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 2

Feature vector.

Feature vector	Pearson’s correlation coefficient
Band difference algorithm
(498.04–508.22) nm	0.5527
(2092.84–2133.24) nm	0.5773
(528.57–569.27) nm	0.6112
(1648.90–2213.92) nm	0.6248
Band ratio algorithm
(1457.23/1991.96) nm	0.5485
(2082.75/2102.94) nm	0.5497
(498.04/508.22) nm	0.5945
(528.57/569.27) nm	0.6076
Band NDI algorithm
(2082.75–2123.13)/(2082.75 + 2123.13) nm	0.5614
(498.04–508.22)/(498.04 + 508.22) nm	0.5926
(528.57–569.27)/(528.57 + 569.27) nm	0.6074