Improving Drought Modeling Using Hybrid Random Vector Functional Link Methods

Abstract

Drought modeling is essential in water resources planning and management in mitigating its effects, especially in arid regions. Climate change highly influences the frequency and intensity of droughts. In this study, new hybrid methods, the random vector functional link (RVFL) integrated with particle swarm optimization (PSO), the genetic algorithm (GA), the grey wolf optimization (GWO), the social spider optimization (SSO), the salp swarm algorithm (SSA) and the hunger games search algorithm (HGS) were used to forecast droughts based on the standard precipitation index (SPI). Monthly precipitation data from three stations in Bangladesh were used in the applications. The accuracy of the methods was compared by forecasting four SPI indices, SPI3, SPI6, SPI9, and SPI12, using the root mean square errors (RMSE), the mean absolute error (MAE), the Nash–Sutcliffe efficiency (NSE), and the determination coefficient (R2). The HGS algorithm provided a better performance than the alternative algorithms, and it considerably improved the accuracy of the RVFL method in drought forecasting; the improvement in RMSE for the SPI3, SP6, SPI9, and SPI12 was by 6.14%, 11.89%, 14.14%, 24.5% in station 1, by 6.02%, 17.42%, 13.49%, 24.86% in station 2 and by 7.55%, 26.45%, 15.27%, 13.21% in station 3, respectively. The outcomes of the study recommend the use of a HGS-based RVFL in drought modeling.

Drought Forecasting: A Review and Assessment of the Hybrid Techniques and Data Pre-Processing

“…Thus, a water shortage may negatively impact agricultural productivity and threaten food security. Water shortage is a significant concern in different parts of the world [32,41]. Erhardt and Czado [42] The prediction of drought is difficult because of its variability.…”

“…Different climatic variables are used as inputs to the forecasting model. The technique given here may be beneficial for decision-makers in reducing its consequences and developing effective strategies for water resource management on a monthly or seasonal timeline [32,44]. Agricultural production, the economy, and the environment are all negatively affected by their impacts.…”

“…Besides, a few studies employed all the data pre-processing steps. No Yes Yes Khan et al [31] No Yes No Pham et al [35] Yes Yes Yes Banadkooki et al [38] Yes No Yes Adnan et al [32] Yes No No Nabipour et al [20] Yes No No Mohamadi et al [68] Yes No Yes Djerbouai and Souag-Gamane [37] Yes Yes No Wu et al [40] Yes Yes No Soh et al [52] Yes Yes No Başakın et al [27] Yes Yes No Das et al [62] Yes Yes No Belayneh et al [23] Yes Yes No Kisi et al [39] Yes No Yes…”

“…Various studies have demonstrated that hybrid methods are better than standalone methods. Therefore, several studies recommended using hybrid models to increase forecast precision [22,31,32]. Recently, hybrid prediction models have become more popular than standalone models in hydrology.…”

“…(2) The parameter optimisation-based hybrid models (OBH): The primary idea behind the OBH models is to use optimisation algorithms to identify the optimal parameters of the models [34], and combine the models with nature-inspired algorithms for hydrological drought prediction such as Adnan, et al [32], Nabipour et al [20], Banadkooki et al [38], and Kisi et al [39].…”