RiceMapEngine: A Google Earth Engine-based Web Application for Fast Paddy Rice Mapping

Mapping rice area is a critical resource planning task in many South Asia countries where the primary crop. Remote sensing-based methods typically rely on domain knowledge, such as crop calendar and phenology, supervised classification with ground truth samples. Applying Google Earth Engine (GEE) has been proven effective especially at large scale owing to comprehensive up-to-date data catalog massive server-side processing power. However, writing scripts through code editor requires users program JavaScript understand GEE Application Programming Interface (API), which can be challenging for researchers. Thus, this paper presents GEE-based web application that aims eliminate programming requirements selection, preprocessing, visualizations so easily produce maps refine collections intuitive Graphical User Interfaces (GUI). This software includes 3 sub-module apps, namely collection app, threshold-based mapping classification-based app. Users customize flow using GUI designed Bootstrap, backend server uses Python API, service account authentication execute workflow cloud servers. The experiment shows both overall accuracy (OA) Kappa scores of result are higher than 0.9 suggests RiceMapEngine significantly reduce complexity time costs it takes accurate meet demands real-world stakeholders.