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:
2018-03-21
[10.1016/j.envsoft.2018.03.007]
2018-03-08
[10.1016/j.envsoft.2018.02.013]
2018-02-26
[10.1016/j.envsoft.2018.02.011]
2018-02-16
[10.1016/j.envsoft.2018.01.017]
2018-02-09
[10.1016/j.envsoft.2018.01.010]