Environmental Modelling & Software 2017-12-06

Data-driven rainfall/runoff modelling based on a neuro-fuzzy inference system

N. Bartoletti, F. Casagli, S. Marsili-Libelli, A. Nardi, L. Palandri

Index: 10.1016/j.envsoft.2017.11.026

Full Text: HTML

Abstract

The development of rainfall/runoff models involves extensive computation and the availability of different coexisting platforms, including numerical flow models and GIS for their physiographical characterization. In this paper we present a data-driven approach which avoids the use of GIS, but is based on a combination of Principal Component Analysis (PCA) and an Adaptive Neuro Fuzzy Inference System (ANFIS) to produce a simple and effective output flow prediction based on previous rainfall/runoff data in the catchment. The emphasis of the paper is on how to set-up an efficient data structure that produces a good output flow estimation. The PCA approach is compared to the Thiessen polygons method, requiring GIS, and we demonstrate that the former can produce a better ANFIS model, with less algorithmic complexity and improved accuracy. The combined PCA + ANFIS procedure is applied to two minor river basins in Tuscany, Italy, to demonstrate its effectiveness.

Latest Articles:

Creating extreme weather time series through a quantile regression ensemble ☆

2018-03-21

[10.1016/j.envsoft.2018.03.007]

Hybrid SOM+k-Means clustering to improve planning, operation and management in water distribution systems

2018-03-08

[10.1016/j.envsoft.2018.02.013]

Modelling background air pollution exposure in urban environments: Implications for epidemiological research

2018-02-26

[10.1016/j.envsoft.2018.02.011]

Environmental data stream mining through a case-based stochastic learning approach

2018-02-16

[10.1016/j.envsoft.2018.01.017]

Inverse modelling of snow depths

2018-02-09

[10.1016/j.envsoft.2018.01.010]

More Articles...