基于MATLAB的BP神经网络在南通市地下水质量评价中的应用

利用MATLAB的神经网络工具箱，建立了地下水质量的评价模型，并对南通市地下水水质进行了评价，评估结果反映了南通市地下水质量的现状，表明BP神经网络模型具有很强的学习和自适应能力，避免了在权值和阀值确定中人为因素的影响，增加了评价结果的客观性、公正性和精度，具有一定的实用价值。

Application of BP neural network technology in evaluation of groundwater quality of Nantong based on MATLAB

As a new method system, artificial neural network is characteristic of parallel processing, non-linear mapping, self-adaptive learning and Robust fault-tolerant, and is widely applied in pattern recognition, control optimization and intelligent information processing. Based on the neural network toolbox of MATLAB, the authors designed an evaluation model on the groundwater quality, and took the groundwater sample in Nantong City as an example. The evaluation results reflected the reality of the groundwater situation of the studied city, showed the BP neural network was of strong learning and self-adaptive abilities, capable of avoiding the artificial factor influence in the determination of weight and threshold values, increasing the objectivity, fairness and precision of evaluation results.