Prediction and Validation of Rainfall Classes for Vaigai River Catchment using El Nino

Abstract

Extraordinary weather patterns are being observed globally during the past 30 years due to climate change resulting in variations in temperature and rainfall. Studies on long-term trend pattern of temperature and rainfall since 1980 distinctly shows a rise in mean temperature and declining rainfall trend. Due to change of climate at global level change, forecasting of rainfall with the conventional statistical analysis could not predict satisfactory results. Among the available processes, the El Niño Southern Oscillation (ENSO) cycle is considered efficient. Statistical analysis was carried out in this study so as to investigate the implication of rainfall data in seven rain gauge stations located in Vaigai River Catchment through the period from 1959 to 2016. ENSO Cycle was used also to predict rainfall for Vaigai River catchment of the Tamil Nadu State, India. Quadratic discrimination analysis (QDA) and Neural Network models are used to identify the class of rainfall classes with reference to ENSO cycle. The patterns recognized on the study area offer constructive information to administrators of water resource management, to implement the same for agriculture, water supply and power generation.

Artificial Intelligence in the Water–Energy–Food Model: A Holistic Approach towards Sustainable Development Goals

“…Following the various steps through which our research has been carried out, our data collection is composed of 94 articles. Most of the articles used quantitative methodologies [52][53][54][55][56][57][58][59] to assess the trade-offs between water and energy, food and energy, or water and food. Case study analysis has often been combined with a quantitative methodology to gain a deeper understanding of WEF in particular contexts or sectors [60][61][62].…”