The purpose of this study is to propose a technology to replace green roofs to white(cool) roof, which currently occupy most of the roofs of Korea. This paper presents related studies about effectiveness of the cooling loop, deals with the limitations and problems of large-scale regional cooling loop construction, and presents various technical solutions to these problems. Introducing with cool roof effectiveness, and how to apply the replacement idea into massive area within image processing techniques. We'll cover full steps of image processing, at first, gathering images is time-consuming process, so we purpose data import pipeline with automated tools, then we do label images in purpose of detecting and classifying images via CNN (Convolutional Neural Network) layer. Then we Figure out the labels of images, which are randomly gathered all around the nation, and calculate the efficiency of the replacement by given input images
ACKNOWLEDGEMENT This research was supported by the MSIT (Ministry of Science and ICT), Korea, under the ITRC (Information Technology Research Center) support program (IITP-2022-2018-0-01424) supervised by the IITP (Institute for Information & communications Technology Promotion)