应用激光诱导荧光技术测量水中溶解有机物含量，具有检测速度快，灵敏度高等优点，而实际测量中荧光光谱受到激光发射光，瑞利散射和拉曼散射等因素的不同程度影响，难以建立荧光强度与有机物浓度的准确关系。在分析激光诱导荧光光谱特征的基础上,利用误差逆向传播(BP)神经网络对复杂非线性映射关系的强大逼近能力，对上述各影响因素进行综合处理，从而建立光谱的荧光强度与有机物浓度之间对应关系。通过对已知浓度有机物溶液的测量，用得到的荧光强度有机物浓度样本对BP神经网络进行精确训练，实现对水中溶解有机物浓度的测量。实验表明，以上方法可以实现对水中溶解有机物含量的准确测量。

The analysis of the dissolved organic matter in water by laser-induced fluorescence spectroscopy has an advantage of high sensitiveness and accuracy. But, actually, this method is affected by laser light, Rayleigh scattering, Raman scattering and other factors. So it is difficult to establish the exact relationship between the fluorescence intensity and the concentration of the organic matter. Based on the analysis of the characteristics of laser-induced fluorescence spectroscopy, the error back propagation (BP) neural network which has powerful approximation ability in mapping complex nonlinear relationship, is applied to process the above-mentioned factors, to establish the exact relationship. By measuring organic solution with known concentration, and then using the data of fluorescence intensity-concentration of organic matter as a training set to train the BP neural network, accurate measurements has been achieved. The experimental results show that this method can accurately measure the dissolved organic content in water.