神经网络建模用于检验多个变量之间的关系 水处理厂取水口的相关水质和水量参数 位于特拉华河上的设施。这些关系被用来训练 隐孢子虫卵囊峰值浓度预测的神经网络模型 在新泽西州一家水处理设施的取水口。将参数输入到 模型的选择是基于它们与卵囊浓度的相关性和 逐步评估神经网络训练。最后训练的神经系统 网络模型预测了输入隐孢子虫浓度的两种情况， 背景和背景以上（分别指定为1和0），从8 其他水质参数。产气荚膜梭菌浓度最高 预测最终模型性能的最重要输入参数。浑浊度 是最不重要的参数。此外，一种特定地点的线性关系 在完整卵囊的数量和通过 指出了水处理厂取水口的信息收集规则方法 （完整卵囊=0.595 x总卵囊，R2=0.9011）。包括15个参考文献、表格和图表。

Neural network modeling was used to examine the relationships between multiple interrelated water quality and quantity parameters at the intake to a water treatment facility located on the Delaware River. The relationships were used to train a neural network model to predict peak concentrations of Cryptosporidium oocysts at the intake of a New Jersey water treatment facility. Input parameters to the model were selected based on their correlation with oocyst concentrations and stepwise evaluation of neural network training. The final trained neural network model predicted two conditions of input Cryptosporidium concentrations, background and above background (assigned as 1 and 0, respectively), from eight other water quality parameters. Clostridium perfringens concentrations were the most significant input parameter in predicting the final model's performance. Turbidity was the least significant parameter. Furthermore, a site-specific, linear relationship between the numbers of full oocysts and the total number of oocysts recovered by the Information Collection Rule method at the water treatment plant intake was noted (full oocysts = 0.595 x total oocysts, R2 = 0.9011). Includes 15 references, tables, figures.