Machine learning-based smart irrigation system and soil nutrients analysis to increase productivity in agriculture field

Abstract

In agriculture, intelligent sensor approaches have gained a lot of attention in the past several years. Planning many operations and missions with limited resources and little human involvement is used in agriculture. New agricultural approaches are currently highly popular among producers like Machine learning.As a result of the technique,Machine learning helps keep the irrigation system appropriate. It optimizes water use, supplies the field with needed water and fertility, increases output, decreases handling, and decreases crop disease.Plants are grown in a growth chamber under completely controlled circumstances by misting them with a nutritional solution instead of dirt.Backpropagation networks(BPN) train BPN to discover the appropriate correlating proportion between the characteristics by providing reference crop growth properties and their capacity to supply nutrients from their reserves in both instances and external crop production applications. For all-weather circumstances, the system is updated immediately, and no water dispersion for crops occurs. By analyzing the cloud and monitoring the temperature, this set-up can rapidly feel the weather and be used as a water conservation device. Forecasting may be improved by gathering real-time weather, soil and air quality, and crop maturity data in order to make better judgments in the future. A data collecting system that generates and gathers information autonomously in isolated or remote areas is described in this study.A line-following robot regularly gathers soil moisture data from the sensor module and air temperature data from the sensor module. It uploads the data to a computer through a cloud connection for further analysis.