Evaluation of the Effectiveness of Multiple Machine Learning Methods in Remote Sensing Quantitative Retrieval of Suspended Matter Concentrations: A Case Study of Nansi Lake in North China

Table 5

Operation results of the models.

Model		RMSE (mg/L)	ARE (%)
Single-band model	0.466	246.613	668.671
Binary linear model 1	0.614	8.679	44.233
Binary linear model 2	0.637	8.414	45.274
BPNN	0.921	4.142	8.69
KNN	0.678	8.277	16.67
Decision tree	0.897	3.387	10.05
AdaBoost	0.948	2.786	9.29
RF	0.969	2.135	7.02
GA_RF	0.980	1.715	6.83