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 4
Parameter settings of the machine learning models.
Machine learning model
Parameter settings
BPNN model
Hidden layer neuron function: log S-type function
Output function: linear function
Training function: momentum BP algorithm with variable learning rate
Number of iterations: 1000
Learning rate: 0.003
KNN model
Search algorithm: brute-force search algorithm
K: 4
The rest of the parameters: default settings
Decision tree model
Criterion: Gini
Splitter: best
Max_depth: none
Min_samples_split: 2
Min_samples_leaf: none
The rest of the parameters: default settings
AdaBoost model
Base_estimator: none
N_estimators: 60
Learning_rate: 0.85
Loss: linear
The rest of the parameters: default settings
RF model
Number of decision trees (k): 100
Number of features (m): 6
The rest of the parameters: default settings
GA_RF model
Population size: 10
Variation rates: 0.05
Maximum number of genetic generations: 500
Range of the number of decision trees: 5 to 1000; step size: 10
Range of number of features: 1 to 32; step size: 1
