Optimizing Extreme Learning Machine for Drought Forecasting: Water Cycle vs. Bacterial Foraging

Abstract

Machine learning (ML) methods have shown noteworthy skill in recognizing environmental patterns. However, presence of weather noise associated with the chaotic characteristics of water cycle components restricts the capability of standalone ML models in the modeling of extreme climate events such as droughts. To tackle the problem, this article suggests two novel hybrid ML models based on combination of extreme learning machine (ELM) with water cycle algorithm (WCA) and bacterial foraging optimization (BFO). The new models, respectively called ELM-WCA and ELM-BFO, were applied to forecast standardized precipitation evapotranspiration index (SPEI) at Beypazari and Nallihan meteorological stations in Ankara province (Turkey). The performance of the proposed models was compared with those the standalone ELM considering root mean square error (RMSE), Nash-Sutcliffe efficiency (NSE), and graphical plots. The forecasting results for three- and six-month accumulation periods showed that the ELM-WCA is superior to its counterparts. The NSE results of the SPEI-3 forecasting in the testing period proved that the ELM-WCA improved drought modeling accuracy of the standalone ELM up to 72% and 85% at Beypazari and Nallihan stations, respectively. Regarding the SPEI-6 forecasting results, the ELM-WCA achieved the highest RMSE reduction percentage about 63% and 56% at Beypazari and Nallihan stations, respectively.

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

“…In the work of Nabipour [12], short-term hydrological drought was predicted using the index known as the Standardized Hydrological Drought Index (SHDI). SHDI was calculated on 1-, 3-, and 6-month scales using the previous SHDI, SPI, and precipitation values.…”

Drought characterization: A systematic literature review

“…The accuracy of conventional indices faces many constraints such as data gaps, inappropriate monitoring networks, and data unavailability at the required spatiotemporal scales (Bageshree et al, 2022). In addition, these traditional indices depend closely on ground-based hydrometeorological data, which are typically obtained from individual meteorological stations, and the density and distribution of ground station networks are limited and not representative (Danandeh Mehr et al, 2023). According to Huang et al (2018), meteorological stations show their limits at the regional level, because it is difficult to cover very large areas with sufficient stations.…”

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

“…To this end, the performance of various ML models, including ANN (e.g., [27][28][29][30]), support vector machine (SVM; e.g., [31,32]), RF (e.g., [33]) and long short-term memory (LSTM; e.g., [34]). In the most recent research, hybrid ML models coupled with optimization algorithms have been built and applied successfully to address drought prediction issues (e.g., [35][36][37]). This combined method benefits from one or multiple optimization algorithms during the training phase; therefore, they train with a boosting optimization approach, which leads to error reduction.…”