A Review on Digital Farming using Machine Learning Techniques | IEEE Conference Publication | IEEE Xplore

A Review on Digital Farming using Machine Learning Techniques


Abstract:

To compensate rainfall shortages and improve irrigation delivery for plants development, fresh water is necessary. Agricultural activities use more than 70% of the availa...Show More

Abstract:

To compensate rainfall shortages and improve irrigation delivery for plants development, fresh water is necessary. Agricultural activities use more than 70% of the available freshwater resources. This study highlights the need for effective water management, which involves the application of digitized agricultural technology. In addition to, this study intends to merge multiple machine learning models to provide the best irrigation monitoring process. The emerging trend and application of machine learning models, as well as the application of established machine learning algorithms to perform long-term irrigation management are also analyzed. Finally, this study discusses how digital farming tools, including such smartphone and web applications, may support farmers in managing smart irrigation operations in a cost-effective manner.
Date of Conference: 13-15 December 2022
Date Added to IEEE Xplore: 07 February 2023
ISBN Information:
Conference Location: Pudukkottai, India
No metrics found for this document.

I. Introduction

The agriculture industry uses around 85 percent of freshwater resources globally due to population rise [1]. An increase in food production is required. Traditional irrigation management has several disadvantages, including inefficient water usage and low productivity. Anthropogenic global warming also has an effect on the quantity of raindrops necessary to provide water to crops [2], [3]. Crop water consumption and biological impacts are therefore seasonal, vary per plant, and are impacted by external variables such as weather. On a greenhouse, the environment can be managed, but in an isolated field farm, these features are difficult to control [4]. The varied environmental factors must be considered.

Usage
Select a Year
2025

View as

Total usage sinceFeb 2023:100
012345JanFebMarAprMayJunJulAugSepOctNovDec400000000000
Year Total:4
Data is updated monthly. Usage includes PDF downloads and HTML views.

References

References is not available for this document.