Sharing image processing module in TWDC platform: using AI landslide application as an example

Taiwan Data Cube (TWDC) is a cloud platform used for the storage and processing of multi-sensor, multi-temporal remote sensing data. The platform is majorly an image application platform for making value-added services for user customized applications. In this study, the image analysis application for landslide detection based on AI technique in TWDC is used as an example to demonstrate how it can be shared to local user with security. Currently, to share an application properly without security consideration from an application server, the use of Application Programming Interface (API) is a standard procedure and has been widely used in information technology area. However, for the researcher who develop remote sensing applications, to build an API connectivity for local users to submit parameters and obtain results from the application in cloud environment is still a difficult job. Therefore, for generating a demonstration that can be followed for those who need an example to establish API connectivity in sharing their image processing application in TWDC, following are steps applied in this study: (1) Integrating multi-temporal satellite data (Formosat-5 and Sentinel-2) as inputs for AI models. (2) A manual SLIP based landslide detection approach is applied to automate the labelling process in the training stage of AI model. (3) An executable AI based landslide detection model with trained database is carried out and corresponding API connection is established. (4) A test procedure of shared model including the submission of spatial-temporal criterion and retrieving the final detected landslide area is demonstrated.