This pipeline is absolutely principal in doing the actual linear inversion. Currently, we have all these scattered solutions to also scattered problems. We have to get these together, implement a smooth program where we can plug-in-play with different combinations of these solutions, this requires an architecture shown as below:

With the implementation of this architecture, we have to do some testing before 22nd. We really need to know if the current optical design’s ability to differentiate npv and soil is good enough. To determine this, assuming that our spectral library has the simulated data of current optical design, we will try different combinations of these sub-algorithms and solutions to come up with the most satisfactory result.

This way, we can at least determine if the current optical design is not going to work. Note that this working does not necessarily mean our design will work as expected, further unexpected errors are really plausible. Therefore, this method is only to try and prove if the old design is not going to work, it won’t be able to prove that it’ll work.

Umm What the Sigma?