Linear Z Score and Gaussian Radial Artificial Neural Network Big Data Analytics to Enhance Crop Yield

Crop yield estimation is a pivotal matter in agricultural management, specifically under the backdrop of demographic growth and changing climatic conditions. Many studies have been conducted employing remote sensing for crop yield estimation. However, most were specifically concentrated on condition-based environmental monitoring systems. A shortage of exclusive applications persists regarding the use of remote sensing for soil health monitoring and implementing necessary measures to enhance crop yield. To address such insufficiency, the Linear Z-score and Gaussian Radial Artificial Neural Network-based (LZ-GRANN) crop yield estimation method is proposed in this paper to enhance productivity. The performance evaluation of the proposed LZ-GRANN method reduced the overall crop yield estimation time and error by 59% and 58% and improved precision and accuracy by 23% and 26% in comparison with the existing methods.