PREDICTING THE IMPACT OF AIR POLLUTANTS ON RICE AND WHEAT USING MACHINE LEARNING

Agricultural crop production and quality can deteriorate when exposed to high concentrations of various air pollutants. Deterioration can range from visible markings on the foliage, to reduced growth and yield, to the premature death of the plant. Accurate prediction of crop development stages plays an important role in crop production management. Such predictions will also support the allied industries in strategizing the logistics of their business. An increase of atmospheric CO2 works as carbon fertilizer, improves plant growth and productivity of crops and negatively impacts the nutrients such as iron, zinc and crude protein contents in the grains. In this paper, we are proposing a web-based system for predicting the impact of air pollutants on crop quality and production using machine learning tools. We are considering parameters like SO2, NOX, Suspended Particulate Matter (SPM). These factors will help find the impact and complications of air pollutants present in our environment on crop yield. We are using Gradient Boosted Regressor for our work.