STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)

Basic needs are increasing as the population increases. This can lead to the conversion of agricultural land into community habitation so that it can reduce crop yields from agriculture. For this reason, an agricultural method is needed in order to produce basic needs in conditions of narrow land...

Full description

Saved in:
Bibliographic Details
Main Author: Armando Putra, Rifky
Format: Final Project
Language:Indonesia
Online Access:https://digilib.itb.ac.id/gdl/view/73114
Tags: Add Tag
No Tags, Be the first to tag this record!
Institution: Institut Teknologi Bandung
Language: Indonesia
id id-itb.:73114
spelling id-itb.:731142023-06-15T09:33:11ZSTUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT) Armando Putra, Rifky Indonesia Final Project Control, Hydroponics, Internet of Things, Machine Learning. INSTITUT TEKNOLOGI BANDUNG https://digilib.itb.ac.id/gdl/view/73114 Basic needs are increasing as the population increases. This can lead to the conversion of agricultural land into community habitation so that it can reduce crop yields from agriculture. For this reason, an agricultural method is needed in order to produce basic needs in conditions of narrow land, one of the methods is hydroponics. Hydroponics is the cultivation of plants that utilize water with an emphasis on providing sufficient nutrients. To increase production from vegetables, modifications were made to the hydroponic system where with the help of machine learning to obtain a better growth model by controlling nutrient levels. In this study, a nutrient control system was created in hydroponic kale plants using an STM 32 controller, which can provide a dose of ABMix nutrients with the required PPM (Part Per Million) which aims to meet the needs of oxygen and substances needed by plants for survival. A system that regulates nutrient levels is expected to produce better growth. The data used for machine learning are solution concentration, humidity, solution temperature, environmental temperature and light intensity as independent variables and stem height as dependent variables. Measurements of each variable were carried out for 22 days. For the concentration of the solution (nutrients) it is divided into 2 trials, namely with the ratio of nutrient A, nutrient B and water 9ml: 9ml: 1L and 4.5ml: 4.5ml: 1L. The models used are Random Forest and Gradient Boosting. The results of the analysis show that the model used to predict growth has an error function in the form of R 2 = 0.9154 and MAE (Mean Absolute Error) = 1.89% for Random Forest and R 2 = 0.7986 and MAE = 4.24% for Gradient Boosting. For the ratio of nutrients A, B and water it is better 9ml:9ml:1L where the height is 51cm and weight is 145gr. text
institution Institut Teknologi Bandung
building Institut Teknologi Bandung Library
continent Asia
country Indonesia
Indonesia
content_provider Institut Teknologi Bandung
collection Digital ITB
language Indonesia
description Basic needs are increasing as the population increases. This can lead to the conversion of agricultural land into community habitation so that it can reduce crop yields from agriculture. For this reason, an agricultural method is needed in order to produce basic needs in conditions of narrow land, one of the methods is hydroponics. Hydroponics is the cultivation of plants that utilize water with an emphasis on providing sufficient nutrients. To increase production from vegetables, modifications were made to the hydroponic system where with the help of machine learning to obtain a better growth model by controlling nutrient levels. In this study, a nutrient control system was created in hydroponic kale plants using an STM 32 controller, which can provide a dose of ABMix nutrients with the required PPM (Part Per Million) which aims to meet the needs of oxygen and substances needed by plants for survival. A system that regulates nutrient levels is expected to produce better growth. The data used for machine learning are solution concentration, humidity, solution temperature, environmental temperature and light intensity as independent variables and stem height as dependent variables. Measurements of each variable were carried out for 22 days. For the concentration of the solution (nutrients) it is divided into 2 trials, namely with the ratio of nutrient A, nutrient B and water 9ml: 9ml: 1L and 4.5ml: 4.5ml: 1L. The models used are Random Forest and Gradient Boosting. The results of the analysis show that the model used to predict growth has an error function in the form of R 2 = 0.9154 and MAE (Mean Absolute Error) = 1.89% for Random Forest and R 2 = 0.7986 and MAE = 4.24% for Gradient Boosting. For the ratio of nutrients A, B and water it is better 9ml:9ml:1L where the height is 51cm and weight is 145gr.
format Final Project
author Armando Putra, Rifky
spellingShingle Armando Putra, Rifky
STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
author_facet Armando Putra, Rifky
author_sort Armando Putra, Rifky
title STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
title_short STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
title_full STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
title_fullStr STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
title_full_unstemmed STUDY ON HYDROPONIC NUTRITION CONTROL ON GROWTH OF WATER SPINACH (IPOMOEA AQUATIC F.) BASED ON THE INTERNET OF THINGS (IOT)
title_sort study on hydroponic nutrition control on growth of water spinach (ipomoea aquatic f.) based on the internet of things (iot)
url https://digilib.itb.ac.id/gdl/view/73114
_version_ 1822992843759681536