.. _Sensitivity analysis Discrete Dynamic:

Sensitivity analysis for Dynamic solution
==========================================

| The Sensitivity analysis for Dynamic solution provides the sensitivity of any output feature to the input features: each input feature is assigned a coefficient, varying between zero and one, depending on the sensitivity of the output to this input feature. 
| If a coefficient is equal to zero the corresponding input feature does not have any impact on the considered output. If a coefficient is equal to one, the considered output depends only on the corresponding input feature. The values in between allow to establish the relative importance of the input features. 

This functionality is based on the backpropagation computations, and its general idea is:

•	At a set of timepoints of a chosen output trajectory compute the gradients with respect to all input trajectories via the backpropagation
•	For each input calculate the norm of its obtained gradients 
•	Normalize the results, so that the sum of sensitivities to all inputs is equal to one

To perform the Sensitivity analysis:

* Switch to **Metrics** panel

* Choose the file in **Evaluation files** section:

  * If the file was supplied earlier, it is already listed in **Evaluation files**

  * To add new file for evaluation, press **+** in **Additional** section of **Evaluation files**
  
* Choose the type of initialization (see :std:ref:`Evaluate NeurEco Discrete Dynamic model with GUI` and :std:ref:`Metrics Discrete Dynamic`)

* Click on one of the output neurons (representing output features) on the plot in the **Network sensitivity** section

* Each input neuron (representing input features) becomes colored according to the sensitivity of the chosen output neurons with respect to this neuron and its sensitivity coefficient is showed in the plot

An example of the sensitivity analysis:


.. figure:: ../../../images/NetworkSensitivityExampleDatasetDynamic.png
    :width: 800
    :alt: Dynamic network sensitivity 
    :align: center

    Dynamic network sensitivity. Discrete Dynamic test case: :std:ref:`Temperature forecasting test case`.
	
.. Note::
    
	By default, the **Network sensitivity** is performed with the last model available in the checkpoint. Use the checkpoint slider in the bottom to choose any other available model.