生成式人工智能对地震成像技术具有广泛而深远的影响

壳牌公司最近宣布，计划在其深海油气勘探和生产活动中使用基于人工智能的技术

人工智能技术也开始在可再生能源领域发挥重要作用，并帮助创建智能电网

中国石化新闻网讯 据油价网2023年5月21日报道，人工智能(AI)已经成为我们这个时代最大的长期大趋势之一。人工智能正在推动第四次工业革命，并越来越被视为应对气候变化和污染等这个时代一些重大挑战的关键战略。能源公司正在使用人工智能工具将记录数字化，分析大量数据和地质图，并潜在地识别设备过度使用或管道腐蚀等问题。能源巨头壳牌公司就是这样一家公司。5月17日，壳牌公司宣布计划在其深海油气勘探和生产中使用大数据分析公司Spark Cognition的基于人工智能的技术，以提高运营效率和速度，并提高油气产量。

壳牌公司负责创新和绩效的副总裁Gabriel Guerra在一份声明中表示：“我们致力于寻找新的创新方法，重塑我们的油气勘探作业方式。”

总部位于美国得克萨斯州奥斯丁的大数据分析公司Spark Cognition公司首席科学官布鲁斯·波特表示，生成式人工智能对地震成像技术具有广泛而深远的影响，该技术可以将勘探时间从9个月大幅缩短至9天以内。Spark Cognition公司的生成式人工智能将使用比平时更少的地震数据扫描生成地下图像，从而有助于深海保护。更少的地震勘探作业反过来将加速勘探过程，改善作业流程并节省高性能计算成本。

但这并不是壳牌公司首次涉足人工智能技术。早在2018年，壳牌公司就与微软公司合作，将Azure C3物联网平台整合到其海上业务中。这个平台使用人工智能来提高公司海上基础设施的效率，从钻井和开采到员工授权和安全。

壳牌公司并不是唯一在运营中使用人工智能的国际大型石油公司。早在2019年，英国石油公司(bp)就投资了总部位于休斯敦的科技初创公司贝尔蒙特技术公司，后者帮助bp开发了一个名为“桑迪”的基于云地球科学平台。“桑迪”获取bp地质、地球物理和油藏项目信息并进行解释分析，从而创建独特的“知识图表”，包括bp地下资产的全息图像。然后，bp可以使用程序的神经网络系统进行模拟并解释结果。

2019年3月，阿克尔公司与Spark Cognition公司合作，在其“认知操作”措施中增强人工智能应用。阿克尔Spark Cognition公司创建的Spark Predict人工智能系统，还用于监测30多个海上设施表层和海底设施。

4年前，英国石油和天然气管理局(OGA)推出了英国首个石油和天然气国家数据存储库(NDR)。 这个庞大的数据存储库包含了130兆兆字节的地球物理、基础设施、油气田和油气井数据。这些数据涵盖了5000多次地震调查、12500个井眼和3000条管道。NDR利用人工智能来解释这些数据，OGA希望能够发现新的油气远景构造，并从现有的基础设施中提高产量。这个平台还将用于英国的能源转型，储层和基础设施数据将用于支持碳捕获、利用和储存项目。

人工智能技术和可再生能源

人工智能技术也开始在可再生能源领域发挥重要作用，并帮助创建智能电网。

美国实现100%可再生能源电网梦想的最大障碍之一是可再生能源的间歇性。毕竟，人类电网是为接近恒定的电力输入/输出而设计的，而风并不总是吹，太阳也不总是照耀。为了成功地向可再生能源转型，电网必须变得更加智能。

幸运的是，有一个令人鼓舞的先例。

几年前，谷歌公司宣布，包括数据中心和办公室在内的全球业务已实现100%使用可再生电力。如今，谷歌公司是可再生电力最大的企业买家，承诺购买总计7吉瓦(7000兆瓦)的风能和太阳能。谷歌公司与美国国际商用机器公司（IBM）合作，为风力发电的高度间歇性寻找解决方案。利用IBM的DeepMind人工智能平台，谷歌公司在美国中部700兆瓦的风力发电能力上部署了极大似然估计法算法（ML），足以为一个中等城市供电。

IBM表示，通过使用一个经过广泛可用的天气预报和历史涡轮机数据训练的神经网络，DeepMind人工智能平台现在能够在实际发电前36小时预测风力发电量。

其他风电场运营商也可以使用类似的模型，以更智能、更快、更多的数据驱动优化其电力输出，以更好地满足客户需求。

IBM的DeepMind人工智能平台利用受过训练的神经网络，比实际发电提前36小时预测风力发电量。

总部位于得克萨斯州休斯敦的Innowatts是一家初创公司，它开发了一种用于能源监测和管理的自动化工具包。Innowatts的公用事业平台从2100万客户的3400多万个智能电表中获取数据，其中包括美国主要的公用事业公司，如亚利桑那公共服务电力公司、波特兰通用电气公司、Avangrid公司、Gexa能源公司、WGL公司和Mega能源公司。Innowatts表示，其机器学习算法能够分析数据，预测几个关键数据点，包括短期和长期负荷、变化幅度、天气敏感度等。

Innowatts估计，如果没有它的机器学习模型，在危机最严重的时候，公用事业公司的预测会有20%甚至更多的不准确性，从而给他们的运营带来巨大压力，最终推高最终用户的成本。

此外，人工智能和数字解决方案可以使我们的电网更安全。

通过采用数字和人工智能模型，我们的电网将变得越来越智能和可靠，并使向可再生能源的转型更加顺利。

李峻 编译自 油价网

原文如下：

Why AI Is The Future Of Offshore Oil Drilling

·     Generative AI for seismic imaging has broad and far-reaching implications.

·     Shell recently announced plans to use AI-based technology in its deep-sea exploration and production activities.

·     AI tech is also starting to play a big role in the renewable energy sector and aiding in the creation of smart grids.

Artificial Intelligence (AI) has emerged as some of the biggest secular megatrends of our time. AI is powering the fourth industrial revolution and is increasingly being viewed as a key strategy for mastering some of the greatest challenges of our time including climate change and pollution. Energy companies are employing AI toolsto digitize records, analyze vast troves of data and geological maps, and potentially identify problems such as excessive equipment use or pipeline corrosion.One such company is Dutch energy giant Shell Plc (NYSE:SHEL). On Wednesday, Shell announced plans to use AI-based technology from big-data analytics firm SparkCognition in its deep sea exploration and production in a bid to improve operational efficiency and speed as well as boost production.

"We are committed to finding new and innovative ways to reinvent our exploration ways of working," Gabriel Guerra, Shell's vice president of innovation and performance, said in a statement.

According to Bruce Porter, chief science officer for Texas-based SparkCognition, Generative AI for seismic imaging has broad and far-reaching implications, adding that the technology can dramatically shorten explorations to less than nine days from nine months. The company’s Generative AI will generate subsurface images using fewer seismic data scans than usual and thus help with deep sea preservation. Fewer seismic surveys will in turn accelerate the exploration process, improve workflow and save costs in high-performance computing.

But this is not Shell’s first foray into AI tech. Back in 2018, the company partnered with Microsoft to incorporate the Azure C3 Internet of Things platform in its offshore operations. The platform uses AI to drive efficiencies across the company’s offshore infrastructure, from drilling and extraction to employee empowerment and safety.

Shell is not the only Big Oil company employing AI in its operations. Back in 2019, BP Plc (NYSE:BP) invested in Houston-based technology start-up Belmont Technology which helped the company develop a cloud-based geoscience platform nicknamed “Sandy.” Sandy allows BP to interpret geology, geophysics and reservoir project information thus creating unique “knowledge-graphs” including robust images of BP’s subsurface assets. BP is then able to perform simulations and interpret results using the program’s neural networks.

In March 2019, Aker Solutions partnered with SparkCognition to enhance AI applications in its ‘Cognitive Operation’ initiative. Aker SparkCognition’s AI systems called SparkPredict to monitor topside and subsea installations for more than 30 offshore structures.

Four years ago, the Oil and Gas Authority (OGA) launched the UK’s first oil and gas National Data Repository (NDR). The massive repository contains 130 terabytes of geophysical, infrastructure, field and well data. This data covers more than 5,000 seismic surveys, 12,500 wellbores and 3,000 pipelines. NDR employs AI to interpret this data, with OGA hoping to uncover new oil and gas prospects as well as enable more production from existing infrastructure. The platform will also be used in the country’s energy transition, with reservoir and infrastructure data used to support carbon capture, usage and storage projects.

AI And Renewable Energy

AI tech is also starting to play a big role in the renewable energy sector and aiding in the creation of smart grids.

One of the biggest barriers to the United States realizing its dream of having a 100% renewable grid is the intermittency of renewable power sources. After all, our grids are designed for near-constant power input/output whereas the wind doesn’t always blow and the sun doesn’t always shine. For the transition to renewable energy to be successful, our power grids have to become a lot smarter.

Luckily, there’s an encouraging precedent.

A few years back, Google announced that it had reached 100% renewable energy for its global operations including its data centers and offices. Today, Google is the largest corporate buyer of renewable power, with commitments totalling 7 gigawatts (7,000 megawatts) of wind and solar energy. Google teamed up with IBM to search for a solution to the highly intermittent nature of wind power. Using IBM’s DeepMind AI platform, Google deployed ML algorithms to 700 megawatts of wind power capacity in the central United States——enough to power a medium-sized city.

IBM says that by using a neural network trained on widely available weather forecasts and historical turbine data, DeepMind is now able to predict wind power output 36 hours ahead of actual generation. Consequently, this has boosted the value of Google’s wind energy by roughly 20 percent.

A similar model can be used by other wind farm operators to make smarter, faster and more data-driven optimizations of their power output to better meet customer demand.

IBM’s DeepMind uses trained neural networks to predict wind power output 36 hours ahead of actual generation

Houston, Texas-based Innowatts, is a startup that has developed an automated toolkit for energy monitoring and management. The company’s eUtility platform ingests data from more than 34 million smart energy meters across 21 million customers including major U.S. utility companies such as Arizona Public Service Electric, Portland General Electric, Avangrid, Gexa Energy, WGL, and Mega Energy. Innowatts says its machine learning algorithms are able to analyze the data to forecast several critical data points including short- and long-term loads, variances, weather sensitivity, and more.

Innowatts estimates that without its machine learning models, utilities would have seen inaccuracies of 20% or more on their projections at the peak of the crisis thus placing enormous strain on their operations and ultimately driving up costs for end-users.

Further, AI and digital solutions can be employed to make our grids safer.

By employing digital and AI models, our power grids will become increasingly smarter and more reliable and make the shift to renewable energy smoother.