Welcome to the InfoSci Platform
Reference Hub6
An Intelligent Irrigation Scheduling and Monitoring System for Precision Agriculture Application

An Intelligent Irrigation Scheduling and Monitoring System for Precision Agriculture Application

RajinderKumar Mallayya Math, Nagaraj V. Dharwadkar
Copyright: © 2020 |Volume: 11 |Issue: 4 |Pages: 24
ISSN: 1947-3192|EISSN: 1947-3206|EISBN13: 9781799806967|DOI: 10.4018/IJAEIS.2020100101
Cite Article Cite Article

MLA

Math, RajinderKumar Mallayya, and Nagaraj V. Dharwadkar. "An Intelligent Irrigation Scheduling and Monitoring System for Precision Agriculture Application." IJAEIS vol.11, no.4 2020: pp.1-24. http://doi.org/10.4018/IJAEIS.2020100101

APA

Math, R. M. & Dharwadkar, N. V. (2020). An Intelligent Irrigation Scheduling and Monitoring System for Precision Agriculture Application. International Journal of Agricultural and Environmental Information Systems (IJAEIS), 11(4), 1-24. http://doi.org/10.4018/IJAEIS.2020100101

Chicago

Math, RajinderKumar Mallayya, and Nagaraj V. Dharwadkar. "An Intelligent Irrigation Scheduling and Monitoring System for Precision Agriculture Application," International Journal of Agricultural and Environmental Information Systems (IJAEIS) 11, no.4: 1-24. http://doi.org/10.4018/IJAEIS.2020100101

Export Reference

Mendeley
Favorite Full-Issue Download

Abstract

In spite of technological advancements, the farm productivity of Indian agriculture is still on the lower side. The underlying reason for poor farm productivity in India is due to the inefficient usage of agricultural inputs, resulting in low or poor-quality agricultural yields. Water happens to be one of such imperative agricultural input that has a huge impact on agricultural productivity. Precision agriculture systems can take care of irrigation requirements by optimally and efficiently using irrigation water for producing crops having superior quality and quantity. This work proposes a smart irrigation system that can efficiently manage the water requirements of the crop for its optimal growth. The irrigation schedules are developed using a feed forward neural network model that can predict the variation in the soil moisture considering the environmental factors such as temperature, humidity, atmospheric pressure, and the rain. The results indicate the effectiveness of the developed system in predicting the soil moisture with mean square error as low as 0.13 and the R value as high as 0.98.