SISTEM KENDALI KADAR AIR TANAH PADA TANAMAN TOMAT CERI MENGGUNAKAN MIKROKONTROLER ESP32 DENGAN ALGORITMA LONG SHORT TERM MEMORY
Abstract
Abstrak
Kadar air tanah merupakan salah satu pengaruh terbesar dalam pertumbuhan tanaman khususnya tanaman tomat ceri untuk tumbuh. Akan tetapi pengairan air pada tumbuhan tomat ceri sampai saat ini masih dilakukan secara manual, menjadikan alasan mengapa kurang baik dan efisien dalam perawatan tumbuhan tomat ceri. Penelitian ini bertujuan untuk merancang sistem untuk mengendalikan kadar air pada tanah dengan bantuan sensor dan sistem pemantauan berbasis algoritma Long-Short Term Memory, data yang pernah terkoleksi dijadikan sebagai referensi untuk prediksi aktifasi stepper motor dimasa datang pada rumah kaca. Hasil penelitian ini menunjukkan pertumbuhan tanaman tomat ceri dengan sistem kendali kadar air memiliki pertumbuhan yang lebih baik yaitu 18.5cm dibandingkan dengan tanaman tomat ceri dengan kadar air perhari yang sama ataupun kadar air yang lebih banyak yaitu 15.5cm, serta prediksi motor untuk mengairi tanaman tomat memiliki performa estimasi error sebesar 0.39 mean absolute error.
Kata-kata kunci: tanaman tomat ceri, time-series prediction, kadar air tanah
Abstract
Soil moisture is one of the biggest influences on the growth of any plant especially cherry tomato plants. However, water irrigation in cherry tomato plants has been carried out manually until now, which is the reason why it is not good and efficient in plant care, especially for cherry tomatoes. This study aims to design a system to control the water content in the soil with the help of sensors and use a Long-Short Term Memory algorithm to predict the next time the stepper motor activates in a greenhouse. The results of this study showed that the growth of cherry tomato plants with a moisture control system had better growth of 18.5cm compared to cherry tomato plants with the same daily water content or higher water content of 15.5cm, as well as prediction of the motor for irrigating plants, has an error estimation performance of 0.39 mean absolute error.
Keywords: cherry tomato plants. time-series prediction, soil moisture
References
R. R. Shamshiri et al., “Review of optimum temperature, humidity, and vapour pressure deficit for microclimate evaluation and control in greenhouse cultivation of tomato: a review,” Int. Agrophys, vol. 32, no. 2, pp. 287-302, 2018, doi: 10.1515/intag-2017-0005.
K. E. Alordzinu et al., “Water stress affects the physio-morphological development of tomato growth,” Journal of Agricultural Research, vol. 17, no. 5, pp. 733-742, 2021, doi: 10.5897/AJAR2021.15450.
H. H. Sak, A. Senior, B. Google, “Long Short-Term Memory Recurrent Neural Network Architectures for Large Scale Acoustic Modeling,” 2014.
P. R. Karthikeyan et al., “IoT Based Moisture Control and Temperature Monitoring In Smart Farming,” Journal of Physics: Conference Series, vol. 1964, no. 6, p. 062056, 2021, doi: 10.1088/1742-6596/1964/6/062056.
G. Van Houdt, C. Mosquera, and G. Nápoles, “A review on the long short-term memory model,” Artificial Intelligence Review, vol. 53, no. 8, pp. 5929-5955, 2020, doi: 10.1007/S10462-020-09838-1.
A. S. Bayangkari Karno, “Analisis Data Time Series Menggunakan LSTM (Long Short Term Memory) Dan ARIMA (Autocorrelation Integrated Moving Average) Dalam Bahasa Python,” Ultima InfoSys: Jurnal Ilmu Sistem Informasi, vol. 11, no. 1, pp. 1-7, 2020, doi: 10.31937/SI.V9I1.1223.
