Answers are grounded in this paper and cite their sources.
Prediction of droughts plays a very significant role in planning utilization of water resources of a region and deciding mitigation plans for the upcoming season. Predicting of droughts happens to be a difficult task due to inherent complexities in modeling climatic systems. The paucity of rainfall results in meteorological drought further leads to agricultural drought and hydrologic drought. Large-scale atmospheric circulation patterns show marked influence on Indian Summer Monsoon Rainfall. Hence, signals obtained from the large-scale atmospheric circulation patterns in form of their indices are used for the development of drought prediction models in this work. Signals of two atmospheric circulation patterns viz. El Nino Southern Oscillation (ENSO) and Equatorial Indian Ocean Oscillation (EQUINOO) are used for prediction of meteorological drought for Marathwada meteorological subdivision of India. AI tool ‘Genetic Programming’ (GP) is advantageously used to establish the complex nonlinear relationship between Standardized Precipitation Index (SPI-5) as drought index and ENSO index, EQUINOO index and monthly anomaly rainfall. The good correlation coefficients 0.867 and 0.801 for training and testing, respectively, for one month lead time predictions. Two months and three month lead time prediction models also give reasonably good correlation coefficients 0.758, 0.632 and 0.679, 0.487 for training and testing, respectively.
No takes yet. Share an insight, caveat, or question.
Chavadekar et al. (2019) studied this question.
Synapse has enriched 10 related papers. Consider them for comparative context: