Algorithm 1. Pseudo code for optimization for the environmental and economic nonlinear model by ANN-GA-IPA.

Start GA  Inputs: To measure the chromosomes of the same network element as:  W = [$\mathit{n}$,$\mathit{w}$,$\mathit{l}$]  Population: Set of chromosome is given as:  ${\mathit{W}}_X=[{\mathit{n}}_X,{\mathit{\omega }}_X,{\mathit{l}}_X]$, ${\mathit{W}}_Y=[{\mathit{n}}_Y,{\mathit{\omega }}_Y,{\mathit{l}}_Y]$ and ${\mathit{W}}_Z=[{\mathit{n}}_Z,{\mathit{\omega }}_Z,{\mathit{l}}_Z]$.  Output: Global weight values are WGB  Initialization: To adjust the chromosomes selection, adjust the WGB.  Fit Estimation: Modify the values of FIT (E) using the  population (P) for systems 4 to 8 Stopping standards: Terminate if [Iterations = 60], [E = 10−06], [TolCon = 10−10], [StallLimit = 120], [TolFun = 10−10] & [PopSize = 200]. Go to storage  Ranking: For the FIT (E), rank WGB in population.  Storage: Store WGB, time, iterations, E & count of function for the  GA. GA process Ends IPA Starts  Inputs: WGB is the Start point:  Output: The best GAIPA weights are represented as WGIPA   Initialize: Iterations, Assignments & WGB.  Terminating Standards: Stop, if [E = 10−12], [MaxFunEvals = 100,000], [TolX = 10−12], [TolFun = 10−12] & [Iterations = 500].  FIT approximation: Compute FIT & WGIPA using Equations (4) to (8).  Amendments: Regulate ‘fmincon’ for the values of IPA, E to  improve the ‘W’ for Equations (4)–(8).  Accumulate: Transform WGIPA, function counts, time FIT,  iterations for the IPA present runs. IPA End