NAN in multivariant stochastic SEIR Model

[nijawa]

Bug description

NAN in compartments in SEIR2V Model

Version

Windows

To reproduce

1. build code
2. execute sde_seir2v_example
   (https://github.com/SciCompMod/memilio/blob/1009-nan-in-multivariant-seir-model/cpp/examples/sde_seir2v.cpp)
   

Relevant log output

No response

Add any relevant information, e.g. used compiler, screenshots.

No response

Checklist

• Attached labels, especially loc:: or model:: labels.
• Linked to project

[nijawa]

I use std::min and std::max instead of std::clamp to ensure that flows are in the correct bonds. Usage of std::clamp gives a "invalid bounds arguments passed to std::clamp" error which is consistent with the NAN output

[mknaranja]

@nijawa : Yes, nan is probably an incorrect input but clamp should prevent any appearance of nan beforehand. So there's potentially another problem? My questions still is "How does the nan appear?" Can you do a break point before the first nan and check what the actual miscomputation is?

[nijawa]

@mknaranja At t = 21.5 we have the compartment InfectedV1V2 at 0.014175747933863577 with an ingoing flow of 0 and an outgoing flow of 0.14175747933863578. With step size = 0.1 that would be 0.014175747933863577 - 0.014175747933863578 in the next step which would be negative. It is displayed as -0.0000 but with higher precision the value seems to be -1.73472347597681e-18. A negative compartment will of course result in nan.

I suspect that the issue is that we dont minimize the flow to the compartment but rather we minimize it to compartment / step_size. compartment / step_size * step_size can differ from compartment in floating point calc.

I dont have a good way to resolve this right now

[nijawa]

Clamping/maximizing with compartment / step_size - eps might work

[mknaranja]

I think that compartment / step_size * step_size can differ from compartment is not the problem, that basically is the thing for all flops. The problem, as you state, rather is that we do not have a tolerance like eps here. Can you make a suggestion based on @reneSchm's already suggested changes? You can now branch from main.