Development of long short-term memory models using rainfall and soil moisture to predict soil moisture dynamics
PLOS One · 21.07.2026 · 21 (7) · e0353268
DOI: 10.1371/journal.pone.0353268 ↗Kurz gefasst
Fachartikel in der Zeitschrift PLOS One, online erschienen am 21.07.2026. Verfasst von Yoon Ji Kim und 7 weiteren Autor:innen. Beteiligte Einrichtung: Department of Horticulture, Chonnam National University, Gwangju, Republic of Korea. Hauptthemen laut MEDLINE: Soil, Rain, Water, Models, Theoretical. Die Arbeit nennt 59 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: Rural Development Administration, Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry.
Abstract (Originalsprache)
Long short-term memory (LSTM) models were developed using rainfall and soil moisture data to predict soil moisture at various depths in an Asian pear orchard. Two types of rainfall inputs were tested: hourly rainfall data treated as individual values and event-based rainfall data, where cumulative rainfall was calculated by applying the minimum inter-event time threshold (12 h). Soil moisture was measured at depths of 20, 40, and 60 cm from the soil surface during 2023 and 2024 using frequency domain reflectometry. The models were trained to predict soil moisture at time horizons of ‘t + 1’, ‘t + 3, ‘t + 6’, and ‘t + 12’ when ‘t’ is present time. Short-term predictions more accurately followed the observed soil moisture trends than long-term predictions. During the collection period, rainfall varied from 0.5 mm to 48.5 mm per hour. Soil moisture contents increased immediately following the onset of rainfall. These results are consistent with existing knowledge. As soil depth increased, soil moisture contents tended to increase and respond more gradually to rainfall. During rainfall, in the topsoil (20 cm depth) moisture content fluctuated significantly, while the subsoil (60 cm depth) remained relatively stable for several hours after rainfall ended. The model performance was evaluated using mean absolute error, root mean square error (RMSE), and normalized RMSE values. In both models using hourly and event-based rainfall inputs, errors in soil moisture prediction tended to increase with longer forecast time horizons. However, these errors were significantly lower when using event-based rainfall data. These findings indicate that event-based rainfall is a more effective input for LSTM models in predicting soil moisture in an Asian pear orchard, and such models can support precision irrigation systems that optimize water use by delivering the right amount of water at the right time.
Schlagwörter
MeSH-Schlagwörter (MEDLINE)
Substanzen
Autor:innen und Institutionen
- Department of Horticulture, Chonnam National University, Gwangju, Republic of Korea.
- Interdisciplinary Program in IT-Bio Convergence System, Chonnam National University, Gwangju, Republic of Korea.
- Department of Statistics, Chonnam National University, Gwangju, Republic of Korea.
- Digital Agriculture Research Institute for Horticultural Fruit, Chonnam National University, Gwangju, Republic of Korea.
- Gyeongsangnam-do Agricultural Research and Extension Services, Jinju, Republic of Korea.
- Pear Research Center, National Institute of Horticultural & Herbal Science, Rural Development Administration, Naju, Republic of Korea.
ORCID-Profile: Sun Woo Chung
Förderung
- Rural Development Administration
- Korea Institute of Planning and Evaluation for Technology in Food, Agriculture and Forestry
Zitieren
APA
Kim, Y. J., Im, H. J., Wi, S. G., Kim, M. S., Lee, S. M., Yang, U., Chung, S. W., & Lee, S. H. (2026). Development of long short-term memory models using rainfall and soil moisture to predict soil moisture dynamics. PLOS One, 21(7), e0353268. https://doi.org/10.1371/journal.pone.0353268
Vancouver
Kim YJ, Im HJ, Wi SG, Kim MS, Lee SM, Yang U, et al. Development of long short-term memory models using rainfall and soil moisture to predict soil moisture dynamics. PLOS One. 2026;21(7):e0353268. doi:10.1371/journal.pone.0353268
BibTeX
@article{Kim2026,
author = {Kim, Yoon Ji and Im, Ho Jin and Wi, Seung Gon and Kim, Min Soo and Lee, Seok Min and Yang, Ung and Chung, Sun Woo and Lee, Sang-Hyun},
title = {Development of long short-term memory models using rainfall and soil moisture to predict soil moisture dynamics},
journal = {PLOS One},
year = {2026},
volume = {21},
number = {7},
pages = {e0353268},
doi = {10.1371/journal.pone.0353268}
}
EUVIMED