Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0). IICST2020: 5th International Workshop on Innovations in Information and Communication Science and Technology, Malang, Indonesia MONITORING SURFACE WATER DYNAMIC USING CLOUD COMPUTING PLATFORM OF GOOGLE EARTH ENGINE Fatwa Ramdani 1 , Putri Setiani 2 1 Geoinformatics Research Group, Brawijaya University, Indonesia, fatwaramdani@ub.ac.id 2 Environmental Engineering, Brawijaya University, Indonesia, psetiani@ub.ac.id ABSTRACT Water is important resources and the pattern of water dynamics is needed to be monitored. Cloud computing platform named Google Earth Engine (GEE) has benefited the scientists with a limited computing system to monitor large scale water reservoir in multi-period with large size to monitor any reservoir whole over the world. This study introduced the novel and reproducible series of steps to monitor the surface water dynamics using GEE platform study case Selorejo reservoir located in East Java, Indonesia. This study found that during 2017 and 2018 the surface water condition of Selorejo reservoir is relatively in good condition while in 2019 the surface water experienced dramatic decreased due to long dry seasons. The novel procedure proposed in this study is efficient to be applied in any other large scale reservoir. Key words: big data, reservoir, water dynamic. 1. INTRODUCTION Water level is an important indicator in a major water body such as large reservoirs and rivers. Changes in water level condition determine the functionality of the water body, both regarding its service for the natural ecosystem and other services that are related to human activities. Selorejo reservoir, the area of interest in this study, is situated in Malang Regency, East Java, Indonesia. Located about 600 meters above sea level, this reservoir is used for electricity generation with a capacity average of 4.5 MW. Water levels in reservoirs are mainly influenced by two factors, (1) seasonal variation, and (2) by the operator of a hydropower plant, who discharges water through the turbines or stores water in the reservoir, in a fashion that maximizes profit (Hirsch et al., 2014). Dynamics of water level in a hydropower plant may significantly impact the capacity of electricity generation. A previous study in using Google Earth Engine (GEE) for water environment has been done by Hird et al. (2017), where a workflow was developed to predict the probability of wetland occurrence within northeastern Alberta, Canada. The study found that the GEE is effective and efficient to support the Alberta Merged Wetland Inventory. This study aims to propose novel and reproducible series of steps to monitor the surface water dynamics of reservoir using cloud computing of GEE platform. 2. STUDY AREA The study area is Selorejo reservoir located in Malang Regency, East Java, Indonesia. Situated between Kelud Mountain, Anjasmoro Mountain, and Kawi Mountain, and in relatively high elevation, approximately 600 meters above sea level, make the cool climate around the reservoir. The Selorejo Hydroelectric Power Plant (PLTA) is located at Pandansari Village, Ngantang District. It was built in 1970 and started operating since July 24, 1973 with a capacity of 4.5 Mega Watt (MW) (ESDM, 2015). The Selorejo reservoir is used as the source of electric power generation. Electricity generated from the Selorejo hydropower plant sent through a 70 kV transmission network is used to meet the electricity needs of the Malang area (ESDM, 2015). Therefore monitoring the surface water level dynamics is very important for a sustainable energy source. 3. DATA AND METHOD To access the GEE, the user could enter the URL address, https://code.earthengine.google.com/. When using GEE platform user have to import the dataset that will be used in the analysis. In this study, we import the Sentinel-2 MSI Level-1c. Then we define the boundary of the study area. The Selorejo boundary is in shapefile format derived from http://tanahair.indonesia.go.id/. To import the shapefile we used “importing Table data” module within the GEE platform. Next step is filtering the dataset, we only use data with the cloud-free condition. The result then