Nutrient concentrations in runoff from beef cattle feedlots were estimated using two different adaptive network-based fuzzy inference systems (ANFIS), which were: (1) grid partition (ANFIS-GP) and (2) subtractive clustering based fuzzy inference system (ANFIS-SC). The input parameters were pH and electrical conductivity (EC); and the output parameters were total Kjeldahl nitrogen (TKN), ammonium-N (NH4-N), orthophosphate (ortho-P), and potassium (K). Models performances were evaluated based on root mean square error, mean absolute error, mean bias error, and determination coeficient statistics. For the same dataset, the ANFIS model outputs were also compared with a previously published nutrient concentration predictability model for runoff using artificial neural network (ANN) outputs. Results showed that both ANFIS-GP and ANFIS-SC models successfully predicted the runoff nutrient concentration. The comparison results revealed that the ANFIS-GP model performed slightly better than ANFIS-SC model in estimating TKN, NH4-N, ortho-P, and K. When compared with the ANN model for the same dataset, ANFIS outperformed ANN in nutrient concentration prediction in runoff.
Leaf area of a plant is essential to understand the interaction between plant growth and environment. This useful variable can be determined by using direct (some expensive instruments) and indirect (prediction models) methods. Leaf area of a plant can be predicted by accurate and simple leaf area models without damaging the plant, thus, provide researchers with many advantages in horticultural experiments. Several leaf-area prediction models have been produced for some plant species in optimum conditions, but not for a plant grown under stress conditions. This study was conducted to develop leaf area estimation models by using linear measurements such as lamina length and width by multiple regression analysis for green pepper grown under different stress conditions. For this purpose, two experiments were conducted in a greenhouse. The first experiment focused to determine leaf area of green pepper grown under six different levels of irrigation water salinity (0.65, 2.0, 3.0, 4.0, 5.0, and 7.0 dS m-1) and the other under four different irrigation regime (amount of applied water was 1.43, 1.0, 0.75, and 0.50 times of required water). In addition to general models for each experiment, prediction models of green pepper for each treatment of irrigation water salinity and of irrigation regime experiments were obtained. Validations of the models for both experiments were realized by using the measurements belong to leaf samples allocated for validation purposes. As a result, the determined equations can simply and readily be used in prediction of leaf area of green pepper grown under salinity and water stress conditions. The use of such models enable researchers to measure leaf area on the same plants during the plant growth period and, at the same time, may reduce variability in experiments. and B. Cemek ... [et al.].