Modeling Languages

ModelingToolkit

ParameterizedFunctions

Model Libraries and Importers

ModelingToolkitStandardLibrary

ModelingToolkitNeuralNets

DiffEqCallbacks

FiniteStateProjection

ReactionNetworkImporters

Symbolic Tools

ModelOrderReduction

SymbolicIntegration

SymbolicAnalysis

Array Libraries

RecursiveArrayTools

ComponentArrays

MultiScaleArrays

Equation Solvers

DifferentialEquations

DifferenceEquations

Inverse Problems / Estimation

SciMLSensitivity

DiffEqParamEstim

PDE Solvers

NeuralOperators

DiffEqOperators

FiniteVolumeMethod

FiniteVolumeMethod1D

Advanced Solver APIs

BoundaryValueDiffEq

Parameter Analysis

EasyModelAnalysis

GlobalSensitivity

StructuralIdentifiability

Third-Party Parameter Analysis

Uncertainty Quantification

SciMLExpectations

Function Approximation

ReservoirComputing

Implicit Layer Deep Learning

DeepEquilibriumNetworks

Symbolic Learning

DataDrivenDiffEq

SymbolicNumericIntegration

Third-Party Differentiation Tooling

SparseDiffTools

Numerical Utilities

ExponentialUtilities

DiffEqNoiseProcess

PreallocationTools

EllipsisNotation

DataInterpolations

DataInterpolationsND

QuasiMonteCarlo

RuntimeGeneratedFunctions

FindFirstFunctions

SparseDiffTools

BipartiteGraphs

High-Level Interfaces

SciMLStructures

SymbolicIndexingInterface

Third-Party Interfaces

StaticArrayInterface

Developer Documentation

DiffEq Developer Documentation

Extra Resources

Extended SciML Tutorials

The SciML Benchmarks

ModelingToolkitCourse

Commercial Support

JuliaHub offers commercial support for ModelingToolkit and the SciML ecosystem. Contact us today to discuss your needs!

Products built with SciML

Dyad
Pumas
Cedar EDA
Neuroblox
Planting Space

/

NeuralPDE.jl: Automatic Physics-Informed Neural Networks (PINNs)
ODE PINN Tutorials
PDE PINN Tutorials
Extended Examples
Manual
Developer Documentation
- Debugging PINN Solutions

Version

Manual
Logging Utilities

Logging Utilities

Logging Utilities

NeuralPDE.LogOptions — Type

LogOptions(log_frequency)
LogOptions(; log_frequency = 50)

Options for logging during optimization.

« Adaptive Loss Functions Transfer Learning with neural_adapter »

Powered by Documenter.jl and the Julia Programming Language.

Settings

Theme

This document was generated with Documenter.jl version 1.17.0 on Thursday 9 April 2026. Using Julia version 1.12.5.