Tobler’s First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection under Weak Supervision
The DOI matches its Crossref record; 9 of the 9 references it cites were found in a registry or an index.
Abstract
Recent interest in geospatial artificial intelligence (GeoAI) has fostered a wide range of applications using artificial intelligence (AI), especially deep learning for geospatial problem solving. Major challenges, however, such as a lack of training data and ignorance of spatial principles and spatial effects in AI model design remain, significantly hindering the in-depth integration of AI with geospatial research. This article reports our work in developing a cutting-edge deep learning model that enables object detection, especially of natural features, in a weakly supervised manner. Our work has made three innovative contributions: First, we present a novel method of object detection using only weak labels. This is achieved by developing a spatially explicit model according to Tobler’s first law of geography to enable weakly supervised object detection. Second, we integrate the idea of an attention map into the deep learning–based object detection pipeline and develop a multistage training strategy to further boost detection performance. Third, we have successfully applied this model for the automated detection of Mars impact craters, the inspection of which often involved tremendous manual work prior to our solution. Our model is generalizable for detecting both natural and man-made features on the surface of the Earth and other planets. This research has made a major contribution to the enrichment of the theoretical and methodological body of knowledge of GeoAI.
Overview
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Integrity signals
Registry
Cites
Statistics
Verification
Claims the paper makes
The claims and statistics of this paper haven’t been checked yet.
Free: it reads the open-access text and checks the first 5 claims that cite a source we can check. Create a free account to check every claim.
Self-check
Percentages, sums and reported differences re-computed from the paper’s own numbers.
The self-check needs the paper’s full text.
Citations
Cites
Faster R-CNN: Towards Real-Time Object Detection with Region Proposal Networks
Ren, S., He, K., Girshick, R., & Sun, J. (2017) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2016.2577031 · Cited by 73,472
Remote Sensing Image Scene Classification: Benchmark and State of the Art
Cheng, G., Han, J., & Lu, X. (2017) · Proceedings of the IEEE · doi:10.1109/jproc.2017.2675998 · Cited by 2,926
Edge Boxes: Locating Object Proposals from Edges
Zitnick, C. L., & Dollár, P. (2014) · Lecture Notes in Computer Science · doi:10.1007/978-3-319-10602-1_26 · Cited by 2,656
Cheng, G., Zhou, P., & Han, J. (2016) · IEEE Transactions on Geoscience and Remote Sensing · doi:10.1109/tgrs.2016.2601622 · Cited by 1,771
Learning RoI Transformer for Oriented Object Detection in Aerial Images
Ding, J., Xue, N., Long, Y., Xia, G.-S., & Lu, Q. (2019) · 2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR) · doi:10.1109/cvpr.2019.00296 · Cited by 1,666
Object Detectors Emerge in Deep Scene CNNs
Zhou, B., Khosla, A., Lapedriza, A., Oliva, A., & Torralba, A. (2014) · arXiv · doi:10.48550/arxiv.1412.6856 · Cited by 971
What Makes for Effective Detection Proposals?
Hosang, J., Benenson, R., Dollar, P., & Schiele, B. (2016) · IEEE Transactions on Pattern Analysis and Machine Intelligence · doi:10.1109/tpami.2015.2465908 · Cited by 727
PatternNet: A benchmark dataset for performance evaluation of remote sensing image retrieval
Zhou, W., Newsam, S., Li, C., & Shao, Z. (2018) · ISPRS Journal of Photogrammetry and Remote Sensing · doi:10.1016/j.isprsjprs.2018.01.004 · Cited by 571
Cheng, G., Han, J., Zhou, P., & Xu, D. (2019) · IEEE Transactions on Image Processing · doi:10.1109/tip.2018.2867198 · Cited by 408 · cited 1×
“In addition, weakly supervised learning and target detection from remote sensing image has been exploited by geospatial researchers.”
Research works printed but not linked: 43
- Anselin, L. 1995. Local indicators of spatial association—LISA. Geographical Analysis 27 (2): 93–115. · DOI · Paper page
- 10.7287/peerj.preprints.27072v1 · doi:10.7287/peerj.preprints.27072v1
- Barrett B., 2013, Remote sensing of energy fluxes and soil moisture content, ed. G. P. Petropoulos,, 85, 10.1201/b15610-6 · doi:10.1201/b15610-6
- 10.3390/rs9020100 · DOI · Paper page
- Bilen, H., and A. Vedaldi. 2016. Weakly supervised deep detection networks. In Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition, ed. L. Agapito, T. Berg, J. Kosecka, and L. Zelnik-Manor, 2846–54. Las Vegas: IEEE. · DOI · Paper page
- 10.1016/j.isprsjprs.2009.06.004 · DOI · Paper page
- 10.1029/2010JE003755 · DOI · Paper page
- Fotheringham A. S., 2003, Geographically weighted regression: The analysis of spatially varying relationships
- 10.1080/13658816.2019.1652304 · DOI
- Gao, M., A. Li, R. Yu, V. I. Morariu, and L. S. Davis. 2018. C-WSL: Count-guided weakly supervised localization. In Proceedings of the European conference on computer vision (ECCV), 152–68. Munich, Germany, September 8–14.
- Gao, Y., et al. 2019. C-MIDN: Coupled multiple instance detection network with segmentation guidance for weakly supervised object detection. In Proceedings of the IEEE/CVF International Conference on Computer Vision, 9834–43. Seoul, Korea, October 27–November 2, 2019.
- Goodchild, M. F. 2004. The validity and usefulness of laws in geographic information science and geography. Annals of the Association of American Geographers 94 (2): 300–303. · DOI · Paper page
- 10.1080/13658810701850497 · doi:10.1080/13658810701850497
- 10.1109/TGRS.2014.2374218 · DOI · Paper page
- 10.1045/january99-hill · doi:10.1045/january99-hill
- Hsu, C. Y., and W. Li. 2020. Learning from counting: Leveraging temporal classification for weakly supervised object localization and detection. The 31st British Machine Vision Virtual Conference, September 7-10, 2020 (virtual), Paper ID: 0621. https://www.bmvc2020-conference.com/assets/papers/0621.pdf
- 10.1016/j.geomorph.2012.11.005 · DOI · Paper page
- Kamusoko C., 2017, Urban development in Asia and Africa, 3, 10.1007/978-981-10-3241-7_1 · DOI
- Li, H., X. Dou, C. Tao, Z. Hou, J. Chen, J. Peng, M. Deng, and L. Zhao. 2017. RSI-CB: A large scale remote sensing image classification benchmark via crowdsource data. arXiv:1705.10450. · arXiv
- 10.5311/JOSIS.2020.20.658 · DOI · Paper page
- 10.1080/13658816.2018.1542697 · DOI · Paper page
- Li, W., B. Zhou, C. Y. Hsu, Y. Li, and F. Ren. 2017. Recognizing terrain features on terrestrial surface using a deep learning model. An example with crater detection. In Proceedings of the 1st Workshop on Artificial Intelligence and Deep Learning for Geographic Knowledge Discovery, ed. H. Mao, Y. Hu, and B. Kar, 33–36. Los Angeles: ACM. · DOI · Paper page
- Liao, M., Z. Zhu, B. Shi, G.S. Xia, and X. Bai. 2018. Rotation-sensitive regression for oriented scene text detection. In Proceedings of the IEEE conference on computer vision and pattern recognition, 5909–18. Salt Lake City, UT, June 18–22.
- 10.1080/13658816.2014.975715 · DOI
- 10.1109/LGRS.2015.2439517 · DOI · Paper page
- 10.1109/TGRS.2016.2645610 · DOI · Paper page
- 10.1007/s11004-013-9511-0 · DOI · Paper page
- 10.1029/2011JE003966 · DOI · Paper page
- Tang P., 2017, Proceedings of the IEEE Conference on Computer Vision and Pattern Recognition (CVPR 2017, 2843
- Tang P., 2018, ., 352
- 10.2307/143141 · DOI · Paper page
- 10.1016/j.proeng.2016.08.134 · doi:10.1016/j.proeng.2016.08.134
- 10.1007/s11263-013-0620-5 · DOI · Paper page
- 10.1109/TGRS.2017.2685945 · DOI · Paper page
- 10.3390/rs9121312 · DOI · Paper page
- 10.1145/1869790.1869829 · DOI · Paper page
- 10.1109/LGRS.2015.2432135 · DOI
- Zhang D., 2014, IEEE Geoscience and Remote Sensing Letters, 12, 701, 10.1109/LGRS.2014.2358994 · DOI · Paper page
- 10.1109/ACCESS.2019.2960931 · DOI
- 10.1016/j.isprsjprs.2018.02.014 · DOI
- 10.1007/s11045-015-0370-3 · DOI
- 10.1080/13658816.2018.1554814 · DOI
- 10.1080/24694452.2019.1694403 · DOI
Cited by
Li, W., & Hsu, C.-Y. (2022) · ISPRS International Journal of Geo-Information · doi:10.3390/ijgi11070385 · Cited by 147
Self-citationHsu, C.-Y., Li, W., & Wang, S. (2021) · Remote Sensing · doi:10.3390/rs13112116 · Cited by 53
“[26] integrate Tobler’s First Law in Geography to leverage an important principle of spatial dependence to achieve weakly supervised object detection leveraging temporal data classification [32].”
BackgroundSelf-citationAssessment of a new GeoAI foundation model for flood inundation mapping
Li, W., Lee, H., Wang, S., Hsu, C.-Y., & Arundel, S. T. (2023) · arXiv · doi:10.48550/arxiv.2309.14500 · Cited by 40
Self-citationAssessment of a new GeoAI foundation model for flood inundation mapping
Li, W., Lee, H., Wang, S., Hsu, C.-Y., & Arundel, S. T. (2023) · Proceedings of the 6th ACM SIGSPATIAL International Workshop on AI for Geographic Knowledge Discovery · doi:10.1145/3615886.3627747 · Cited by 39
Self-citation
Metadata
- Authors
- Li, W., Hsu, C.-Y., & Hu, M.
- Venue
- Annals of the American Association of Geographers
- Publisher
- Informa UK Limited
- Published
- 2021-04-23
- Pages
- 1-19
- ISSN
- 2469-4452 (ISSN-L)
- 2469-4460
- OpenAlex
- W3172509672
- Cited by
- 52
- References
- 9
- FWCI
- 3.44
- Type
- journal article
- Language
- en
- Open access
- closed
- Funders
- National Science Foundation (BCS-1853864, BCS-1455349, OIA-2033521, OIA-1936677, OIA- 1937908)
About these checks
Registry, retraction, Cites and statistics results are computed, not judged, with one exception: a printed reference that no index lists is read once by a model before it counts as a citation error. Claims are extracted by a model and kept only when their quote appears verbatim in the text; each cited source is then checked, with a model’s help, for whether it says what the claim relies on. Those verdicts can be wrong — read the claim’s quote and the cited source before relying on one.
Statistics and arithmetic are recomputed, not judged.
Confidence bands are shown only for fields calibrated on our annotated test set. None is calibrated yet, so no band is shown.
What counts as a claim ›How we measure confidence ›How we check this ›
Are you an author, or do you see a problem with this page? Request a review
How to cite
Cite CoChat for the checks on this page, and the paper for its own findings.
- This page
- CoChat. (2026). Citation check: Tobler’s First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection under Weak Supervision. https://app.cochat.ai/papers/10.1080/24694452.2021.1877527
- The paper
- Li, W., Hsu, C.-Y., & Hu, M. (2021). Tobler’s First Law in GeoAI: A Spatially Explicit Deep Learning Model for Terrain Feature Detection under Weak Supervision. Annals of the American Association of Geographers. https://doi.org/10.1080/24694452.2021.1877527
Data sources
Bibliographic data: Semantic Scholar, OpenAlex, Crossref.
Contains information from the Semantic Scholar Academic Graph Datasets, made available under the ODC Attribution License (ODC-BY 1.0).
Semantic Scholar’s data is described in: Kinney, R., et al. (2023). The Semantic Scholar Open Data Platform. arXiv:2301.10140.