Germany's energy transition （Energiewende） is a paradigm shift into a low-carbon and nuclear-free economy. As part of the European Union's climate neutralization drive, aiming to reduce greenhouse gases to net-zero by the middle of the century. Generous financial support for wind and solar power has boosted renewable energy to produce more electricity than fossil fuels for the first time in 2020. Germany's energy transition is not a policy shift after the Fukushima nuclear disaster, but a long-term process of policy making in response to public opinion and technological trends. Germany's energy transition is still underway and needs to be extended beyond the power supply. However, it may already be pushing more thoroughly through pricing and volume regulations, such as the European Emissions Trading Scheme （EU-ETS） and changes to the carbon tax, which provides incentives for changes to low-carbon technologies. This paper analyses Germany's energy transition and climate policy. The purpose of this paper is to clarify the actual conditions and issues of the reduction effects of greenhouse gas emissions, which are the main policy issues of the energy conversion policy that has been developed mainly on renewable energy for these 20 years.

In this study, we present a new method for estimating input coefficient matrix with deep learning. We use the data of prefectures of Japan as the training data. However, the data is small and is likely to cause overfitting. Therefore, we attempt to avoid the over-fitting by creating new data of virtual areas aggregating multiple prefectures. The approach is based on the concept of data augmentation. As a result of predicting the input coefficient matrix of Yamaguchi prefecture and Gujo city, we showed that the method using deep learning can estimate the matrix with more stable accuracy than RAS method for these areas.