Design and Development of Efficient Techniques to Monitor Environmental Parameters for Agriculture Applications

Abstract

Agriculture is a primary source of income for the majority of the population in India. To make farming more efficient and increase the production rate farmers can adapt scientific equipment like remote sensing and predictive analytics. Remote sensors are used to monitor environmental parameters such as water, rainfall, temperature, humidity, soil nutrients, soil pH etc., which vary from one place to another. Crop yield depends on these parameters and monitoring of these parameters will reduce potential environmental risk and gives updated status of plant health and also it helps in fertilizer management and pesticide application. This technological development in the field of agriculture is an essential requirement for national prosperity. In India, due to a lack of knowledge on technological approaches in farming on sowing patterns, irrigation schedule, and fertilizer application, farmers are not getting the expected yield. Predictive analytics will help in accurate yield prediction which requires understanding of functional relationship between yield and environmental parameters that is available in the form dataset. Modern digital farming uses dataset which consist of data from decades with various attributes required for yield prediction such as soil type, soil nutrients, soil pH, area of production, history of production etc., In conventional farming prediction is made by farmers experience which is time consuming and not very efficient. Therefore, a transition is required from conventional farming to digital farming, which is possible using data-driven models such as machine learning (ML), deep learning (DL), and Internet of Things (IoT) technologies. newline