A Brief Review of Random Forests for Water Scientists and Practitioners and Their Recent History in Water Resources

Water, Journal Year: 2019, Volume and Issue: 11(5), P. 910 - 910

Published: April 30, 2019

Random forests (RF) is a supervised machine learning algorithm, which has recently started to gain prominence in water resources applications. However, existing applications are generally restricted the implementation of Breiman’s original algorithm for regression and classification problems, while numerous developments could be also useful solving diverse practical problems sector. Here we popularize RF their variants practicing scientist, discuss related concepts techniques, have received less attention from science hydrologic communities. In doing so, review resources, highlight potential its variants, assess degree exploitation range Relevant implementations random forests, as well techniques R programming language, covered.

Language: Английский

---

Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan

The Science of The Total Environment, Journal Year: 2019, Volume and Issue: 662, P. 332 - 346

Published: Jan. 21, 2019

Language: Английский

---

Flood Prediction Using Machine Learning Models: Literature Review

Water, Journal Year: 2018, Volume and Issue: 10(11), P. 1536 - 1536

Published: Oct. 27, 2018

Floods are among the most destructive natural disasters, which highly complex to model. The research on advancement of flood prediction models contributed risk reduction, policy suggestion, minimization loss human life, and reduction property damage associated with floods. To mimic mathematical expressions physical processes floods, during past two decades, machine learning (ML) methods in systems providing better performance cost-effective solutions. Due vast benefits potential ML, its popularity dramatically increased hydrologists. Researchers through introducing novel ML hybridizing existing ones aim at discovering more accurate efficient models. main contribution this paper is demonstrate state art give insight into suitable In paper, literature where were benchmarked a qualitative analysis robustness, accuracy, effectiveness, speed particularly investigated provide an extensive overview various algorithms used field. comparison presents in-depth understanding different techniques within framework comprehensive evaluation discussion. As result, introduces promising for both long-term short-term Furthermore, major trends improving quality investigated. Among them, hybridization, data decomposition, algorithm ensemble, model optimization reported as effective strategies improvement methods.

Language: Английский

---

Flood susceptibility assessment in Hengfeng area coupling adaptive neuro-fuzzy inference system with genetic algorithm and differential evolution

The Science of The Total Environment, Journal Year: 2018, Volume and Issue: 621, P. 1124 - 1141

Published: Feb. 2, 2018

Language: Английский

---

Urban flood risk mapping using the GARP and QUEST models: A comparative study of machine learning techniques

Journal of Hydrology, Journal Year: 2018, Volume and Issue: 569, P. 142 - 154

Published: Dec. 5, 2018

Language: Английский

---

Urban flooding risk assessment based on an integrated k-means cluster algorithm and improved entropy weight method in the region of Haikou, China

Journal of Hydrology, Journal Year: 2018, Volume and Issue: 563, P. 975 - 986

Published: June 26, 2018

Language: Английский

---

Spatial prediction of flood susceptibility using random-forest and boosted-tree models in Seoul metropolitan city, Korea

Geomatics Natural Hazards and Risk, Journal Year: 2017, Volume and Issue: 8(2), P. 1185 - 1203

Published: April 10, 2017

Since flood frequency increases with the impact of climate change, damage that is emphasized on flood-risk maps based actual flooded area data; therefore, flood-susceptibility for Seoul metropolitan area, which random-forest and boosted-tree models are used in a geographic information system (GIS) environment, created this study. For mapping, flooded-area, topography, geology, soil land-use datasets were collected entered into spatial datasets. From datasets, 12 factors calculated extracted as input data models. The 2010 was to train model, 2011 validation. importance lastly, validated. As result, distance from river, geology digital elevation model showed high among factors. validation accuracies 78.78% 79.18% regression classification algorithms, respectively, 77.55% 77.26% respectively. provide meaningful decision-makers regarding identification priority areas flood-mitigation management.

Language: Английский

---

Mapping flood susceptibility in mountainous areas on a national scale in China

The Science of The Total Environment, Journal Year: 2017, Volume and Issue: 615, P. 1133 - 1142

Published: Oct. 17, 2017

Language: Английский

---

XGBoost-based method for flash flood risk assessment

Journal of Hydrology, Journal Year: 2021, Volume and Issue: 598, P. 126382 - 126382

Published: April 28, 2021

Language: Английский

---

Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method

The Science of The Total Environment, Journal Year: 2019, Volume and Issue: 711, P. 135161 - 135161

Published: Nov. 21, 2019

Language: Английский

---