Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision
ACM Transactions on Spatial Algorithms and Systems · 30.09.2023 · 9 (3) · 1-26
DOI: 10.1145/3605358 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Transactions on Spatial Algorithms and Systems, online erschienen am 16.08.2023. Verfasst von Minxing Zhang und 3 weiteren Autor:innen. Die Arbeit wurde bisher 6-mal zitiert (Crossref) und nennt 53 Literaturangaben. Gefördert von: National Science Foundation, Computing Research Association/NSF Sub, Department of Homeland Security.
Abstract (Originalsprache)
Spatial prediction is to predict the values of the targeted variable, such as PM2.5 values and temperature, at arbitrary locations based on the collected geospatial data. It greatly affects the key research topics in geoscience in terms of obtaining heterogeneous spatial information (e.g., soil conditions, precipitation rates, wheat yields) for geographic modeling and decision-making at local, regional, and global scales. In situ data, collected by ground-level in situ sensors, and remote sensing data, collected by satellite or aircraft, are two important data sources for this task. In situ data are relatively accurate while sparse and unevenly distributed. Remote sensing data cover large spatial areas, but are coarse with low spatiotemporal resolution and prone to interference. How to synergize the complementary strength of these two data types is still a grand challenge. Moreover, it is difficult to model the unknown spatial predictive mapping while handling the tradeoff between spatial autocorrelation and heterogeneity. Third, representing spatial relations without substantial information loss is also a critical issue. To address these challenges, we propose a novel Heterogeneous Self-supervised Spatial Prediction (HSSP) framework that synergizes multi-source data by minimizing the inconsistency between in situ and remote sensing observations. We propose a new deep geometric spatial interpolation model as the prediction backbone that automatically interpolates the values of the targeted variable at unknown locations based on existing observations by taking into account both distance and orientation information. Our proposed interpolator is proven to both be the general form of popular interpolation methods and preserve spatial information. The spatial prediction is enhanced by a novel error-compensation framework to capture the prediction inconsistency due to spatial heterogeneity. Extensive experiments have been conducted on real-world datasets and demonstrated our model’s superiority in performance over state-of-the-art models.
Förderung
- National Science Foundation
- Computing Research Association/NSF Sub
- Department of Homeland Security
- Jeffress Memorial Trust Award, Amazon Research Award, NVIDIA GPU
- Design Knowledge Company
Zitieren
APA
Zhang, M., Yu, D., Li, Y., & Zhao, L. (2023). Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision. ACM Transactions on Spatial Algorithms and Systems, 9(3), 1-26. https://doi.org/10.1145/3605358
Vancouver
Zhang M, Yu D, Li Y, Zhao L. Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision. ACM Transactions on Spatial Algorithms and Systems. 2023;9(3):1-26. doi:10.1145/3605358
BibTeX
@article{Zhang2023,
author = {Zhang, Minxing and Yu, Dazhou and Li, Yun and Zhao, Liang},
title = {Deep Spatial Prediction via Heterogeneous Multi-source Self-supervision},
journal = {ACM Transactions on Spatial Algorithms and Systems},
year = {2023},
volume = {9},
number = {3},
pages = {1--26},
doi = {10.1145/3605358}
}
EUVIMED