4.7 Article

Flash-flood hazard using deep learning based on H2O R package and fuzzy-multicriteria decision-making analysis

Related references

Note: Only part of the references are listed.
Article Computer Science, Interdisciplinary Applications

Proposing two new metaheuristic algorithms of ALO-MLP and SHO-MLP in predicting bearing capacity of circular footing located on horizontal multilayer soil

Wensheng Liu et al.

Summary: This study utilized artificial neural networks and two metaheuristic algorithms to optimize the prediction of shallow circular footing's bearing capacity. It demonstrated higher reliability in estimating load-bearing capacity using the SHO-MLP hybrid model.

ENGINEERING WITH COMPUTERS (2021)

Article Environmental Sciences

Optimization of state-of-the-art fuzzy-metaheuristic ANFIS-based machine learning models for flood susceptibility prediction mapping in the Middle Ganga Plain, India

Aman Arora et al.

Summary: This study tested and compared novel advanced-machine learning algorithms in predicting flood susceptible areas in a low-altitude, sub-tropical floodplain environment in the Middle Ganga Plain, India. The ANFIS-GA model outperformed other models with the highest success rate and prediction rate, suggesting further study in similar environments for establishing a benchmark model with highest accuracy and sensitivity.

SCIENCE OF THE TOTAL ENVIRONMENT (2021)

Article Multidisciplinary Sciences

A GIS based flood vulnerability modelling of Anambra State using an integrated IVFRN-DEMATEL-ANP model

E. C. Chukwuma et al.

Summary: Flooding is a major environmental issue in Anambra State, Nigeria, affecting food security. Employing IVFRN, DEMATEL, and ANP methods in vulnerability assessment showed the state's high vulnerability to floods, with rainfall intensity being the major cause. The study validates the model's accuracy and recommends prioritizing drainage systems and geospatial-based planning for flood mitigation.

HELIYON (2021)

Article Engineering, Civil

Can deep learning algorithms outperform benchmark machine learning algorithms in flood susceptibility modeling?

Binh Thai Pham et al.

Summary: This paper introduces a new deep learning algorithm DEBP for flood susceptibility mapping in the Vu Gia-Thu Bon watershed. The DEBP model shows promise with the highest goodness-of-fit and prediction accuracy among tested models, indicating its potential as a tool for flood susceptibility modeling.

JOURNAL OF HYDROLOGY (2021)

Article Engineering, Civil

A novel hybrid quantum-PSO and credal decision tree ensemble for tropical cyclone induced flash flood susceptibility mapping with geospatial data

Phuong-Thao Thi Ngo et al.

Summary: Flash floods are considered highly destructive worldwide, especially in tropical countries, leading to the development of a new model called QPSO-CDTreeEns for spatial prediction of flash floods. This model combines Quantum Particle Swarm Optimization and the Credal Decision Tree ensemble to optimize parameters and outperform existing machine learning algorithms in flash flood susceptibility mapping. The proposed model shows promise for sustainable land-use planning and disaster mitigation strategies.

JOURNAL OF HYDROLOGY (2021)

Article Environmental Sciences

Flood susceptibility mapping and assessment using a novel deep learning model combining multilayer perceptron and autoencoder neural networks

Mohammad Ahmadlou et al.

Summary: Floods are one of the most destructive natural disasters globally, and researchers have been using data-driven techniques combined with remote sensing and geographic information systems for flood susceptibility mapping. A novel hybrid autoencoder-MLP model was proposed, which outperformed the traditional MLP model according to the AUROC criterion.

JOURNAL OF FLOOD RISK MANAGEMENT (2021)

Article Geosciences, Multidisciplinary

Deep learning neural networks for spatially explicit prediction of flash flood probability

Mahdi Panahi et al.

Summary: This study presents the potential application of deep learning neural networks, specifically CNN and RNN, for predicting and mapping flash flood probability in Golestan Province, Iran. The CNN model performed slightly better than the RNN model in predicting future floods, demonstrating improved accuracy compared to previous studies. The study suggests focusing on approximately 40% of the land area identified as highly susceptible to flooding for the design and implementation of flood early warning systems.

GEOSCIENCE FRONTIERS (2021)

Article Environmental Sciences

Integrated Framework for Detecting the Areas Prone to Flooding Generated by Flash-Floods in Small River Catchments

Romulus Costache et al.

Summary: The study examined the susceptibility to flash-floods and flooding in the Izvorul Dorului River basin in Romania using ensemble models. The FAHP-WOE model demonstrated the best performance, identifying areas with medium, high, and very high torrential susceptibility, as well as estimating flood susceptibility. Approximately 25% of the total delimited area was found to have high and very high flood susceptibility.

WATER (2021)

Article Environmental Sciences

Hybrid Models Incorporating Bivariate Statistics and Machine Learning Methods for Flash Flood Susceptibility Assessment Based on Remote Sensing Datasets

Jun Liu et al.

Summary: This study proposed three hybrid models for flood susceptibility prediction, with the CNN-FMV model showing the best performance. These models have the potential for application in specific areas for future flood susceptibility assessment.

REMOTE SENSING (2021)

Article Geosciences, Multidisciplinary

Evaluating urban flood risk using hybrid method of TOPSIS and machine learning

Elham Rafiei-Sardooi et al.

Summary: This study evaluates flood risk in Jiroft city, Iran using a combination of machine learning and decision-making methods. The random forest model produced the most accurate map, with urban drainage density and distance to urban drainages identified as key factors in urban flood hazard modeling. Areas with high population density are most vulnerable to flooding.

INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION (2021)

Article Engineering, Civil

Predicting flood susceptibility using LSTM neural networks

Zhice Fang et al.

Summary: The proposed LSS-LSTM method for flood susceptibility prediction, integrating appropriate feature engineering methods and optimization techniques, achieves satisfactory prediction performance by capturing both the attribution information of flood conditioning factors and the local spatial information of flood data, as well as having powerful sequential modeling capabilities.

JOURNAL OF HYDROLOGY (2021)

Article Geosciences, Multidisciplinary

Flood Susceptibility Modeling in a Subtropical Humid Low-Relief Alluvial Plain Environment: Application of Novel Ensemble Machine Learning Approach

Manish Pandey et al.

Summary: This study developed and tested two ensemble models for flood susceptibility mapping in the Middle Ganga Plain, with one model performing better than the other. The results are important for natural hazard managers and can be used for damage computation through risk analysis.

FRONTIERS IN EARTH SCIENCE (2021)

Article Geosciences, Multidisciplinary

Improved flood susceptibility mapping using a best first decision tree integrated with ensemble learning techniques

Binh Thai Pham et al.

Summary: Enhancing accuracy in flood prediction and mapping is essential for minimizing flood damage. This study introduced and validated three ensemble models utilizing BFT, with the Decorate-BFT model showing superior performance in predicting flood susceptibility.

GEOSCIENCE FRONTIERS (2021)

Article Environmental Sciences

Prediction of the sorption efficiency of heavy metal onto biochar using a robust combination of fuzzy C-means clustering and back-propagation neural network

Bo Ke et al.

Summary: The FCM-BPNN model showed promising results in predicting the sorption efficiency of heavy metals onto biochar, outperforming the BPNN model alone. The FCM algorithm significantly improved the performance of the BPNN model in this study.

JOURNAL OF ENVIRONMENTAL MANAGEMENT (2021)

Article Environmental Sciences

Flood susceptibility mapping by integrating frequency ratio and index of entropy with multilayer perceptron and classification and regression tree

Yi Wang et al.

Summary: The study integrated multiple models and techniques to evaluate flood susceptibility in Poyang County, China, and found that elevation, slope angle, and soil play important roles in flood prediction. The experimental results showed that between 20% and 50% of the study area has high and very high flood susceptibility, with the multilayer perceptron-probability density hybrid model being the most effective.

JOURNAL OF ENVIRONMENTAL MANAGEMENT (2021)

Article Engineering, Civil

Exploring the utility of radar and satellite-sensed precipitation and their dynamic bias correction for integrated prediction of flood and landslide hazards

Sheng Wang et al.

Summary: The study demonstrates that bias correction methods for radar and satellite QPE can significantly improve the accuracy of predicting floods and landslides. A correction time interval of 24 hours is found to achieve optimal results in the bias correction process. Both gauge density and spatial resolution impact the accuracy of bias correction methods, but even a small number of rain gauge observations can help reduce uncertainty in radar and satellite QPE.

JOURNAL OF HYDROLOGY (2021)

Article Multidisciplinary Sciences

Long-term vegetation restoration increases deep soil carbon storage in the Northern Loess Plateau

Zhilong Lan et al.

Summary: Afforestation plays a vital role in soil carbon storage and water balance, particularly in regions like the Chinese Loess Plateau. This study found that converting farmland back to forests can increase soil organic carbon storage and decrease soil water consumption. However, further research is needed to fully understand the interactions between deep soil water and carbon in the context of ecological restoration sustainability in the Northern Loess Plateau.

SCIENTIFIC REPORTS (2021)

Article Environmental Sciences

Drought Monitoring over Yellow River Basin from 2003-2019 Using Reconstructed MODIS Land Surface Temperature in Google Earth Engine

Xiaoyang Zhao et al.

Summary: This study used remote sensing technology and meteorological data to analyze drought conditions in the Yellow River Basin. The results show that reconstructed temperature and vegetation indices can improve the accuracy of drought monitoring, different drought indices show consistency in spatial and temporal patterns but differences in some local areas, and drought level in the Yellow River Basin is highest in the northwest and lowest in the southwest and southeast, remaining stable from 2003 to 2019.

REMOTE SENSING (2021)

Article Environmental Sciences

A Comprehensive Evaluation of Five Evapotranspiration Datasets Based on Ground and GRACE Satellite Observations: Implications for Improvement of Evapotranspiration Retrieval Algorithm

Lijun Chao et al.

Summary: The study compared the performance of five typical remote sensing evapotranspiration datasets and found that P-LSH and GLEAM performed the best at the annual scale, P-LSH outperformed the other four datasets at the seasonal scale, while MTE and PML showed higher accuracy in arid regions. MODIS and MTE tended to underestimate and overestimate ET values during estimation.

REMOTE SENSING (2021)

Article Environmental Sciences

Flash Flood Susceptibility Assessment and Zonation Using an Integrating Analytic Hierarchy Process and Frequency Ratio Model for the Chitral District, Khyber Pakhtunkhwa, Pakistan

Hassan Waqas et al.

Summary: The study generated a flash flood map in Pakistan's Chitral District using AHP and FR models, identifying high-risk zones and providing policy guidelines for various stakeholders.

WATER (2021)

Article Engineering, Civil

Flood susceptibility mapping using convolutional neural network frameworks

Yi Wang et al.

JOURNAL OF HYDROLOGY (2020)

Article Telecommunications

Multi-Branch Deep Residual Learning for Clustering and Beamforming in User-Centric Network

Yuan He et al.

IEEE COMMUNICATIONS LETTERS (2020)

Article Environmental Sciences

Comparison of bathymetric data sources used in hydraulic modelling of floods

Ludek Bures et al.

JOURNAL OF FLOOD RISK MANAGEMENT (2019)

Article Computer Science, Information Systems

A GIS-Based Support Vector Machine Model for Flash Flood Vulnerability Assessment and Mapping in China

Junnan Xiong et al.

ISPRS INTERNATIONAL JOURNAL OF GEO-INFORMATION (2019)

Article Green & Sustainable Science & Technology

Prediction Success of Machine Learning Methods for Flash Flood Susceptibility Mapping in the Tafresh Watershed, Iran

Saeid Janizadeh et al.

SUSTAINABILITY (2019)

Article Geosciences, Multidisciplinary

Characteristics and influencing factors of rainfall-induced landslide and debris flow hazards in Shaanxi Province, China

Ke Zhang et al.

NATURAL HAZARDS AND EARTH SYSTEM SCIENCES (2019)

Review Computer Science, Interdisciplinary Applications

Relief-based feature selection: Introduction and review

Ryan J. Urbanowicz et al.

JOURNAL OF BIOMEDICAL INFORMATICS (2018)

Article Geosciences, Multidisciplinary

Modified Flash Flood Potential Index in order to estimate areas with predisposition to water accumulation

Roxana Tincu et al.

OPEN GEOSCIENCES (2018)

Article Geosciences, Multidisciplinary

Rainfall-runoff modelling using Long Short-Term Memory (LSTM) networks

Frederik Kratzert et al.

HYDROLOGY AND EARTH SYSTEM SCIENCES (2018)

Article Geography

Historic flood events in NE Romania (post-1990)

Gheorghe Romanescu et al.

JOURNAL OF MAPS (2017)

Article Automation & Control Systems

Deep feature weighting for naive Bayes and its application to text classification

Liangxiao Jiang et al.

ENGINEERING APPLICATIONS OF ARTIFICIAL INTELLIGENCE (2016)

Article Geosciences, Multidisciplinary

Flood susceptibility assessment using GIS-based support vector machine model with different kernel types

Mahyat Shafapour Tehrany et al.

CATENA (2015)

Article Geosciences, Multidisciplinary

Assessment and mapping of flood potential in the Slănic catchment in Romania

LILIANA ZAHARIA et al.

Journal of Earth System Science (2015)

Article Geosciences, Multidisciplinary

PROMETHEE II and fuzzy AHP: an enhanced GIS-based landslide susceptibility mapping

Majid Shadman Roodposhti et al.

NATURAL HAZARDS (2014)

Article Engineering, Civil

Curve Number Determination Methods and Uncertainty in Hydrologic Soil Groups from Semiarid Watershed Data

Dave Stewart et al.

JOURNAL OF HYDROLOGIC ENGINEERING (2012)

Article Engineering, Multidisciplinary

Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naive Bayes Models

Dieu Tien Bui et al.

MATHEMATICAL PROBLEMS IN ENGINEERING (2012)

Article Environmental Sciences

Flash flood forecasting, warning and risk management: the HYDRATE project

M. Borga et al.

ENVIRONMENTAL SCIENCE & POLICY (2011)

Article Computer Science, Artificial Intelligence

A performance evaluation model by integrating fuzzy AHP and fuzzy TOPSIS methods

Chia-Chi Sun

EXPERT SYSTEMS WITH APPLICATIONS (2010)

Article Water Resources

Modelling the impact of urbanization on flood frequency relationships in the UK

Thomas R. Kjeldsen

HYDROLOGY RESEARCH (2010)