Abstract
The Japanese government has set a goal of reducing greenhouse gases by 46% by 2030 compared to 2013 levels. In the household sector, the target is as high as 66%. In order to reach the target, all municipalities need to have an accurate understanding of their energy demand and CO2 emissions from primary data. However, it is difficult for small municipalities to obtain primary data on their own. The traditional proration method cannot determine whether the estimation results are reliable. Therefore, in this research, we proposed a method that utilizes the recursiveness of statistical data. One is an empirical Bayesian method and the other is an energy selection model when using heat. Next, I estimated the environmental load intensity of 1,718 municipalities nationwide. However, the accuracy of the data is still insufficient to run the PDCA cycle. In order to further improve the estimation accuracy, it is necessary to comprehensively utilize various statistics and related information. In addition, it is necessary to quickly aggregate statistical data and publish the results promptly, and to develop advanced analysis tools and future prediction tools for collected data.
