ANFIS-based soft computing models for forecasting effective drought index over an arid region of India Ayilobeni Kikon a, *, B. M. Dodamani a , Surajit Deb Barma a and Sujay Raghavendra Naganna b a Department of Water Resources and Ocean Engineering, National Institute of Technology Karnataka, Surathkal, Mangalore 575025, India b Department of Civil Engineering, Manipal Institute of Technology Bengaluru, Manipal Academy of Higher Education, Manipal 576104, Karnataka, India *Corresponding author. E-mail: ayilobeni@gmail.com AK, 0000-0003-4821-1037; SDB, 0000-0003-0849-3033; SRN, 0000-0002-0482-1936 ABSTRACT Drought is a natural hazard that is characterized by a low amount of precipitation in a region. In order to evaluate the drought-related issues that cause chaos for human well-being, drought indices have become increasingly important. In this study, the monthly precipitation data from 1964 to 2013 (about 50 years) of the Jodhpur district in the drought-prone Rajasthan state of India was used to derive the effective drought index (EDI). The machine learning models hybridized with evolutionary optimizers such as the genetic algorithm adaptive neuro- fuzzy inference system (GA-ANFIS) and particle swarm optimization ANFIS (PSO-ANFIS) were used in addition to the generalized regression neural network (GRNN) to predict the EDI index. Using the partial autocorrelation function (PACF), models for forecasting the monthly EDI were constructed with 2-, 3- and 5-input combinations to evaluate their outcomes based on various performance indices. The results of the different combination models were compared. With reference to 2-input and 3-input combination models, both GA-ANFIS and PSO- ANFIS show better performance results with R 2 ¼ 0.75, while among the models with 5-input combination, GA-ANFIS depicts better perform- ance results compared to other models with R 2 ¼ 0.78. The results are presented suitably with the aid of scatter plots, Taylor’s diagram and violin plots. Overall, the GA-ANFIS and PSO-ANFIS models outperformed the GRNN model. Key words: drought, EDI, forecasting, GA-ANFIS, GRNN, PSO-ANFIS HIGHLIGHTS • Effective drought index (EDI) was predicted using soft computing techniques. • Hybrid machine learning algorithms were used. • GA-ANFIS, PSO-ANFIS and GRNN paradigms were used. • The EDI of an arid region in India was used for prediction. • Precipitation data was used for computing the EDI of drought-prone areas. This is an Open Access article distributed under the terms of the Creative Commons Attribution Licence (CC BY 4.0), which permits copying, adaptation and redistribution, provided the original work is properly cited (http://creativecommons.org/licenses/by/4.0/). © 2023 The Authors AQUA — Water Infrastructure, Ecosystems and Society Vol 00 No 0, 1 doi: 10.2166/aqua.2023.204 corrected Proof Downloaded from http://iwaponline.com/aqua/article-pdf/doi/10.2166/aqua.2023.204/1234249/jws2023204.pdf by guest on 03 June 2023