内容来源：https://news.microsoft.com/source/asia/features/pairing-geotechnical-data-with-ai-helps-new-zealand-to-build-better/

内容总结：

新西兰引入人工智能管理地质数据库，助力更安全、高效的基础设施建设

新西兰工程地质学家奥利维亚·埃利斯-加兰如今只需在电脑地图上输入一句“显示霍布森维尔地区的勘察数据”，系统便能瞬间调出奥克兰该郊区的地下土层构成、水位和岩层等关键信息。这得益于该国最新升级的、运行于微软云平台Azure上的新西兰岩土工程数据库。

该数据库最初源于2011年基督城大地震后的重建需求。当时，工程师们急需地下数据以评估建筑安全，但数据分散在各机构，难以获取，导致重复勘察，耗时耗力。为此，新西兰于2013年建立了国家岩土工程数据库，旨在集中共享全国地质信息。

2024年，工程咨询公司Beca将其数字孪生平台BEYON与数据库整合升级，打造了新一代平台。2025年末，平台进一步引入基于OpenAI GPT-5.1大模型的人工智能助手，使超过4300名用户能够直接用自然语言快速查询、筛选所需地质数据。

“人工智能工具让我们响应速度极大提升，它能如此快速地调取海量信息，”埃利斯-加兰表示，“它是我们了解地下情况的入口。”据Beca估算，借助AI助手，工程师检索所需数据的时间平均减少了40%。

平台不仅提升了效率，也通过数据积累增强了工程安全性。例如，在霍布森维尔一处住宅开发项目中，埃利斯-加兰借助平台已有的周边区域扫描数据，精准定位了地质变化区域，从而为客户节省了勘察时间和成本。“数据库就像我们的‘地球图书馆’，”她说，“共享的数据越多，我们的判断就越可靠，从而能够建造更安全、更优质的工程。”

Beca产品战略经理斯蒂芬·威瑟登指出，未来将继续利用AI增强数据审核流程，并提供更丰富的可视化功能，以确保数据的准确可靠，从而“帮助建设更具韧性、更安全的社区”。公司首席执行官阿米莉亚·林齐则表示，整合百年来的工程经验与数据，并以数字化方式赋能决策，旨在“助力客户为国家的未来繁荣做出选择”。

中文翻译：

将岩土数据与人工智能相结合，助力新西兰打造更优质的建筑

奥利维娅·埃利斯-加兰在笔记本电脑上点击新西兰地图，输入指令："显示霍布森维尔的勘察数据。"几秒钟内，列表弹出，地图自动缩放，展现出奥克兰这座风景如画郊区的各项地下测试数据，每项数据都包含土壤成分、水位和岩层等关键信息。

作为工程地质学家，这类细节能帮助埃利斯-加兰了解地下构造及其特性。她利用这些数据为岩土工程公司ENGEO的客户提供建议，指导他们如何规划地面建设方案。

如今，通过升级版的新西兰岩土数据库（NZGD），人们可以借助人工智能用自然语言检索和查询全国各地的复杂地质信息。该数据库搭载于全球工程咨询公司Beca开发的数字孪生平台BEYON之上。

Beca产品战略经理斯蒂芬·威瑟登表示，通过BEYON平台，工程师能够观察并与真实世界的"高保真复现模型"互动，这个模型"形似、神似且与现实世界紧密相连"。

NZGD和BEYON均运行于微软云平台Azure。BEYON的人工智能助手基于OpenAI的GPT-5.1大语言模型开发，通过微软铸造厂的Azure OpenAI服务构建而成。

"当前NZGD与人工智能工具的融合极大提升了我们的响应能力，因为它能如此迅速地汇集海量信息，"埃利斯-加兰说道，"这是我们通往地下的门户。"

基督城地震催生数据库

NZGD的诞生源于2011年2月基督城那场毁灭性地震。这场灾难导致185人遇难，数千人流离失所，市中心大部分基础设施严重损毁。

参与重建的工程师们急需地下状况数据来做出关键决策，例如判断建筑能否安全修复或必须彻底拆除。

埃利斯-加兰回忆当时为约4000栋待重建住宅进行评估的工作："民众流离失所时，我们的工作尤为敏感，必须争分夺秒。"

但数据整合面临巨大挑战。

Beca首席执行官阿米莉亚·林赛指出："这些数据往往非常零散。"

她解释说，工地建设时，不同机构或私人开发商会各自收集地下扫描或测试结果。无法获取现有数据意味着工程师不得不耗费时间和资金重新钻孔采集，有时甚至可能重复他人已完成的工作。

建立公共存储库来集中管理和共享所有信息成为必然选择。

"这正是创建NZGD的初衷，"林赛表示，"将这些数据整合为国家资产。"

NZGD由坎特伯雷地震重建局于2013年创立。十年后，新西兰商业、创新和就业部公开征集平台托管与升级方案。此时NZGD已积累数千用户，共享约16.8万份岩土测试数据。

Azure托管的NZGD 2.0

Beca提出将数字孪生平台BEYON应用于NZGD升级版的方案并获得采纳，由此成为NZGD的新任管理者。

2024年11月，升级版NZGD正式上线。新平台运行于微软Azure的SQL数据库，通过BEYON平台访问。

"我们致力于打造现代化、安全可靠、符合标准且融合现代空间分析技术的系统，"威瑟登表示，"这使我们能获得更优质的数据质量、可用性和访问体验。"

威瑟登解释选择数字孪生技术的原因在于其能最优地整合管理复杂交错的工程信息。

将NZGD技术架构迁移至Azure后，平台通过Azure Entra ID等访问控制实现了更高可及性、扩展性和安全性，也为后续功能拓展奠定基础。

2025年末，Beca为BEYON增配智能体AI层，使4300多名NZGD用户能用自然语言筛选、查询和提取岩土数据。该AI助手在微软铸造厂设计开发，遵循严格响应规则。

"微软铸造厂的内置防护机制让我们能精准控制AI响应方式，"威瑟登强调，"它不被允许执行岩土工程分析。"

数据与技术的深度融合让埃利斯-加兰这样的用户能更快做出精准决策。

AI助手不仅为她精准定位勘察记录，更帮助她在信息洪流中高效筛选。

"最实用的是能剔除无关数据，"她举例说，可要求AI仅显示锥探测试结果，排除手钻勘察数据。

据Beca估算，AI助手使工程师检索所需数据的时间平均缩短40%。

与此同时，数据共享越充分，置信度就越高。

在霍布森维尔项目中，埃利斯-加兰通过NZGD提前掌握周边地质变化规律，精准定位客户400套住宅的地质勘察区域，显著节约了时间和成本。

"这个优质平台促使所有工程师积极使用并上传数据，使我们能持续获取最新信息，"埃利斯-加兰形容道，"NZGD就像我们的地球图书馆。"

对于斜坡稳定性或液化现象（地震时土壤呈现液态特性的现象）等需要持续数据流进行计算分析的评估工作，数据库价值尤为凸显。

"数据越丰富，我们的工作成效就越显著，"埃利斯-加兰表示，"如今我们能打造更优质的建筑，因为可调用的资源空前丰富。"

威瑟登透露未来将提供更丰富的NZGD数据可视化方案，并运用AI强化审核流程，确保上传信息的准确可靠。

"更便捷的数据访问能增强社会韧性，建设更安全、准备更充分的社区。"

对Beca而言，BEYON平台上的NZGD已成为这家新西兰最大专业服务咨询公司百年传承的重要组成部分。

"我们的使命是让每一天更美好，"CEO林赛总结道，"这体现了我们如何凝聚在新西兰的百年积淀，整合包括岩土数据在内的所有成果，以助力客户为国家未来繁荣做出科学决策。"

题图说明：工程地质学家奥利维娅·埃利斯-加兰在奥克兰霍布森维尔建筑工地，将基于微软Azure的新西兰岩土数据库（NZGD）称为"我们通往地下的门户"。摄影：Radical for Microsoft。

林艾琳为微软源刊撰写人工智能专题报道，重点关注AI如何改善亚洲人民生活。艾琳曾任新加坡《海峡时报》副外电编辑，目前仍不定期撰写周末专栏。可通过LinkedIn联系作者。

英文来源：

Pairing geotechnical data with AI helps New Zealand to build better
Olivia Ellis-Garland clicks on a map of New Zealand on her laptop and types: “Show me the investigations in Hobsonville.” A list pops up in seconds and the map automatically zooms, displaying underground tests of the scenic Auckland suburb, each containing crucial data like soil composition, water levels and rock layers.
Details like these inform Ellis-Garland, an engineering geologist, what the ground beneath is made of and how it behaves. She uses this data to advise her clients at geotechnical engineering firm ENGEO what can be built above ground and how.
This complex information on sites across the country can now be navigated and queried in natural language using AI, thanks to the upgraded New Zealand Geotechnical Database (NZGD) hosted on BEYON, the digital twin platform developed by global engineering consultancy Beca.
With BEYON, engineers can see and interact with a “high fidelity representation” of the real world that “looks like, behaves like and is connected to the real world,” said Stephen Witherden, Beca’s product strategy manager.
Both NZGD and BEYON run on Microsoft’s cloud platform Azure. BEYON’s AI assistant, powered by OpenAI’s GPT-5.1 large language model, was developed using Azure OpenAI in Microsoft Foundry.
“The NZGD now and the AI tool has made us really responsive because it can just bring up so much information so quickly,” said Ellis-Garland. “This is our gateway to the ground.”
Christchurch quake
The NZGD was born in the aftermath of the devastating earthquake that struck Christchurch in February 2011. A total of 185 people were killed, thousands displaced and much of the city center’s infrastructure was badly damaged.
Engineers involved in rebuilding efforts urgently needed data on sub-surface conditions to make critical decisions, such as whether a structure could be safely repaired or restored, or needed to be demolished entirely.
Ellis-Garland recalled working on around 4,000 assessments for homes that needed to be rebuilt. “It’s sensitive work when people are displaced and so we had to do our work really quickly,” she said.
But collating that data was a challenge.
“It can be pretty fragmented,” said Beca CEO Amelia Linzey.
She explained that results of underground scans or tests are collected by different agencies or private developers when a site is being built. Being unable to access such data meant engineers had to spend time and money drilling fresh boreholes to collect new data or, frustratingly, the same data that someone else might already have.
Creating a common repository to centralize and share all that information was the obvious solution.
“That was really the sentiment behind the NZGD,” said Linzey. “Getting that data together as a national asset.”
The NZGD was established in 2013 by the Canterbury Earthquake Recovery Authority. Ten years later, the Ministry of Business, Innovation and Employment invited proposals to host and upgrade the platform. By then, the NZGD had amassed thousands of users and around 168,000 geotechnical tests had been uploaded and shared.
NZGD 2.0, on Microsoft Azure
Beca submitted its idea for the next version of NZGD to use BEYON, its digital twin platform. This idea was accepted, making Beca the next custodian of the NZGD.
In November 2024, it launched the updated NZGD, which now runs on an SQL database on Microsoft Azure and is accessed via BEYON.
“Our focus was making it modern, secure, standards-compliant and integrated with modern spatial analytics technologies,” said Beca’s Witherden. “So that allows us to have better data quality, usability and access.”
Beca opted for digital twin technology, said Witherden, because it’s the best way to curate and manage complex, interconnected engineering information.
Shifting NZGD’s technology stack to Azure made it more accessible, scalable and secure, said Witherden, with access controls like Azure Entra ID. It also set the foundation for more bells and whistles.
In late 2025, Beca added an agentic AI layer in BEYON, enabling over 4,300 NZGD users to filter, query and extract geotechnical data using natural language. The AI assistant was designed in Microsoft Foundry, with strict rules guiding its responses.
“Using Microsoft Foundry has been such a great tool for us because it has built-in guardrails, and that allows us to control how the AI responds,” said Witherden. “It’s not allowed to do geotechnical analysis.”
Having all this data and technology on tap means users like Ellis-Garland can make better decisions, faster.
The AI assistant not only zeroes in on the investigation logs for her; it helps her cut through the ensuing information overload.
“What is really helpful is you can eliminate data that you don’t need,” she said. She can ask the AI to only show her cone penetration tests, for example, and remove investigations done using hand augers.
Beca estimates that with the AI assistant, engineers on average take 40% less time to retrieve the data they need.
Meanwhile, the more data is shared, the higher the confidence level.
At the Hobsonville site, Ellis-Garland saved time and expense because she knew where to target ground investigations for the 400 homes her client was building. Earlier scans of the surrounding area on NZGD already told her how and where the geology changed.
“Because it’s such a good platform, all of the engineers have been using it and uploading data. So, we’re able to stay current with more and more information to draw on,” said Ellis-Garland. “The NZGD is like our Earth library.”
Detailed analysis, such as assessing slope stability or liquefaction – the phenomenon where ground behaves like liquid during a temblor – require a consistent stream of data on which calculations can be run.
“The more that we have of that, the better our job is,” said Ellis-Garland. “We can now build better because we’ve got so many more resources to draw from.”
More improvements are in store, said Witherden, to provide richer visualizations of NZGD data and use AI to boost the audit and review process, which ensures the information uploaded is accurate and reliable.
“Having better access to this data makes for more resilience and safer and better prepared communities,” he said.
For Beca, NZGD on BEYON is now part of its legacy as the country’s largest professional services consultancy.
“Our purpose is to make every day better,” said CEO Linzey. “This is us thinking about how we can bring together a hundred-year legacy of being in New Zealand and all the work that we’ve done, including the geotechnical information that has been collected. And giving it in a way that can help our clients make decisions for the future prosperity of the country.”
Top image caption: Engineering geologist Olivia Ellis-Garland, shown here at a building site in Hobsonville, Auckland, describes the Microsoft Azure-powered New Zealand Geotechnical Database (NZGD) as “our gateway to the ground”. Photo by Radical for Microsoft.
Lim Ai Leen reports on AI for Microsoft Source, focusing on how it’s improving lives in Asia. Ai Leen was formerly associate foreign editor at The Straits Times in Singapore and still pens an occasional weekend column. Contact her on LinkedIn.