The Dynamics of Ground Consolidation Through Soil Penetration Resistance and Artificial Neural Networks

Abstract

Ground consolidation, a consequence of intensive farming practices, poses challenges to soil health and mechanical properties. Assessing Ground consolidation is vital for effective tillage and machinery selection in agriculture. Soil Penetration Resistance (SPR) serves as a key indicator, impacting water uptake, root growth, and overall crop yields. This study explores the intricate relationship between SPR and various soil properties, including moisture, bulk density, texture, and organic carbon. Laboratory determination of SPR is expensive and time consuming, leading to efforts to predict SPR using indirect methods and mathematical models based on easily accessible soil properties. The study employs Artificial Neural Networks (ANN) to predict SPR under diverse conditions, considering the impact of tractor speed and soil moisture. The research aims to enhance understanding, refine prediction models, and contribute to sustainable agricultural practices. The methodology involves comprehensive field experiments, soil sampling, and advanced modeling techniques. The results demonstrate the significance of soil texture and moisture in SPR predictions, emphasizing the potential of ANN models for accurate assessments. The study contributes valuable insights into Ground consolidation, supporting improved land management and environmental sustainability in agriculture