Abstract
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.
Highlights
Rainfall is a meteorological phenomenon that is a product of the condensation process of atmospheric water vapor and the influence of many ocean–atmospheric factors
Its estimation in a region is considered essential for adequate water resources management, in many decision-making processes concerned with water and agriculture planning, to perform risk management
We considered many exogenous variables; the NNARMAX model is described in Equation (3) as follows: y(k + 1) = f ( y(k), y(k − 1), · · ·, y k − n y, u1 (k), u1 (k − 1), · · ·, u1 (k − nu1 ), · · ·, u2 (k), u2 (k − 1), · · ·, u2 (k − nu2 ) · · ·, ur (k), ur (k − 1), · · ·, ur (k − nur ), e(k), e(k − 1), · · ·, e(k − ne ))
Summary
Rainfall is a meteorological phenomenon that is a product of the condensation process of atmospheric water vapor and the influence of many ocean–atmospheric factors. The occurrence of extreme rainfall events linked to climatic variability can result in flooding and droughts with material damage and even loss of human life in the local communities [2,3]; it is meaningful to study the rainfall variability in terms of anomalies, which show the deviations from rainfall normal patterns [4]. According to Solomon et al [5], the rainfall anomalies are a good indicator of the climatic variability in a region, which has often been studied in different regions with multiple purposes [6,7,8]. Understanding rainfall anomalies, knowing the factors that influence their behavior, and improving forecast accuracy are significant aspects for the proper planning and management of water resources [9]. To improve the rainfall forecast accuracy, several authors have used its influential variables and applied different modeling approaches, whether linear or non-linear. Linear methods conventionally use stochastic models such as the Multiple Linear Regression (MLR) [10,11], the Autoregressive
Sign-in/Register to view highlights & summary Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have
Schedule a callDisclaimer: All third-party content on this website/platform is and will remain the property of their respective owners and is provided on "as is" basis without any warranties, express or implied. Use of third-party content does not indicate any affiliation, sponsorship with or endorsement by them. Any references to third-party content is to identify the corresponding services and shall be considered fair use under The CopyrightLaw.
