Modeling of Chaotic Political Optimizer for Crop Yield Prediction

Crop yield is an extremely difficult trait identified using many factors like genotype, environment and their interaction. Accurate Yield Prediction (CYP) necessitates the basic understanding of functional relativity among yields collaborative factor. Disclosing such connection requires both wide-ranging datasets efficient model. The CYP important to accomplish irrigation scheduling assessing labor necessities for reaping storing. Predicting various kinds effective optimizing resources, but a process owing existence distinct factors. Recently, Deep Learning (DL) approaches offer solutions complicated data weather parameters, maturity groups, etc. In this aspect, paper presents Automated utilizing Chaotic Political Optimizer with (ACYP-CPODL) proposed ACYP-CPODL technique involves different processes namely pre-processing, prediction parameter optimization. addition, hybrid Convolutional Neural Network (CNN) Long-Short Term Memory (LSTM) designed process. Moreover, hyperparameter tuning CNN-LSTM approach performed by CPO algorithm. has produced result MSE 0.031 R2 Score 0.936, whereas BLSTM model near-optimal results. As result, method proven be tool predicting crop yields. For validating improved predictive performance technique, wide range simulations take place on benchmark comparative results highlighted betterment over recent methods.