Atmospheric temperature and humidity profile retrievals using a machine learning algorithm based on satellite-based infrared hyperspectral observations

Fig. 2. Method implementation flowchart

Fig. 3. CNN model frame structure

Fig. 4. Temperature scatter diagram of retrieval. (a)-(c) Three classification schemes of BP neural network; (d)-(f) Three classification schemes of CNN

Fig. 5. Water vapor mixing ratio same as Fig.4

Fig. 6. Error profile of retrieval for temperature. (a)-(c) Three classification schemes, red is the bias, black is the root mean square error, dotted line is the BP neural network method, and the solid line is the CNN method; (d) Root mean square error profile of the three classification schemes of CNN, the solid line is the first scheme, the dotted line is the second scheme, and the dashed line is the third scheme

Fig. 7. Mean relative error profile of retrieval for temperature. (a)-(c) Three classification schemes, dotted line is the BP neural network method, and the solid line is the CNN method; (d) Mean relative error profile of the three classification schemes of CNN, the solid line is the first scheme, the dotted line is the second scheme, and the dashed line is the third scheme

Fig. 8. Water vapor mixing ratio same as Fig.6

Fig. 9. Water vapor mixing ratio same as Fig.7

Table 1. Training parameters of BP neural network

Table 1. Training parameters of BP neural network

Parameter	Set value	Attributes
Net.trainParam.epochs	10000	Training times
Net.trainParam.goal	0	Training goal
Net.trainParam.lr	0.01	Learning rate
Net.trainParam.mc	0.95	Momentum factor
Net.trainParam.show	25	Number of intervals displayed
Net.trainParam.min_grad	1×10⁻⁶	Minimum performance gradient

Table 2. Network training reference indicators for different convolution kernel sizes of conv_1

Table 2. Network training reference indicators for different convolution kernel sizes of conv_1

Convolution kernel size	Validation RMSE	Temperature retrieval RMSE/K	Training time
$ 3\times 1 $	0.8521	3.4625	12'48''
$ 4\times 1 $	0.8329	3.4217	13'14''
$ 5\times 1 $	0.8298	3.4137	14'20''
$ 6\times 1 $	0.8274	3.3871	15'00''

Table 3. Network training reference indicators for different output feature maps of conv_1

Table 3. Network training reference indicators for different output feature maps of conv_1

Number of output feature maps	Validation RMSE	Temperature retrieval RMSE/K	Training time
20	0.7916	3.2888	16'14''
30	0.7816	3.2427	22'47''
40	0.7730	3.2245	27'32''
50	0.7595	3.1698	27'55''
60	0.7617	3.1756	35'80''

Table 4. Complete structure of CNN model