Aims: Accurate estimates of evaporation by employing efficient and proven soft computing techniques that involve least number of influencing variables are important to tackle present water crisis. Place and Duration of Study: In the present study, Artificial Neural Network (ANN) and fuzzy logic models were developed to predict the pan evaporation (Ep) in Raichur, Karnataka, using six input parameters viz., maximum and minimum temperatures, maximum and minimum relative humidity, sunshine hours and wind speedfor the period of 30 years (1990-2019). Methodology: Comparison between models was done to select best suitable model to predict pan evaporation. The ANN models were trained withthree training algorithms. Gaussian membership function was used in fuzzy logic (FL) model. Results: The results revealed that, the ANN-GDX model performed better over ANN-LM, ANN-BR and fuzzy logic models during validation period. The correlation coefficient (r), coefficient of efficiency (CE), mean absolute error (MAE) and root mean square error (RMSE) were observed to be 0.7637, 0.5831, 1.3880 and 1.8541 respectively during validation period between actual and predicted pan evaporation (Ep) with 1.3880 mm root mean square error. Therefore, ANN-GDX model was chosen for predicting pan evaporation in the study area. Conclusion: ANN-GDX model was chosen for predicting pan evaporation in the study area.

Aims: To measure and characterize storm wise runoff for the catchment area of the farm pond and to correlate rainfall intensity and runoff relationship for the catchment area will help to design the appropriate size of the farm pond and waste weirs of the bunding system. Place and Duration of Study: The study was conducted in a micro catchment (field sized area) of a dugout farm pond, having an area of 6 ha located in the new area of UAS campus Raichur, which comes under Zone II in Region-I of Karnataka state. Geographically it is located at 16° 12′ N latitude and 77° 20′ E longitude and at an elevation of 389 m above the mean sea level (MSL). The study was conducted for a period of one year during 2019. Methodology: The existing farm pond constructed was used for conducting hydrological studies. The detailed soil and rainfall characterization of the study area has been made through appropriate methods. The rainfall intensity for each storm has been measured using self-recording rain gauge. The runoff has been measured at the out let of the field sized micro catchment area of farm pond using hydraulic structures coupled with automatic runoff recorder. The event wise rainfall, rainfall intensity and runoff have been measured and analysed to see the relationship between rainfall intensity and runoff with prevailing soil and topographical characteristics of the study area. Results: The percent runoff varied from 6.79 to 50.42 and highest was 50.42 per cent occurred on 25-10-2019 followed by 44.03, 39.36 and 37.46 per cent. The data shows that the individual storm wise percent runoff was quite high as compared to annual percent runoff of 15.99 per cent. The storm wise high runoff percent was due to the fact that high intensity of rainfall followed by high AMC in the soil. Further the minimum runoff yield of 142.66 m3 was observed on 18-07-2019 against the rainfall of 35.00 mm and maximum of 2985.48 m3 was yielded on 25-09-2109 against rainfall of 113.00 mm and followed by 1086.64 m3, 944.24 m3, 665.61 m3 and 431.25 m3 against rainfall of 46.00 mm, 42.00 mm, 22.00 mm and 48.00 mm respectively. The total annual runoff yield was found to be 6255.90 m3 against the rainfall of 651.50 mm. Therefore, there is a scope for harvesting excess quantity of runoff which is going as a waste. The existing pond capacity of 547.77 m3 is insufficient to store prevailing runoff generated in the catchment area and hence, pond capacity may be enhanced. The maximum intensity of rainfall and runoff during six events were showed statistically insignificant relationship with R2 value of 0.370. There is no correlation between intensity of rainfall and runoff.

Aims: Estimation of water balance components of a micro watershed by employing efficient calibrated and validated SWAT model helps to understand each components of water balance and are important to plan agricultural water management, climate change impact assessment, flow forecasting, water quality assessment etc. This water balance study minimizes possibility of drought and mismanagement, and hence will lead to a proper utilization of accessible water resource. Place and Duration of Study: In the present study, QSWAT hydrological model was calibrated and validated using measured runoff data from the outlet of the micro watershed and then put to use for long term simulations in Patapur micro watershed, Raichur District, Karnataka using weather, land use and land cover, soil and digital elevation model for the period of 37 years (1980-2016). Methodology: The QSWAT model was set up using the input data of Patapur micro watershed and was accurately calibrated and validated using the measured runoff data. The calibrated was used for long term simulation from 1980-2016 and then water balance components of the micro watershed was estimated. Results: The results revealed that the QSWAT model performed better in simulating the runoff and other water balance components. The daily calibration statistics results for behavioral parameters in SWAT-CUP for stream flow discharge during the period 2012-2014 are R2, NS, PBIAS and RSR values between measured and simulated by model was found to be 0.88, 0.87, -21.30 and 0.36, respectively indicating the model performance for daily calibration was very good in terms of both R2 and NS value as their value being >0.75 as per the performance ratings of hydrological model. The water yield that is draining out of the watershed includes surface runoff, lateral flow and groundwater contribution to stream flow minus the transmission losses (water lost as deep percolation and evapo-transpiration) which amounts to 168.40 mm. The annual water balance components for the watershed indicated that out of 527.70 mm of annual precipitation, 322.50 mm and 114.91 mm was lost by evapo-transpiration and surface runoff, respectively. The water balance also revealed that 82.86 mm was contributed to groundwater by percolating into shallow aquifer which was followed by 43.40 mm of base flow but the ground water recharge and storage is very meager that accounts to only 4.14 mm that is the matter of concern over the micro watershed. The simulation model indicates that 58.77 to 64.54% by rainfall was lost by evapotranspiration and very less amount lost through the lateral flow. Groundwater flow and percolation were contributing 3.68 to 10.13% and 9.95 to 19.82 % respectively, from total rainfall. During the highest rainfall year, about 33.22, 10.13% and 1.10% of the rainfall was transformed into surface runoff, groundwater flow and lateral flow respectively. During lowest rainfall year, about 8.31%, 3.68% and 1.35% of the rainfall was transformed into surface runoff, groundwater flow and lateral flow respectively.