The launch of the digital economy has brought with it an expansion of disruptive technologies such as predictive analytics, artificial intelligence (AI) and robotics that are readily being used to transform the marketplace. But can we also use these breakthrough technologies to accelerate the development of safer, more sustainable materials for the renewable energy sector?
Starting with one of the fastest-growing clean energy sectors, solar technology, this is the fundamental question that a unique collaboratory is asking itself.
Three years ago, the Department of Materials Design and Innovation at the University at Buffalo, Clean Production Action (CPA) and Niagara Share created the Collaboratory for a Regenerative Economy (CoRE). CoRE recognizes the critical societal importance of scaling clean energy technologies such as solar to address the climate crisis. But to do this sustainably, we need to collectively scale solutions to reduce the use of toxic chemicals and scarce, unrecyclable materials that impede circular economies.
Issues such as toxicity and environmental impact are often an afterthought in the design phase, which is predominantly focused on improving the technical functions and efficiencies of materials. With more than 78 million tons of contaminated waste related to solar panels expected to hit landfills by 2050, this trend needs to be reversed.
To improve the life-cycle footprint of solar panels, big data tools can help manufacturers embed human health and environmental criteria into the front end of the design phase of materials and products.
我们需要集体缩放解决方案，以减少妨碍循环经济的有毒化学品和稀缺，不可折扣的材料。
在最近发布的报告中，“变革的元素：向前迈进更清洁更安全的未来，”核心概述了可再生能源公司的策略：
- Reduce chemical footprints of products, supply chains and manufacturing;
- Apply machine learning to design techniques for lead-free panels; and
- 使用大数据工具快速表征化学品并识别更安全的溶剂。
安全地满足可再生能源技术的需求
太阳能energy, along with other clean energy technologies, depends on hazardous chemicals and novel materials to reduce costs and optimize efficiencies. Some of these chemistries are unsafe for the environment and human health.
For example, solar energy technologies rely on toxic materials such as lead in solar cells and hydrofluoric acid used in manufacturing processes. This is especially harmful for workers exposed to hazardous chemicals throughout the life cycle of renewable energy technologies from production to disposal.
太阳能部门并不孤单。根据国际劳工组织的说法，超过2,780,000名工人每年都在全球死亡，不安全和不健康的工作条件。联合国人权委员会估计，一名工人至少每30秒死于暴露于有毒工业化学品，杀虫剂，粉尘，辐射等有害物质。
注册会计师的工作与电子行业的司机afer chemical is applicable to the solar sector and all clean energy technologies. For example, HP, Inc is a leader in its work to reduce its chemical footprint, documented by its participation in the annual Chemical Footprint Survey. This survey measures a company’s chemical footprint against best practices. It is modeled on the Carbon Disclosure Project, and is open and transparent, providing solar companies with a roadmap to safer chemical use.
Apple使用CPA的Greenscreen对其供应商提供指导，即将使用作为清洁剂和供应链中的危险化学品的危险化学品。GREENSCREEN是一家领先的危险评估工具，基于跨越18人体健康和环境终点的表现来基准化学品。太阳能公司可以使用此工具识别对氢氟酸等有问题材料的更安全的解决方案。
These leading electronic companies even have teamed up with nonprofits such as CPA and academics to form the Clean Electronic Production Network (CEPN), which aims to eliminate exposure to toxic substances in the workplace.
This is a massive undertaking related to the manufacturing of computers, electronics and other information technologies. Solar manufacturers work off a similar manufacturing platform that stands to benefit from the tools and resources that CEPN is creating to do full chemical inventories and safer substitution with suppliers.
今天的太阳能公司可以通过电子公司的效果，并对更安全的化学用途进行有意义的进展来适应CEPN工具和策略。但对于所有这些公司来说，仍然存在重大挑战，特别是太阳能 - 发现新材料相对于其增长预测所需的时间。这是核心相信AI，机器学习和预测分析的地方可以发挥作用，在加速物质发现过程中对人类健康和环境的益处以及优化的技术性能。
使用大数据和AI加速材料发现
高性能材料的发展通常需要数十年，有时长达30年来商业化新材料。大数据工具可以组织大量的分类信息公司需要提高材料的技术，环境和社会绩效。每年参加CPA化学脚印调查的太阳能公司以衡量其化学足迹并跟踪其对最佳实践的表现，可以利用这些工具来映射模式和影响，以决策和优先级所需的模式和影响。
例如，在太阳能电池板中的铅在这些产品的生产和处置中存在问题。电子公司已显示，可以设计无铅电子产品，但太阳能公司仍然非常依赖基于铅的技术。即使使用下一代太阳能电池板 - 例如，基于Perovskite的太阳能电池板也表明了提高面板效率的可能性，但它们的化学依赖于铅。
理性设计是一种绕过试验和错误方法的过程，基于对基本科学绩效的预测理解来创造新材料。
核心证明“数据指纹”可以提供普罗夫斯基钛矿晶体化学特征的强大表示。这是克服更安全替代的障碍的关键，例如铅。
Data-driven screening tools and machine learning methods can help navigate the complexity of information associated with new and emerging chemicals used in the manufacture of solar devices. This includes harnessing advanced materials modeling and informatics techniques to identify pathways for the rational design of new materials chemistries for renewable technologies (solar energy) that minimize adverse environmental and human health impacts without compromising functionality.
理性设计是一种绕过试验和错误方法的过程，基于对基本科学绩效的预测理解来创造新材料。在寻找适当的材料化学质量，这些材料符合最小危险和增强的工程性能的多种功能度量，要求我们探索化学搜索空间，这些空间对于使用传统方法可以在合理的时间范围内探索和制定关键发现。
核心要求通过应用材料信息和基于物理学的建模来填补科学知识的差距来解决这一挑战，然后指导加速材料发现和太阳能技术设计。在核心，我们的目标是更好地了解化学的原子规模变化如何对太阳能电池的材料制造，性能和可持续性的多尺度影响。必威体育2018
欧盟委员会最近宣布了一种新的化学策略，为其绿色新的交易，为其公民提供了无毒的未来，并为零污染计划进行了规划。该计划包括绿色和更安全的材料创新的新投资。这项政策将刺激对更环保的需求，更安全的产品;对可再生能源公司的压力造成更全面地思考其生命周期的影响。
通过building on best practices established widely in the electronics sector and leveraging the untapped benefits of AI and big data, solar companies can lead the way for the renewable energy sector in transforming their chemical footprints and accelerating the adoption of safer materials.
