• Mr. S. Thirumal
• Dr. R. Latha

India is the second largest rice producer which contributes around 20% of the world’s rice production. Rice crop is indispensable for majority of the world’s population, and therefore, correct prediction of rice production is paramount for development policies, trade, decision-makers, humanitarian assistance, and so on. Crop predicting, the art of forecasting agriculture production before the crop harvest take place, assist a many interested parties making superior decisions around agricultural decision-making. Accurate, reliable, and timely rice production forecasting in India is central for global health and food security problems. Statistical machine learning models and Classical mechanistic models should recognize patterns, creating the investigation on and application of these techniques time-consuming and laborious. Therefore, this study develops a Moth Flame Optimizer with Ensemble Machine Learning Driven Rice Crop Yield Prediction (MFOEML-RCYP) algorithm. The MFOEML-RCYP methodology exploits Z-score normalization to pre-process input characteristics, which ensures optimum data dissemination for succeeding analysis. To optimize predictive accuracy, an ensemble technique is introduced, integrating the strengths of various techniques such as Backpropagation Neural Network (BPNN), Wavelet Neural Network (WNN), and Light Gradient Boosting Machine (Light GBM). Moreover, parameter optimization is implemented by the Moth Flame Optimizer (MFO) for maximizing predictive outcomes and adjusting model parameters. Empirical outcomes illustrate the effectiveness of the presented MFOEML-RCYP technique in precisely predicting rice crop yields, emphasizing its prospective for enhancing crop management approaches and informing agricultural decision-making.

Crop Yield Prediction; Machine Learning; Moth Flame Optimizer; Fitness Function; Pre-processing

"Ensemble Machine Learning with Optimization Driven Rice Crop Yield Prediction Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.11, Issue 6, page no.h239-h250, June-2024, Available :http://www.jetir.org/papers/JETIR2406726.pdf

"Ensemble Machine Learning with Optimization Driven Rice Crop Yield Prediction Model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.11, Issue 6, page no. pph239-h250, June-2024, Available at : http://www.jetir.org/papers/JETIR2406726.pdf