A Novel Resource and Distribution Aware Random Forest for Agricultural Productivity Prediction

Agriculture has continued being one of the economic powerhouses of India, but then the productivity is usually compromised due to the poor utilization of soil and environment data. This paper is a proposal of a new framework named Distribution and Resource Aware Random Forest (DRARF) to be used in smart farming applications. The strategy combines IoT-ready soil data that comprises of moisture, temperatures, humidity, pH, and NPK that are monitored via different sources and used to make crop-specific decisions. The DRARF presents two important novel features to traditional Random Forests: (i) distribution-aware threshold selection, which guarantees statistical meaningful data partition and (ii) resource-aware feature selection, which gives more predictive power without the expense of buying sensors in the IoT. It assessed the framework using soil and environmental data of wheat and rice. The comparative tasks performed using Logistic Regression, Support Vector Machine, Naïve Bayes, and the classical random Forest have shown that DRARF not only provides a better accuracy, precision, recall and F1-scores, but it also minimizes sensor redundancy. Its potential depends on its scalability, efficiency, and reliability as a precision agricultural decision-support system and this, as well as the remaining results, are reflected in the results. The given approach with machine learning and IoT-facilitated sensing source-based solutions can bring the advancements in the sphere of smart farming technologies to help increase the yield of crops and resources and improve long-term food security.