Machine learning model for snow depth estimation using a multisensory ubiquitous platform

Abstract Snow depth estimation is an important parameter that guides several hydrological applications and climate change prediction. Despite advances in remote sensing technology enhanced satellite observations, the of snow at local scale still requires improved accuracy flexibility. The ubiquitous wearable promote new prospects tackling this challenge. In paper, a IoT platform exploits pressure acoustic sensor readings to estimate classify classes using some machine-learning models have been put forward. Significantly, results Random Forest classifier showed 94%, indicating promising alternative measurement compared situ, LiDAR, or expensive large-scale wireless network, which may foster development further affordable ecological monitoring systems based on cheap sensors.