Abstract:
Evapotranspiration constitutes one of the major components of the hydrological cycle and hence its accurate estimation is of vital importance to assess water availability and requirements. This study explores the utility of soft computing techniques to develop the model for evapotranspiration process. An important characteristic of these techniques are that both the model structure and coefficients are simultaneously optimized.
The goal of this study is to analyze the potential evapotranspiration with changing environment using soft computing techniques. A data driven model has been developed to predict the Potential evapotranspiration of Varanasi (a part of Eastern Uttar Pradesh). The Eastern part of Uttar Pradesh includes sixteen districts namely Allahabad, Azamgarh, Ballia, Chandauli, Deoria, Ghazipur, Gorakhpur, launpur, Kushinagar, Maharajganj, Mau, Mirzapur, Sant Kabir Nagar,, Sant Ravidas Nagar, Sonbhadra and Varanasi. During this modeling, only data for Varanasi area is considered.
Vapour-pressure, precipitation, cloud-cover, wet day frequency and average temperature of the region are used
as the input data while potential evapotranspiration is used as output of the model. A relationship between
inputs and output has been developed through the Fuzzy based soft computing modeling. This model has been
developed on the basis of Fuzzy Technique which is one of the emerging techniques in the field of modeling. Grid
Partitioning and Subtractive Clustering Methods in Adaptive Neuro-Fuzzy Inference System (ANFIS) have
been used to develop the models, During the study, data have been taken from the website http://
www.indiawaterportal.org/. After developing the models, the effects of temperature increments have been
studied over potential evapotranspiration which gives the climate change in this region. Thus the effect of temperature increment (Global Warming) has been studied for the climate change.
