Social Energy System Design Incorporating AI and Lived Experience

在此研究计划下，取得了许多研究成果。首先，机器学习的理论基础以及通过现有数据集（以前进行的调查）预测利益相关者的环境和社会公平偏好已经建立，并在应用能源公司目前正在审查的研究中报告。该手稿详细介绍了能源系统设计偏好的多种机器学习算法方法，以及增加训练数据对准确率的影响。根据这些调查结果，设计并部署了一项全国调查，特别是为了实现低负担，高产量的预测数据集，这将在未来一年中得到利用。目前，这些数据正被用于支持预测和可视化工具的努力。

Many research achievements have been made under this research plan. Firstly, the theoretical underpinnings of machine learning and prediction of environmental and social equity preferences of stakeholders via existing data sets (previously undertaken surveys) was established and reported in research currently under review at Applied Energy. The manuscript details multiple machine learning algorithmic approaches to energy system design preferences and the effects of imcreasing training data toward accuracy rates. Based on these findings, a national survey was designed and deployed, specifically to achieve a low-burden, high yield predictive data set which will be leveraged in the coming year. Currently this data is being used to underpin efforts toward a prediciton and visualization tool.