Geospatial Artificial Intelligence Approaches for Understanding Location Descriptions in Natural Disasters and Their Spatial Biases

用于理解自然灾害位置描述及其空间偏差的地理空间人工智能方法

• 批准号: 2117771
• 负责人: Yingjie Hu
• 金额: $ 37.89万
• 依托单位: SUNY at Buffalo
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2021
• 资助国家: 美国
• 起止时间: 2021-09-01 至 2026-08-31
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2117771&HistoricalAwards=false
• 关键词: Geospatial; Artificial; Intelligence; Approaches; Understanding

The objective of this project is to understand how people describe locations on social media during natural disasters. These data from social media are potentially beneficial in disaster response efforts, and to further this goal, computational algorithms are being developed to extract location information from social media postings. However, uneven use of social media by different populations and varying ways of describing places can complicate the process of identifying locations. This project advances knowledge by enhancing the understanding of the ways in which people describe geographic locations during natural disasters, the effectiveness of different algorithmic approaches for location extraction, and the potential spatial biases in the described locations. Such knowledge benefits society by informing future disaster response practices to help save lives and reduce inequality in response efforts. This project provides interdisciplinary research experience for undergraduates and graduates and will enhance academia and industry partnership. The datasets and algorithmic tools produced from this project will be publicly shared. Social media platforms, such as Twitter, are increasingly being used by people impacted by natural disasters. Descriptions about the locations of victims and accidents are often contained in help-seeking messages posted on these platforms. However, a limited understanding exists of how locations are described on social media during natural disasters, which hinders their automatic extraction via computational tools. This project addresses three research questions: (1) What are the typical forms of location descriptions used by people on social media during natural disasters? (2) How effective are different geospatial artificial intelligence (GeoAI) approaches for extracting these location descriptions and representing them in geographic space? And (3) What spatial biases have characterized location descriptions on social media during natural disasters? The research team is collaborating with emergency management specialists to understand location descriptions on social media, examine multiple geo-knowledge-informed AI approaches for location extraction, and investigate the spatial biases of the extracted locations and their relation to vulnerable communities. The obtained knowledge about location descriptions and the developed methods can be applied to future disasters in diverse settings.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.

这个项目的目标是了解人们在自然灾害期间如何在社交媒体上描述地点。来自社交媒体的这些数据在灾难应对工作中可能是有益的，为了进一步实现这一目标，正在开发计算算法，以从社交媒体帖子中提取位置信息。然而，不同人群对社交媒体的不均衡使用以及描述地点的不同方式可能会使识别地点的过程复杂化。该项目通过加强人们在自然灾害期间描述地理位置的方式、提取位置的不同算法的有效性以及所描述位置中潜在的空间偏差的理解来促进知识的发展。这种知识使社会受益，因为它为未来的灾害应对做法提供信息，以帮助拯救生命和减少应对工作中的不平等。该项目为本科生和毕业生提供跨学科的研究经验，并将加强学术界和产业界的合作。该项目产生的数据集和算法工具将公开共享。Twitter等社交媒体平台正越来越多地被受自然灾害影响的人们使用。关于遇难者和事故地点的描述通常包含在这些平台上发布的求助消息中。然而，对于自然灾害期间社交媒体上如何描述地点存在有限的理解，这阻碍了通过计算工具自动提取地点。该项目解决了三个研究问题：(1)自然灾害期间人们在社交媒体上使用的位置描述的典型形式是什么？(2)不同的地理空间人工智能(GeoAI)方法在提取这些位置描述并在地理空间中表示它们的效率如何？以及(3)在自然灾害期间，社交媒体上的位置描述存在哪些空间偏向？研究团队正在与应急管理专家合作，以了解社交媒体上的位置描述，检查多种利用地理知识进行位置提取的人工智能方法，并调查提取的位置的空间偏差及其与脆弱社区的关系。获得的位置描述知识和开发的方法可以应用于不同环境下的未来灾难。这一奖项反映了NSF的法定使命，并通过使用基金会的智力优势和更广泛的影响审查标准进行评估，被认为值得支持。

项目成果

Towards a foundation model for geospatial artificial intelligence (vision paper)

• DOI: 10.1145/3557915.3561043
• 发表时间: 2022-11
• 期刊: Proceedings of the 30th International Conference on Advances in Geographic Information Systems
• 作者: Gengchen Mai;Chris Cundy;Kristy Choi;Yingjie Hu;Ni Lao;Stefano Ermon

How Do People Describe Locations During a Natural Disaster: An Analysis of Tweets from Hurricane Harvey

人们如何描述自然灾害期间的地点：对飓风哈维的推文分析

• 发表时间: 2021
• 期刊: 11th International Conference on Geographic Information Science
• 作者: Hu, Yingjie;Wang, Jimin
• 通讯作者: Wang, Jimin

Geo-knowledge-guided GPT models improve the extraction of location descriptions from disaster-related social media messages

• DOI: 10.1080/13658816.2023.2266495
• 发表时间: 2023-10
• 期刊: International Journal of Geographical Information Science
• 影响因子: 5.7
• 作者: Yingjie Hu;Gengchen Mai;Chris Cundy;Kristy Choi;Ni Lao;Wei Liu;Gaurish Lakhanpal;Ryan Zhenqi Zhou;Kenneth Joseph

A review of location encoding for GeoAI: methods and applications

• DOI: 10.1080/13658816.2021.2004602
• 发表时间: 2021-11
• 期刊: International Journal of Geographical Information Science
• 影响因子: 5.7
• 作者: Gengchen Mai;K. Janowicz;Yingjie Hu;Song Gao;Bo Yan;Rui Zhu;Ling Cai;Ni Lao

TopoBERT: a plug and play toponym recognition module harnessing fine-tuned BERT

• DOI: 10.1080/17538947.2023.2239794
• 发表时间: 2023-08
• 期刊: International Journal of Digital Earth
• 影响因子: 5.1
• 作者: Bing Zhou;Lei Zou;Yingjie Hu;Yi Qiang;Daniel Goldberg