inherent nonlinearity affiliated with influential hydrological processes of urban catchments, coupled limited availability measured data, limits the prediction accuracy conventional models. Artificial Neural Network models (ANNs) have displayed commendable progress in recognising simulating highly complex, non-linear associations allied input-output variables, comprehension underlying physical processes. Therefore, this paper investigates effectiveness ANN models, estimating catchment runoff, employing minimal commonly available data variables – rainfall upstream flow two powerful supervised-learning-algorithms, Bayesian-Regularization (BR) Levenberg-Marquardt (LM). Gardiners Creek catchment, encompassed Melbourne, Australia, more than thirty years quality-checked streamflow was chosen as study location. Two significant storm events that transpired within last fifteen - 4th February 2011 6th November 2018, were nominated for calibration validation model. results advocate use LM-ANN model stipulates accurate estimates historical events, a stronger correlation lower generalisation error, contrast to BR-ANN model, while integration alongside rainfall, vindicate their collective impact upon dynamics being spawned at downstream locations, significantly enhancing performance providing cost-effective near-realistic modelling approach can be considered application studies responses, availability.

Language: Английский

Citations

4
Utilizing sequential modeling in collaborative method for flood forecasting DOI
Wandee Thaisiam, Konlawat Yomwilai, Papis Wongchaisuwat

et al.

Journal of Hydrology, Journal Year: 2024, Volume and Issue: 636, P. 131290 - 131290

Published: May 9, 2024

Language: Английский

Citations

4
Empowering flood preparedness: Enhancing flood knowledge, risk perception, and preparedness among primary school learners in flood-affected southern Thailand DOI Creative Commons
Mujalin Intaramuean, Atsuko Nonomura, Tum Boonrod

et al.

Progress in Disaster Science, Journal Year: 2025, Volume and Issue: unknown, P. 100410 - 100410

Published: Feb. 1, 2025

Language: Английский

Citations

0
Sensor Fusion Enhances Anomaly Detection in a Flood Forecasting System DOI Creative Commons

Andrew Ma,

Abhir Karande,

Natalie Dahlquist

et al.

Journal of Sensor and Actuator Networks, Journal Year: 2025, Volume and Issue: 14(2), P. 34 - 34

Published: March 25, 2025

To build an Internet of Things (IoT) infrastructure that provides flood susceptibility forecasts for granular geographic levels, extensive network IoT weather sensors in local regions is crucial. However, these devices may exhibit anomalistic behavior due to factors such as diminished signal strength, physical disturbance, low battery life, and more. ensure incorrect readings are identified addressed appropriately, we devise a novel method multi-stream sensor data verification anomaly detection. Our uses time-series detection identify readings. We expand on the state-of-the-art by incorporating fusion mechanisms between nearby improve ability. system pairs fuses them creating new time series with difference corresponding This then input into model which identifies if any anomalistic. By testing our nine different machine learning methods synthetic based one year real data, find outperforms previous improving F1-Score 10.8%.

Language: Английский

Citations

0
Data quality and uncertainty issues in flood prediction: a systematic review DOI Creative Commons
Jinhui Yu, Yichen Li, Xiao Huang

et al.

International Journal of Digital Earth, Journal Year: 2025, Volume and Issue: 18(1)

Published: April 24, 2025

Language: Английский

Citations

0