Retrieving volume FeO and TiO2 abundances of lunar regolith with CE-2 CELMS data using BPNN method*

The volume FeO and TiO2 abundances (FTAs) of lunar regolith will be more important to understand the geological evolution of the Moon compared to the optical and gamma-ray results. In this paper, the volume FTAs are retrieved with the microwave sounder (CELMS) data from Chang’E-2 satellite using the back propagation neural network (BPNN) method. Firstly, a three-layered BPNN network with five-dimension input is constructed by taking nonlinearity into account. Then, the brightness temperature (TB) and surface slope are set as the inputs and the volume FTAs are set as the outputs of the BPNN network. Thereafter, BPNN network is trained with the corresponding parameters collected in Apollo, Luna, and Surveyor missions. Finally, the volume FTAs are retrieved with the trained BPNN network using the four-channel TB concluded from the CELMS data and the surface slope estimated from LOLA data. The rationality of the retrieved FTAs is verified by comparing with the Clementine UV-VIS results and LP-GRS results. The retrieved volume FTAs enable us to re-evaluate the geological features of the lunar surface. Several important results are as follows. Firstly, very-low-Ti (<1.5 wt.%) basalts are the most spatially abundant, and the surfaces with TiO2 > 5 wt.% constitute less than 10% of the maria. Also, there occur two linear relationships between the FeO abundance (FA) and the TiO2 abundance before and after the threshold, 16 wt.% of FA. Secondly, a new perspective about the mare volcanism is concluded with the volume FTAs in several important mare basins, although the conclusion should be severely treated with more sources of data. Thirdly, the FTAs in the lunar regolith change from depth to the uppermost surface, and the change is complex over the lunar surface. Finally, the distribution of the volume FTAs hints that the highlands crust is probably homogeneous at least in the microwave thermophysical parameters. ∗ Corresponding author 2 C. Liu, H.-Y. Sun, Z.-G. Meng, et al.