Determination of Machine Learning and IOT Enabled Complete Architecture for Agriculture Applications | Chapter 2 | New Visions in Science and Technology Vol. 10

 Traditional agriculture models have some drawbacks, such as the risk cost and real execution without the necessary quality data. Soil additives such as moisture, nitrogen (N), phosphorus (P), and potassium are required for any crop's productivity improvement (K). To overcome the constraints of the traditional approach, we developed a model that uses deep learning and remote sensing to estimate soil fertility levels and productivity predictions. Current technological breakthroughs that provide foretelling form, which increases state-of-the-art precision agriculture. In the previous decade, the usage of machine learning (ML) techniques with IoT devices has developed in a variety of industries. The increasing accessibility of soil data enabled ML approaches to analyse and increase production, which was aided by the use of IoT. The first stage is to set up the physical environment, which includes placing IoT devices in the fields to gather soil parameters. In the second step, we create a dynamic model using a back-propagation neural network, a machine learning and deep learning method, to forecast soil attributes and evaluate the input data from the first phase using raw soil field data. Internet of Things (IoT) devices and connections for wireless communication with sensors are currently available for a variety of agricultural field work applications, including soil preparation, water management, and crop development status. State-of-the-art farm architecture based on IoT and deep learning identifies traditional limitations and provides relevant solutions. The major goal of this research paper is to look at how deep learning, specifically back propagation neural networks, may be used to predict soil attributes from spectral (raw) data from organic soils using inputs from various IoT sensors.

Author(S) Details

Shivnath Ghosh
Brainware University, Kolkata, West Bengal, India.

Santanu Koley
Haldia Institute of Technology, Haldia, West Bengal, India.

Pinaki Pratim Acharjya
Haldia Institute of Technology, Haldia, West Bengal, India.

Mihir Baran Bera
Haldia Institute of Technology, Haldia, West Bengal, India.

View Book:- https://stm.bookpi.org/NVST-V10/article/view/4881