Application of Unascertained Neural Networks to Financial Early Warning

2009 ◽  
Author(s):  
Huawang Shi
Keyword(s):  
Neural Networks ◽  
Early Warning

scholarly journals Estimation of Rainfall from Climatology Data Using Artificial Neural Networks in Palembang City South Sumatera

2021 ◽  
Vol 930 (1) ◽  
pp. 012062
Author(s):  
E Suhartanto ◽  
S Wahyuni ◽  
K M Mufadhal
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Early Warning ◽  
Rainfall Data ◽  
Climatological Data ◽  
Data Requirement ◽  
Floods And Droughts ◽  
Artificial Neural

Abstract Estimation of climatological parameters, especially rainfall is a data requirement for all regions of Indonesia. The availability of rainfall data is used for early warning of flood or drought disasters. The study location is in Palembang City, South Sumatra Province, where floods and droughts often occur and lack of availability of rainfall data. This study aims to obtain the best model in estimating rainfall from climatological data. The analysis was carried out to estimate the rainfall from the climatological data using the Artificial Neural Networks method. The Artificial Neural Networks were applied and showed some results with the best calibration was at 16 years using TRAINLM with 1500 epochs that is the performances NSE = 0.54, RMSE = 99.37, and R = 0.74. Whereas the best validation was at 1 year that is the performances NSE = 0.41, RMSE = 87.32, and R = 0.65.

scholarly journals Training LSTM-neural networks on early warning signals of declining cooperation in simulated repeated public good games

MethodsX ◽  
2020 ◽  
Vol 7 ◽  
pp. 100920
Author(s):  
Manfred Füllsack ◽  
Marie Kapeller ◽  
Simon Plakolb ◽  
Georg Jäger
Keyword(s):  
Neural Networks ◽  
Public Good ◽  
Early Warning ◽  
Warning Signals ◽  
Early Warning Signals ◽  
Public Good Games

scholarly journals Establishment of urban waterlogging pre-warning system based on coupling RBF-NARX neural networks

2020 ◽  
Vol 82 (9) ◽  
pp. 1921-1931
Author(s):  
Ming Wei ◽  
Lin She ◽  
Xue-yi You
Keyword(s):  
Neural Networks ◽  
Early Warning ◽  
Early Warning System ◽  
Low Impact Development ◽  
Warning System ◽  
Extreme Rainfall ◽  
Area At Risk ◽  
Risk Area ◽  
Rainfall Process ◽  
Flooding Duration

Abstract The optimal layout of low-impact development (LID) facilities satisfying annual runoff control for low rainfall expectation is not effective under extreme rainfall conditions and urban waterlogging may occur. In order to avoid the losses of urban waterlogging, it is particularly significant to establish a waterlogging early warning system. In this study, based on coupling RBF-NARX neural networks, we establish an early warning system that can predict the whole rainfall process according to the rainfall curve of the first 20 minutes. Using the predicted rainfall process curve as rainfall input to the rainfall-runoff calculation engine, the area at risk of waterlogging can be located. The results indicate that the coupled neural networks perform well in the prediction of the hypothetical verification rainfall process. Under the studied extreme rainfall conditions, the location of 25 flooding areas and flooding duration are well predicted by the early warning system. The maximum of average flooding depth and flooding duration is 16.5 cm and 99 minutes, respectively. By predicting the risk area and the corresponding flooding time, the early warning system is quite effective in avoiding and reducing the losses from waterlogging.

Sign in / Sign up

Export Citation Format

Share Document