Adaptive neuro fuzzy inference system (ANFIS) machine learning algorithm for assessing environmental and socio-economic vulnerability to drought: a study in Godavari middle sub-basin, India

Climate change has increased the frequency of drought occurrence in various parts world. Drought as a complex phenomenon causes severe impacts on ecological and socio-economic status. Short-term long-term occurrences have made many regions vulnerable globally. This paper makes an attempt to assess vulnerability Godavari Middle Sub-basin India. Twenty-four site specific environmental factors were identified based extensive literature review. was assessed using standardized precipitation index (SPI). These datasets divided into training (70%) testing (30%) data. Frequency ratio (FR) model utilized establish relationship among conditioning frequency. Weights obtained from FR used input adaptive neuro-fuzzy inference systems (ANFIS) model. results validated data receiver operating characteristic (ROC). The accuracy ANFIS models for 1-month (0.957), 3-months (0.882), 6-months (0.964) 12-months (0.938) showed high suitability assessment vulnerability. findings revealed that very low normalized difference vegetation (NDVI) increasing trend highest maximum mean temperature major which influenced sub-basin. High proportion area under fallow land, infant mortality rate (IMR) moderate literacy making watersheds during short droughts. Largest sub-basin found 3-months, followed by Thus, study calls policy intervention towards lessening impact highly watersheds.