PT1.1 - A Support Vector Machine Learning Prediction Model of Evapotranspiration Using Real-time Sensor Node Data
- Event
- EUROSENSORS XXXVI
2024-09-01 - 2024-09-04
Debrecen (Hungary) - Band
- Poster
- Chapter
- PT1 - Theory, Modelling, Design and Testing
- Author(s)
- W. A. K. Afridi, S. C. Mukhopadhyay, B. M. Macquarie University - Sydney (Australia)
- Pages
- 219 - 220
- DOI
- 10.5162/EUROSENSORSXXXVI/PT1.1
- ISBN
- 978-3-910600-03-4
- Price
- free
Abstract
An IoT-enabled smart sensor node has been developed to acquire real-time field data and formulate an adaptable prediction model to predict crop Evapotranspiration (ETc) using a Support Vector Ma-chine (SVM) learning algorithm. Integrating the SVM algorithm with real-time sensor nodes offers great potential to improve spatial and temporal resolution of water data uncertainty. In the model de-velopment, key input features are measured in real-time and computed using mathematical equations such as Penman-Monteith, which include soil-environmental parameters.