DEVELOPMENT OF A HYDROPONICS SIMULATOR TO GENERATE GUIDELINES FOR DATA COLLECTION IN HYDROPONICS FOR MACHINE LEARNING APPLICATIONS
Published: 13 Nov 2023
Abstract: Hydroponics, a soilless growing method using nutrient-rich water solutions, offers distinct advantages in plant growth and resource efficiency. Data-driven optimization in hydroponics relies on precise control of environmental factors. To effectively apply data-driven optimization, comprehensive and accurate data describing hydroponic plant growth is essential. In the first part of the project and in this paper, we seek to identify critical parameters that influence plant growth, recommend optimal resolutions and measurement frequencies, and address challenges in data collection. Standardization of data collection procedures and establishment of data collection guidelines are fundamental to obtaining high quality, comparable and reproducible data. Establishing a standard for data collection will allow data from different experiments to be compared and used in future research. In the initial phase of the project and throughout this paper, our primary objective is to identify the relevant parameters affecting plant growth in a hydroponic system. These critical parameters encompass aspects such as light intensity, spectral composition, nutrient solution composition, water quality, pH levels, and more. By conducting a thorough investigation, we aim to recommend optimal resolutions for these parameters. Additionally, we will address the challenges associated with collecting data related to these key variables, ensuring that the data obtained is reliable and useful to further research and scientific exploration in the field of hydroponics. Accurate data on these characteristics enables data-driven decisions and methods, such as machine learning and machine vision, which in turn allow optimization of hydroponic productivity. The study conducted a comprehensive analysis and identified 30 essential parameters crucial for characterizing a hydroponic system. The findings are summarized as a list of relevant parameters that need to be measured or recorded to enable data-driven optimization of hydroponic systems.
Keywords: hydroponics, plant growth parameters, data driven optimization, machine learning, data acquisition, condition monitoring
Cite this article: Jonas W. Swiatek, Felix Kuthe, Loui Al-Shrouf, Mohieddine Jelali. DEVELOPMENT OF A HYDROPONICS SIMULATOR TO GENERATE GUIDELINES FOR DATA COLLECTION IN HYDROPONICS FOR MACHINE LEARNING APPLICATIONS. Journal of International Scientific Publications: Agriculture & Food 11, 321-333 (2023). https://www.scientific-publications.net/en/article/1002676/
Download full text
Back to the contents of the volume
© 2024 The Author(s). This is an open access article distributed under the terms of the Creative Commons Attribution License http://creativecommons.org/licenses/by/3.0/
, which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited. This permission does not cover any third party copyrighted material which may appear in the work requested.