The study was conducted at the University of Nebraska Pesticide Application and Technology Laboratory in North Platte, Nebraska in July 2015. Two application volume rates (100 and 200 l · ha−1) and three nozzle types (XR, AIXR, TTI) were selected at two flow rates (0.8 and 1.6 l · min−1) and at a single application speed of 7.7 km · h−1. Each collector type [Mylar washed (MW), Mylar image analysis (MIA), water-sensitive paper (WSP), and Kromekote (KK)] was arranged in a randomized complete block design. Each nozzle treatment was replicated twice, providing six cards of each collector type for each nozzle treatment. A water + 0.4% v/v Rhodamine WT spray solution was applied, given the fluorescent and visible qualities of Rhodamine, which allows it to be applied over all the collector types. MW had the highest coverage at 18.3% across nozzle type, followed by WSP at 18%, KK at 12% and lastly by MIA at 4%. MW resulted in a 58% increase in coverage, WSP in a 56% increase, and KK only an increase of 39% when the volume rate was doubled from 100 l · ha−1 to 200 l · ha−1 across nozzle type. MW coverage was similar to KK for half of the nozzles (XR 11002, XR 11004, AIXR 11002). Droplet number density fixed effects were all significant for nozzle type and collector type (p < 0.001) as was the interaction of nozzle type and collector type (p < 0.001). Results from this study suggest a strong correlation to data produced with WSP and MW collectors, as there was full agreement between both types except for the TTI 11004. Using both collector types in the same study would allow for a visual understanding of the distribution of the spray, while also giving an idea of the concentration of that distribution.

This study is aimed at evaluating the applicability of Artificial Neural Network (ANN) model technique for river discharge forecasting. Feed-forward multilayer perceptron neural network trained with back-propagation algorithm was employed for model development. Hydro-meteorological data for the Imo River watershed, that was collected from the Anambra-Imo River Basin Development Authority, Owerri – Imo State, South-East, Nigeria, was used to train, validate and test the model. Coefficients of determination results are 0.91, 0.91 and 0.93 for training, validation and testing periodsrespectively. River discharge forecasts were fitted against actual discharge data for one to five lead days. Model results gave R2 values of 0.95, 0.95, 0.92, 0.96 and 0.94 for first, second, third, fourth, and fifth lead days of forecasts, respectively. It was generally observed that the R2 values decreased with increase in lead days for the model. Generally, this tech-nique proved to be effective in river discharge modelling for flood forecasting for shorter lead-day times, especially in areas with limited data sets.