Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method
Flash-flood hazard assessment using ensembles and Bayesian-based machine learning models: Application of the simulated annealing feature selection method
复制标题
基于集成和贝叶斯机器学习模型的山洪灾害风险评估：模拟退火法特征选择方法的应用
DOI：
10.1016/j.scitotenv.2019.135161
复制
发表时间：
2020-04-01
影响因子：
9.8
通讯作者：
Haghighi, Ali Torabi
中科院分区：
文献类型：
--
作者：
Hosseini, Farzaneh Sajedi;Choubin, Bahram;Haghighi, Ali Torabi
山洪暴发日益被认为是世界范围内一种常见的自然灾害。伊朗是受大洪水影响最严重的地区之一。虽然山洪暴发时间预报模型主要是为预警系统开发的，但评估危险地区的模型可大大有助于适应和缓解政策的制定以及减少灾害风险。以往的研究在山洪灾害制图提高了更精确的模型的进步的迫切性。因此，目前的研究提出了最先进的整体模型的提升广义线性模型（GLMBoost）和随机森林（RF），和贝叶斯广义线性模型（BayesGLM）方法更高的性能建模。此外，预处理方法，即模拟退火（SA），是用来消除冗余变量的建模过程。基于命中和未命中分析的建模结果表明两种模型的高性能（准确度= 90- 92%，Kappa = 79- 84%，成功率= 94- 96%，威胁评分= 80- 84%，Heidke技能评分= 79-84%）。与河流的距离、植被、排水密度、土地利用和海拔等变量对模拟山洪有更大的贡献。本研究的结果可以显着地促进危险区的地图，并进一步协助流域管理人员控制和补救的数据稀缺地区的洪水诱发的损害。(C)2019爱思唯尔B. V.保留所有权利。
Flash-floods are increasingly recognized as a frequent natural hazard worldwide. Iran has been among the most devastated regions affected by the major floods. While the temporal flash-flood forecasting models are mainly developed for warning systems, the models for assessing hazardous areas can greatly contribute to adaptation and mitigation policy-making and disaster risk reduction. Former researches in the flash-flood hazard mapping have heightened the urge for the advancement of more accurate models. Thus, the current research proposes the state-of-the-art ensemble models of boosted generalized linear model (GLMBoost) and random forest (RF), and Bayesian generalized linear model (BayesGLM) methods for higher performance modeling. Furthermore, a pre-processing method, namely simulated annealing (SA), is used to eliminate redundant variables from the modeling process. Results of the modeling based on the hit and miss analysis indicates high performance for both models (accuracy = 90-92%, Kappa = 79-84%, Success ratio = 94-96%, Threat score = 80-84%, and Heidke skill score = 79-84%). The variables of distance from the stream, vegetation, drainage density, land use, and elevation have shown more contribution among others for modeling the flash-flood. The results of this study can significantly facilitate mapping the hazardous areas and further assist watershed managers to control and remediate induced damages of flood in the data-scarce regions. (C) 2019 Elsevier B.V. All rights reserved.