Add to Favourites
To login click here
This paper presents a novel approach to increase the spatiotemporal resolution of an environmental variable by utilizing machine learning algorithms to construct a satellite-like image based on measurements from IoT sensors. The approach was tested with three different machine learning algorithms and the highest accuracy yield was from the prediction models built with the feed-forward neural network, with an RMSE of 15.49 ×10-6 mol/m2.