A Bayesian framework based on a Gaussian mixture model and radial-basis-function Fisher discriminant analysis (BayGmmKda V1.1) for spatial prediction of floods

• Published in: Geoscientific Model Development 2017-09, Vol.10 (9), p.3391-3409
• Main Authors: Dieu Tien Bui, Hoang, Nhat-Duc
• Format: Article
• Language: English
• Subjects: Accuracy; Adaptive systems; Artificial neural networks; Bayesian analysis; Data base management systems; Developing countries; Discriminant analysis; Flood damage; Flood mapping; Flood predictions; Floods; Frameworks; Fuzzy logic; Fuzzy systems; Geographic information systems; Geographical information systems; Hydrology; Information systems; Infrastructure; Land use; Land use management; Land use planning; LDCs; Mathematical models; Modelling; Probabilistic models; Probability theory; Radial basis function; Remote sensing; Runoff; Satellite navigation systems; Software; Statistical analysis; Storm damage; Support vector machines; Time series
• ISSN: 1991-9603; 1991-962X; 1991-959X; 1991-9603; 1991-962X
• DOI: 10.5194/gmd-10-3391-2017

In this study, a probabilistic model, named as BayGmmKda, is proposed for flood susceptibility assessment in a study area in central Vietnam. The new model is a Bayesian framework constructed by a combination of a Gaussian mixture model (GMM), radial-basis-function Fisher discriminant analysis (RBFDA), and a geographic information system (GIS) database. In the Bayesian framework, GMM is used for modeling the data distribution of flood-influencing factors in the GIS database, whereas RBFDA is utilized to construct a latent variable that aims at enhancing the model performance. As a result, the posterior probabilistic output of the BayGmmKda model is used as flood susceptibility index. Experiment results showed that the proposed hybrid framework is superior to other benchmark models, including the adaptive neuro-fuzzy inference system and the support vector machine. To facilitate the model implementation, a software program of BayGmmKda has been developed in MATLAB. The BayGmmKda program can accurately establish a flood susceptibility map for the study region. Accordingly, local authorities can overlay this susceptibility map onto various land-use maps for the purpose of land-use planning or management.