LSTM Based Prediction of Total Dissolved Solids in Hydroponic System

DOI

10.2991/adics-es-19.2019.13How to use a DOI?

Keywords

LSTM, forecasting, hydroponic, total dissolved solids

Abstract

This paper discusses the implementation of long short term memory (LSTM) for forecasting the value of total dissolved solids (TDS). The TDS value in a hydroponic system represents the number of nutrients contained in water. The amount of water in the hydroponic system is important to note because optimal plant growth depends on the number of nutrients obtained by the plant. TDS data is sequential data, and one way to do forecasting is to use LSTM. This study uses a combination of epoch values of 100, 200, 300, 400 and 500. The RMSE values of on any combinations 57.41, 50.90, 57.81, 67.60 and 26.62. In general, the smallest RMSE value of each combination produces a graph that is close to except for a 70%: 30% combination. The greater use of training data compared to test data (90%: 10%) results in the smallest average RMSE value of 35.48.

Copyright

© 2019, the Authors. Published by Atlantis Press.

Open Access

This is an open access article distributed under the CC BY-NC license (http://creativecommons.org/licenses/by-nc/4.0/).

Download article (PDF)

TY  - CONF
AU  - Riky Puriyanto
AU  - Supriyanto
AU  - Anton Yudhana
PY  - 2019/11
DA  - 2019/11
TI  - LSTM Based Prediction of Total Dissolved Solids in Hydroponic System
BT  - Proceedings of the 2019 Ahmad Dahlan International Conference Series on Engineering and Science (ADICS-ES 2019)
PB  - Atlantis Press
SP  - 7
EP  - 10
SN  - 2352-5401
UR  - https://doi.org/10.2991/adics-es-19.2019.13
DO  - 10.2991/adics-es-19.2019.13
ID  - Puriyanto2019/11
ER  -