Modeling Various Drought Time Scales via a Merged Artificial Neural Network with a Firefly Algorithm

Abstract

Drought monitoring and prediction have important roles in various aspects of hydrological studies. In the current research, the standardized precipitation index (SPI) was monitored and predicted in Peru between 1990 and 2015. The current study proposed a hybrid model, called ANN-FA, for SPI prediction in various time scales (SPI3, SPI6, SPI18, and SPI24). A state-of-the-art firefly algorithm (FA) has been documented as a powerful tool to support hydrological modeling issues. The ANN-FA uses an artificial neural network (ANN) which is coupled with FA for Lima SPI prediction via other stations. Through the intelligent utilization of SPI series from neighbors’ stations as model inputs, the suggested approach might be used to forecast SPI at various time scales in a meteorological station with insufficient data. To conduct this, the SPI3, SPI6, SPI18, and SPI24 were modeled in Lima meteorological station using other meteorological stations’ datasets in Peru. Various error criteria were employed to investigate the performance of the ANN-FA model. Results showed that the ANN-FA is an effective and promising approach for drought prediction and also a multi-station strategy is an effective strategy for SPI prediction in the meteorological station with a lack of data. The results of the current study showed that the ANN-FA approach can help to predict drought with the mean absolute error = 0.22, root mean square error = 0.29, the Pearson correlation coefficient = 0.94, and index of agreement = 0.97 at the testing phase of best estimation (SPI3).

A Synergistic Optimization Algorithm with Attribute and Instance Weighting Approach for Effective Drought Prediction in Tamil Nadu

“…Ali Danandeh Mehr [11] performed SPEI3 and SPEI6 prediction using hybrid Extreme Learning Machine (ELM) with the water cycle and bacterial foraging. To improve the accuracy of ELM, identification of the optimum value of the total number of hidden neurons and maximum number of iterations is required, and this task was carried out using the water cycle and bacterial foraging.…”

Drought Forecasting: Application of Ensemble and Advanced Machine Learning Approaches

“…The research by Gul et al (2023) [39] found that the Extreme Gradient Boosting (XgBoost) model outperformed the Adaptive Boosting (AdaBoost), and Gradient Boosting (GradBoost) models in forecasting SPI-3, SPI-6 and SPI-12 timeseries of the Aegean region in Türkiye. The hybrid ML models can be more interpretable than standard ML models; considering this Mohammadi (2023) [10] applied artificial neural network with firefly algorithm (ANN-FA) to model SPI-3, SPI-6, SPI-18, and SPI-24 of Lima meteorological station in Peru and obtained promising forecasts with higher accuracy. The FA is a metaheuristic algorithm that was used to optimize the parameters of the ANN.…”

A Case Study of Drought during Summer 2022: A Large-Scale Analyzed Comparison of Dry and Moist Summers in the Midwest USA

“…[9] shows a trend toward more intense seasonal droughts in the Mediterranean over the last decade, while ref. [10] showed that longer term drought was forecast better in Peru using their technique.…”

“…Short-term drought focuses on differences between precipitation and evaporation on the seasonal time scale (e.g., [4,9,10]), whereas these references describe long-term drought on a time scale of six months or greater. In addition, ref.…”