Skip to main content

Table 3 List of variables

From: Gaussian mutation–orca predation algorithm–deep residual shrinkage network (DRSN)–temporal convolutional network (TCN)–random forest model: an advanced machine learning model for predicting monthly rainfall and filtering irrelevant data

Variables

Definition

\(AP_{j}^{t}\)

The awareness probability of the crow

\(CR_{j}^{it}\)

The ith location of crow in the jth dimension

e

random number

\(F\)

The controller parameter

\(f\left( {OR_{chase,i}^{t} } \right)\)

The objective function of the new location of the orca

\(f\left( {OR_{i}^{t} } \right)\)

The objective function value of the current location of the orca

J

The average location of one group

\(M_{j}^{i}\)

The ith memory in the jth dimension

\(\max \left( {it} \right)\)

maximum number of iterations

NU

number of total inputs

\(or_{N}\)

The location of the Nth orca

\(or_{1}\)

The location of the first orca

\(OR\)

A group of orcas

\(OR_{chase,1,i}\)

The location of orca based on the first scenario

\(OR_{chase,1,i}\)

The location of orca based on the second scenario

\(OR_{best}^{t}\)

The location of best orca

\(p_{i}\)

The local best solution

\(p_{g}\)

The global best solution

\(r_{1}\)

Random numbers,

\(RI_{ob}\)

Observed rainfall

\(RI_{es}\)

Estimated rainfall

\(s_{i} \left( t \right)\)

The ith solution

\(SO_{i}^{t + 1}\)

The new solution

\(SO_{m,j}^{t}\)

The jth- solution

t

iteration number

T

maximum number of iterations

u

Random number

\(ve_{i} \left( {t + 1} \right)\)

The ith velocity at iteration (t + 1)

\(VE_{chase,1,i}\)

The velocity of orca based on the first scenario

\(VE_{chase,2,i}\)

The velocity of orca based on the second scenario

x

Input feature

\(X_{j}^{t + 1}\)

The jth location at t + 1 iteration

\(Y_{j}^{t}\)

The current location of crow

z

Output

\(\mu\)

random parameter

\(\beta\)

Random number

\(\varphi\)

Threshold value

\(\alpha\)

Random number