III: Small: Spatial Deep Learning from Imperfect Volunteered Geographic Information

III：小：从不完美的自愿地理信息中进行空间深度学习

• 批准号: 2207072
• 负责人: Zhe Jiang
• 金额: $ 50万
• 依托单位: University of Florida
• 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: 2021-10-01 至 2024-11-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2207072&HistoricalAwards=false
• 关键词: III; Small; Spatial; Deep; Learning

This project aims to investigate novel spatial machine learning algorithms based on imperfect volunteered geographical information as ground truth for applications at the intersection of machine learning and geographic information science. The rapid growth of geospatial and spatiotemporal data being collected from space, airborne, and terrestrial platforms provides scientists, farmers, and first responders critical information they need about the surface of the Earth. This emerging area that intersects machine learning, especially deep learning, with geographic information science is called GeoAI. GeoAI can potentially transform society by addressing grand challenges such as rapid disaster response, water resource management, and transportation. One major obstacle, however, is that deep learning heavily relies on a large number of training labels, which are often not easily available for geographic applications due to slow and expensive field surveys. Existing research on semi-supervised learning could not fully resolve the issues due to the complex nature of geographic data such as spatial heterogeneity. This project will fill the gap by exploiting large scale, low-cost, and near real-time volunteered geographic information. The project will contribute towards the next generation water resource management for the U.S. in the 21st century. This research can not only improve the situational awareness for disaster response agencies but also enhance the flood forecasting capabilities of the National Water Model. Planned algorithms will be implemented into open source tools that will enhance the research infrastructure for disaster management and hydrology communities. Educational activities include curriculum development, K-12 computer science education at Alabama Computer Science Summer Camps. The principal investigator has a past record in mentoring undergraduate students from a historically black university and will continue the efforts at the University of Alabama, which has a reputation for producing African American researchers. The planned framework will bring about several innovations to address significant technical challenges due to data quality issues. First, to address the noisy, biased, and incomplete label semantics, the project will develop novel label enhancement and enrichment algorithms based on physics-aware spatial structural constraints, which advance existing methods (that often assume independent labels) by jointly enhancing labels based on structural dependency. Second, the project will explore a new location error model that better captures geometric shapes than existing square patch-based models, and design efficient joint learning algorithms to update deep model parameters while inferring true shape locations. Finally, to address location ambiguity, the project will explore location ambiguity models and mitigating location ambiguity by leveraging geographical contexts from input imagery features as well as spatial hierarchical constraints. Such ideas advance existing location disambiguation methods merely based on the textual semantic context in natural language processing. The project can potentially transform the field of geospatial data science by addressing a major obstacle of limited training labels by a systematic framework of exploiting large-scale, low-cost, and near real-time volunteered geographic information data. The project can potentially make transformative impacts on interdisciplinary GeoAI applications such as rapid disaster response and national water forecasting. This project is jointly funded by III and the Established Program to Stimulate Competitive Research (EPSCoR).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.

该项目旨在研究基于不完全自愿地理信息的新型空间机器学习算法，作为机器学习和地理信息科学交叉应用的基础。从太空、空中和地面平台收集的地理空间和时空数据的快速增长，为科学家、农民和急救人员提供了他们所需的关于地球表面的关键信息。这个将机器学习（尤其是深度学习）与地理信息科学相结合的新兴领域被称为GeoAI。GeoAI可以通过解决诸如快速灾害响应、水资源管理和交通运输等重大挑战来潜在地改变社会。然而，一个主要的障碍是，深度学习严重依赖于大量的训练标签，由于缓慢而昂贵的实地调查，这些标签通常不容易用于地理应用。由于地理数据的空间异质性等复杂性，现有的半监督学习研究还不能完全解决这些问题。该项目将通过利用大规模、低成本和接近实时的志愿地理信息来填补这一空白。该项目将为21世纪美国的下一代水资源管理做出贡献。本研究不仅可以提高灾害响应机构的态势感知能力，还可以提高国家水文模型的洪水预报能力。计划中的算法将被实施到开源工具中，这将增强灾害管理和水文学社区的研究基础设施。教育活动包括课程开发，阿拉巴马州计算机科学夏令营的K-12计算机科学教育。首席研究员过去曾指导过一所历史悠久的黑人大学的本科生，并将继续在以培养非裔美国人研究人员而闻名的阿拉巴马大学努力。计划中的框架将带来一些创新，以解决数据质量问题带来的重大技术挑战。首先，为了解决有噪声、有偏差和不完整的标签语义，该项目将开发基于物理感知的空间结构约束的新型标签增强和丰富算法，通过基于结构依赖性共同增强标签来推进现有方法（通常假设独立标签）。其次，该项目将探索一种新的位置误差模型，该模型比现有的基于正方形补丁的模型更好地捕获几何形状，并设计有效的联合学习算法，在推断真实形状位置的同时更新深度模型参数。最后，为了解决位置模糊问题，该项目将探索位置模糊模型，并通过利用输入图像特征中的地理背景以及空间层次约束来减轻位置模糊。这些思想对自然语言处理中现有的仅基于文本语义上下文的位置消歧方法进行了改进。该项目通过利用大规模、低成本和接近实时的志愿地理信息数据的系统框架，解决了训练标签有限的主要障碍，可能会改变地理空间数据科学领域。该项目可能对跨学科的GeoAI应用产生变革性影响，例如快速灾害响应和国家水资源预报。本项目由III和促进竞争研究的既定计划（EPSCoR）共同资助。该奖项反映了美国国家科学基金会的法定使命，并通过使用基金会的知识价值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

An elevation-guided annotation tool for flood extent mapping on earth imagery (demo paper)

用于在地球图像上绘制洪水范围的高程引导注释工具（演示论文）

• DOI: 10.1145/3557915.3560962
• 发表时间: 2022
• 期刊: SIGSPATIAL '22: Proceedings of the 30th International Conference on Advances in Geographic Information Systems
• 作者: Adhikari, Saugat;Yan, Da;Sami, Mirza Tanzim;Khalil, Jalal;Yuan, Lyuheng;Joy, Bhadhan Roy;Jiang, Zhe;Sainju, Arpan Man
• 通讯作者: Sainju, Arpan Man

Deep Neural Network for 3D Surface Segmentation based on Contour Tree Hierarchy

• DOI: 10.1137/1.9781611976700.29
• 发表时间: 2020-08
• 期刊: ArXiv
• 作者: Wenchong He;Arpan Man Sainju;Zhe Jiang;Da Yan

Semi-supervised Learning with the EM Algorithm: A Comparative Study between Unstructured and Structured Prediction

EM 算法的半监督学习：非结构化和结构化预测的比较研究

• DOI: 10.1109/tkde.2020.3019038
• 发表时间: 2020
• 期刊: IEEE Transactions on Knowledge and Data Engineering
• 影响因子: 8.9
• 作者: He, Wenchong;Jiang, Zhe
• 通讯作者: Jiang, Zhe

Weakly Supervised Spatial Deep Learning based on Imperfect Vector Labels with Registration Errors

• DOI: 10.1145/3447548.3467301
• 发表时间: 2021-08
• 期刊: Proceedings of the 27th ACM SIGKDD Conference on Knowledge Discovery & Data Mining
• 作者: Zhe Jiang;Wenchong He;M. Kirby;S. Asiri;Dan Yan

A Hidden Markov Forest Model for Terrain-Aware Flood Inundation Mapping from Earth Imagery

用于根据地球图像进行地形感知洪水淹没绘图的隐马尔可夫森林模型

• 发表时间: 2023
• 期刊: Proceedings of the 2023 SIAM International Conference on Data Mining (SDM
• 作者: Jiang, Zhe;Zhang, Yupu;Adhikari, Saugat;Yan, Da;Sainju, Arpan Man;Jia, Xiaowei;Xie, Yiqun
• 通讯作者: Xie, Yiqun