Modeling Water Productivity and Yield Response of Aerobic Rice under Drip Irrigation

Abstract

The increasing demand for water-efficient rice cultivation systems has driven the need for advanced modeling approaches to evaluate water productivity and yield response under alternative irrigation methods. This study focuses on modeling water productivity and yield response of aerobic rice under drip irrigation to enhance resource use efficiency and sustainable production. The proposed methodology involves the integration of field experimental data with data-driven and simulation-based modeling techniques. Multi-source datasets, including soil moisture levels, irrigation schedules, climatic variables, and crop growth parameters, are collected and preprocessed through cleaning, normalization, and feature engineering to ensure consistency and accuracy. Advanced analytical and machine learning models, such as regression analysis, Random Forest, and Artificial Neural Networks, are employed to capture the relationship between water input and yield performance. The system is trained and validated using region-specific datasets to ensure robustness under varying agro-climatic conditions. Experimental results demonstrate that drip irrigation in aerobic rice significantly improves water productivity by reducing water losses through evaporation and percolation while maintaining competitive yield levels. The modeling framework accurately predicts yield response under different irrigation regimes and identifies optimal water application strategies. Additionally, the study highlights improved water use efficiency and reduced input costs compared to traditional flooded rice cultivation. The findings emphasize the effectiveness of integrating modeling techniques with efficient irrigation systems for precision agriculture. The study concludes that drip-irrigated aerobic rice systems, supported by intelligent modeling approaches, offer a scalable and sustainable solution for enhancing water productivity, optimizing yield, and ensuring long-term agricultural sustainability.