neuralop.models.OTNO

class neuralop.models.OTNO(*args, **kwargs)[source]

Optimal Transport Neural Operator

The architecture is described in [1].

OTNO integrates optimal transport (OT) into operator learning for partial differential equations (PDEs) on complex geometries.

Parameters:

All arguments are the same as :class:`neuralop.models.FNO`.

See the FNO documentation for detailed descriptions.

Attributes:

device

Returns the device that the model is on.

Methods

forward(x, ind_dec, **kwargs)

OTNO's forward pass

References

[1]

Li, X., Li, Z., Kovachki, N., & Anandkumar, A. “Geometric Operator Learning with Optimal Transport” (2025). arXiv preprint arXiv:2507.20065. https://arxiv.org/pdf/2507.20065

property device

Returns the device that the model is on.

forward(x, ind_dec, **kwargs)[source]

OTNO’s forward pass