scholarly journals Application of artificial neural networks to forecasting monthly rainfall one year in advance for locations within the Murray Darling basin, Australia

2017 ◽  
Vol 12 (08) ◽  
pp. 1282-1298 ◽  
Author(s):  
John Abbot ◽  
Jennifer Marohasy
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Monthly Rainfall ◽  
Murray Darling Basin ◽  
Artificial Neural ◽  
One Year

Can artificial neural networks predict lawyers’ performance rankings?

2018 ◽  
Vol 67 (9) ◽  
pp. 1940-1958 ◽  
Author(s):  
Susana Almeida Lopes ◽  
Maria Eduarda Duarte ◽  
João Almeida Lopes
Keyword(s):  
Neural Networks ◽  
Regression Analysis ◽  
Artificial Neural Networks ◽  
Multivariate Regression Analysis ◽  
Law Firms ◽  
Law Firm ◽  
Content Type ◽  
Non Linear ◽  
Artificial Neural ◽  
One Year

Purpose The purpose of this paper is to propose a predictive model that could replace lawyers’ annual performance rankings and inform talent management (TM) in law firms. Design/methodology/approach Eight years of performance rankings of a sample of 140 lawyers from one law firm are used. Artificial neural networks (ANNs) are used to model and simulate performance rankings over time. Multivariate regression analysis is used to compare with the non-linear networks. Findings With a lag of one year, performance ranking changes are predicted by the networks with an accuracy of 71 percent, over performing regression analysis by 15 percent. With a lag of two years, accuracy is reduced by 4 percent. Research limitations/implications This study contributes to the literature of TM in law firms and to predictive research. Generalizability would require replication with broader samples. Practical implications Neural networks enable extended intervals for performance rankings. Reducing the time and effort spent benefits partners and lawyers alike, who can instead devote time to in-depth feedback. Strategic planning, early identification of the most talented and avenues for tailored careers become open. Originality/value This study pioneers the use of ANNs in law firm TM. The method surpasses traditional static study of performance through its use of non-linear simulation and prediction modeling.

scholarly journals Monthly Rainfall Anomalies Forecasting for Southwestern Colombia Using Artificial Neural Networks Approaches

Water ◽  
2020 ◽  
Vol 12 (9) ◽  
pp. 2628 ◽  
Author(s):  
Teresita Canchala ◽  
Wilfredo Alfonso-Morales ◽  
Yesid Carvajal-Escobar ◽  
Wilmar L. Cerón ◽  
Eduardo Caicedo-Bravo
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Southern Oscillation ◽  
Rainfall Variability ◽  
Monthly Rainfall ◽  
Climate Indices ◽  
Rainfall Forecasting ◽  
Exogenous Variables ◽  
Rainfall Anomalies ◽  
Artificial Neural

Improving the accuracy of rainfall forecasting is relevant for adequate water resources planning and management. This research project evaluated the performance of the combination of three Artificial Neural Networks (ANN) approaches in the forecasting of the monthly rainfall anomalies for Southwestern Colombia. For this purpose, we applied the Non-linear Principal Component Analysis (NLPCA) approach to get the main modes, a Neural Network Autoregressive Moving Average with eXogenous variables (NNARMAX) as a model, and an Inverse NLPCA approach for reconstructing the monthly rainfall anomalies forecasting in the Andean Region (AR) and the Pacific Region (PR) of Southwestern Colombia, respectively. For the model, we used monthly rainfall lagged values of the eight large-scale climate indices linked to the El Niño Southern Oscillation (ENSO) phenomenon as exogenous variables. They were cross-correlated with the main modes of the rainfall variability of AR and PR obtained using NLPCA. Subsequently, both NNARMAX models were trained from 1983 to 2014 and tested for two years (2015–2016). Finally, the reconstructed outputs from the NNARMAX models were used as inputs for the Inverse NLPCA approach. The performance of the ANN approaches was measured using three different performance metrics: Root Mean Square Error (RMSE), Mean Absolute Error (MAE), and Pearson’s correlation (r). The results showed suitable forecasting performance for AR and PR, and the combination of these ANN approaches demonstrated the possibility of rainfall forecasting in these sub-regions five months in advance and provided useful information for the decision-makers in Southwestern Colombia.

Monthly rainfall–runoff modelling using artificial neural networks

2011 ◽  
Vol 56 (3) ◽  
pp. 349-361 ◽  
Author(s):  
Fernando Machado ◽  
Miriam Mine ◽  
Eloy Kaviski ◽  
Heinz Fill
Keyword(s):  
Neural Networks ◽  
Artificial Neural Networks ◽  
Monthly Rainfall ◽  
Rainfall Runoff ◽  
Artificial Neural
Sign in / Sign up

Export Citation Format

Share Document