Research

Comparing deep learning with several typical methods in prediction of assessing chlorophyll-a by remote sensing: a case study in Taihu Lake, China
 

Paper Details

Comparing deep learning with several typical methods in prediction of assessing chlorophyll-a by remote sensing: a case study in Taihu Lake, China
Xiaolan Zhao,Haoli Xu,Zhibin Ding,Daqing Wang,Z. Deng,Yi Wang,Ting Wu,Wei Li,Zhao Lu,Guangyuan Wang
Water Supply
2021
https://app.readcube.com/library/eeeabbd4-b0f2-4d1d-af2b-b1d02dd21a9d/item/32a63361-37ef-41b9-890f-04d59ce81f51
10.2166/ws.2021.137

Add Data

Sample (n) Parameter Model/Algorithm Formula r^2 RMSE Study Area Satellite Reference


Formula Details

Sample (n) Parameter Model/Algorithm Formula r^2 RMSE Study Area Satellite Reference
32 Chl-a Linear Regression Y=-67.88532101122092*(B4/B3)+107.573046753554 0.00100000004749745 Taihu Lake, China Landsat 8
32 Chl-a Logarithmic Regression Y=39.74886869014925+ -63.28937890992608*log(B4/B3) 0.00100000004749745 Taihu Lake, China Landsat 8
32 Chl-a Inverse Y=-18.80174551607722 + 58.64419935909177/(B4/B3) 0.00100000004749745 Taihu Lake, China Landsat 8
32 Chl-a Quadratic Y=3,465.543442615852 + -7,638.402568342078*(B4/B3) + 4,262.740570842534*(B4/B3)*(B4/B3) 0.00400000018998981 Taihu Lake, China Landsat 8
32 Chl-a Cubic Y=2,378.697088001991 + -3,908.075599447289*(B4/B3) + 0*(B4/B3)*(B4/B3) + 1,621.809320132796*(B4/B3)*(B4/B3)*(B4/B3) 0.00400000018998981 Taihu Lake, China Landsat 8
32 Chl-a Compound Regression Y=2,503.918815021841*0.005752479108287114**(B4/B3) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a Power Y=14.85988184091882*(B4/B3)^(-4.582236735711132) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a S Y=e^(-1.33226861857868 + 4.060797975393096/(B4/B3)) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a Growth Y=e^(7.825612309578503= -5.158124367823692*(B4/B3)) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a Exponential Regression Y=2,503.918815021841*e^(-5.158124367823692*(B4/B3)) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a Logistic Regression Y=1/(0 + 0.0003993739709133802*173.8380933116968**(B4/B3)) 0.0199999995529652 Taihu Lake, China Landsat 8
32 Chl-a Back Propagation Neural Network (BP) B1 B2 B3 B4 B5 B6 B7 B8 B9 B10 B11 1.436 Taihu Lake, China Landsat 8 Mean squared error of testing: 1.436
32 Chl-a Rradial Basis Function (RBF) Neural Network B1 B2 B3 B4 B5 B6 B7 B8 B9 B10 B11 4.479 Taihu Lake, China Landsat 8 Mean squared error of testing: 4.479
32 Chl-a Deep Learning Neural Network (DNN) B1 B2 B3 B4 B5 B6 B7 B8 B9 B10 B11 4.356 Taihu Lake, China Landsat 8 Mean squared error of testing: 4.356