The future of vineyard irrigation : AI-driven insights from IoT data

Stojanova, Simona (author), Volk, Mojca (author), Balkovec, Gregor (author), Kos, Andrej (author), Stojmenova Duh, Emilija (author)

Accurate irrigation volume prediction is crucial for sustainable agriculture. This study enhances precision irrigation by integrating diverse datasets, including historical irrigation records, soil moisture, and climatic factors, collected from a small-scale commercial estate vineyard in southwestern Idaho, the United States of America (USA), over a period of three years (2017–2019). Focusing on long-term irrigation forecasting, addressing a critical gap in sustainable water management, we use machine learning (ML) methods to predict future irrigation needs, with improved accuracy. We designed, developed, and tested a Long Short-Term Memory (LSTM) model, which achieved a Mean Squared Error (MSE) of 0.37, and evaluated its performance against a simpler baseline linear regression (LinReg) model, which yielded a higher MSE of 1.29. We validate the results of the LSTM model using a cross-validation technique, wherein a mean MSE of 0.18 was achieved. The low value of the statistical analysis (p-value = 0.0009) of a paired t-test confirmed that the improvement is significant. This research shows the potential of Artificial Intelligence (AI) to optimize irrigation planning and advance sustainable precision agriculture (PA), by providing a practical tool for long-term forecasting and that supports data-driven decisions.

• Language: English
• Keywords: sustainable agriculture, irrigation prediction, internet of things, sensors, linear regression, LSTM
• Work type: Article
• Typology: 1.01 - Original Scientific Article
• Organization: FE - Faculty of Electrical Engineering
• Publication status: Published
• Publication version: Version of Record
• Year: 2025
• Number of pages: 19 str.
• Numbering: Vol. 25, issue 12, art. 3658
• PID: 20.500.12556/RUL-169929
• UDC: 004:634.8
• ISSN on article: 1424-8220
• DOI: 10.3390/s25123658
• COBISS.SI-ID: 239775491
• Publication date in RUL: 18.06.2025

Record is a part of a journal

• Title: Sensors
• Shortened title: Sensors
• Publisher: MDPI
• ISSN: 1424-8220
• COBISS.SI-ID: 10176278

Licences

• License: CC BY 4.0, Creative Commons Attribution 4.0 International
• Link: http://creativecommons.org/licenses/by/4.0/
• Description: This is the standard Creative Commons license that gives others maximum freedom to do what they want with the work as long as they credit the author.

Secondary language

• Language: Slovenian
• Keywords: trajnostno kmetijstvo, napoved namakanja, internet stvari, senzorji, linearna regresija, LSTM

Projects

• Funder: EC - European Commission
• Project number: 101060179
• Name: Maximising the CO-benefits of agricultural Digitalisation through conducive digital ECoSystems
• Acronym: CODECS

• Funder: ARIS - Slovenian Research and Innovation Agency
• Project number: P2-0425
• Name: Decentralizirane rešitve za digitalizacijo industrije ter pametnih mest in skupnosti