Artificial Intelligence and Its Applications in Agriculture With the Future of Smart Agriculture Techniques

Artificial Intelligence and Its Applications in Agriculture With the Future of Smart Agriculture Techniques

Harshit Bhardwaj (Gautam Buddha University, India), Pradeep Tomar (Gautam Buddha University, India), Aditi Sakalle (Gautam Buddha University, India) and Uttam Sharma (Gautam Buddha University, India)
DOI: 10.4018/978-1-7998-1722-2.ch002
OnDemand PDF Download:
No Current Special Offers


Agriculture is the oldest and most dynamic occupation throughout the world. Since the population of world is always increasing and land is becoming rare, there evolves an urgent need for the entire society to think inventive and to find new affective solutions to farm, using less land to produce extra crops and growing the productivity and yield of those farmed acres. Agriculture is now turning to artificial intelligence (AI) technology worldwide to help yield healthier crops, track soil, manage pests, growing conditions, coordinate farmers' data, help with the workload, and advance a wide range of agricultural tasks across the entire food supply chain.
Chapter Preview


Agriculture automation(Jha et. al., 2019) is a major concern and an evolving challenge for every region. The population worldwide is growing rapidly and the need for food is growing rapidly with the increase in population. Traditional methods used by farmers to serve growing demand are not enough and therefore they must hinder the soil through intensified use of harmful pesticides. This has a great influence on agriculture, and, at the end of the day, the earth remains unfertile. There are fields that affect agriculture issues such as crop pests, lack of storage space, pesticide control, plant management, irrigation and water management. Artificial intelligence will overcome all of this.

The history that follows covers AI state-of - the-art and agriculture's potential.The expert systems focused on smart agriculture systems were developed by (Shahzadiet al., 2016). The IoT concept in this system consisted of sending the data to the server in order to make appropriate decisions by the actuators in the field.

In order to estimate soil moisture in Paddy areas (Arifet al., 2012) built two ANN models with substantially less weather data. The analysis of measured soil and calculated soil humidity values has corroborated and tested all models.

The (Hinnellet al., 2012) address neuro-drip irrigation systems in which ANNs have been established to simulate the spatial surface water flow. Water distribution at the lower level of the soil is of major importance for the proper operation of the irrigation system. Here, ANNs makes the prediction that is useful to the user and leads to a rapid decision-making process.

The new field of embedded intelligence analysis (EI) was founded by (Yong et al., 2018). Smart planting, smart field production, smart irrigation and sophisticated greenhouses are part of the agricultural embedded intelligence. For a nation to be able to grow these growing technologies in the agriculture sector, many sectors depend on agriculture.

Complete Chapter List

Search this Book: