physics.cfd.surrogate — net.clojars.helsingin/physics 0.1.4

Spatial surrogates for fluid prediction. Provides deterministic analytical fallbacks and a hook for plugging in future ML models. Returns structured flow fields plus provenance metadata so downstream correctors and translators can reason about confidence.

custom-tensor clj

(custom-tensor payload)

debris clj

(debris geometry params)

list-models clj

(list-models)

maritime clj

(maritime geometry environment params)

model-entry clj

(model-entry id)

plume clj

(plume geometry environment {:keys [emission-rate stability] :as params})

potential-flow clj

(potential-flow geometry {:keys [strength radius center] :as params})

predict clj

(predict {:keys [solver] :as opts})

register-model! clj

(register-model! {:keys [id path backend normalization metadata] :as opts})

Register an ML surrogate weight file plus normalization metadata.

options = {:id :meshgraphnet-v1 :path "models/mgn.onnx" :backend :onnx :normalization {:mean 0.0 :std 1.0} :metadata {:training-run "2025-02-10"}}