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

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

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.

• Jezik: Angleški jezik
• Ključne besede: sustainable agriculture, irrigation prediction, internet of things, sensors, linear regression, LSTM
• Vrsta gradiva: Članek v reviji
• Tipologija: 1.01 - Izvirni znanstveni članek
• Organizacija: FE - Fakulteta za elektrotehniko
• Status publikacije: Objavljeno
• Različica publikacije: Objavljena publikacija
• Leto izida: 2025
• Št. strani: 19 str.
• Številčenje: Vol. 25, issue 12, art. 3658
• PID: 20.500.12556/RUL-169929
• UDK: 004:634.8
• ISSN pri članku: 1424-8220
• DOI: 10.3390/s25123658
• COBISS.SI-ID: 239775491
• Datum objave v RUL: 18.06.2025

Gradivo je del revije

• Naslov: Sensors
• Skrajšan naslov: Sensors
• Založnik: MDPI
• ISSN: 1424-8220
• COBISS.SI-ID: 10176278

Licence

• Licenca: CC BY 4.0, Creative Commons Priznanje avtorstva 4.0 Mednarodna
• Povezava: http://creativecommons.org/licenses/by/4.0/deed.sl
• Opis: To je standardna licenca Creative Commons, ki daje uporabnikom največ možnosti za nadaljnjo uporabo dela, pri čemer morajo navesti avtorja.

Sekundarni jezik

• Jezik: Slovenski jezik
• Ključne besede: trajnostno kmetijstvo, napoved namakanja, internet stvari, senzorji, linearna regresija, LSTM

Projekti

• Financer: EC - European Commission
• Številka projekta: 101060179
• Naslov: Maximising the CO-benefits of agricultural Digitalisation through conducive digital ECoSystems
• Akronim: CODECS

• Financer: ARIS - Javna agencija za znanstvenoraziskovalno in inovacijsko dejavnost Republike Slovenije
• Številka projekta: P2-0425
• Naslov: Decentralizirane rešitve za digitalizacijo industrije ter pametnih mest in skupnosti