Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band Adaptability Article Swipe
Wenwen Li
,
Sizhe Wang
,
Hyunho Lee
,
Cheng-Ze Lu
,
Sujit Roy
,
Rahul Ramachandran
,
Chia-Yu Hsu
·
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2511.04474
YOU?
·
· 2025
· Open Access
·
· DOI: https://doi.org/10.48550/arxiv.2511.04474
Landslides cause severe damage to lives, infrastructure, and the environment, making accurate and timely mapping essential for disaster preparedness and response. However, conventional deep learning models often struggle when applied across different sensors, regions, or under conditions of limited training data. To address these challenges, we present a three-axis analytical framework of sensor, label, and domain for adapting geospatial foundation models (GeoFMs), focusing on Prithvi-EO-2.0 for landslide mapping. Through a series of experiments, we show that it consistently outperforms task-specific CNNs (U-Net, U-Net++), vision transformers (Segformer, SwinV2-B), and other GeoFMs (TerraMind, SatMAE). The model, built on global pretraining, self-supervision, and adaptable fine-tuning, proved resilient to spectral variation, maintained accuracy under label scarcity, and generalized more reliably across diverse datasets and geographic settings. Alongside these strengths, we also highlight remaining challenges such as computational cost and the limited availability of reusable AI-ready training data for landslide research. Overall, our study positions GeoFMs as a step toward more robust and scalable approaches for landslide risk reduction and environmental monitoring.
Related Topics
Concepts
No concepts available.
Metadata
- Type
- preprint
- Landing Page
- http://arxiv.org/abs/2511.04474
- https://arxiv.org/pdf/2511.04474
- OA Status
- green
- OpenAlex ID
- https://openalex.org/W4416026364
All OpenAlex metadata
Raw OpenAlex JSON
- OpenAlex ID
-
https://openalex.org/W4416026364Canonical identifier for this work in OpenAlex
- DOI
-
https://doi.org/10.48550/arxiv.2511.04474Digital Object Identifier
- Title
-
Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band AdaptabilityWork title
- Type
-
preprintOpenAlex work type
- Publication year
-
2025Year of publication
- Publication date
-
2025-11-06Full publication date if available
- Authors
-
Wenwen Li, Sizhe Wang, Hyunho Lee, Cheng-Ze Lu, Sujit Roy, Rahul Ramachandran, Chia-Yu HsuList of authors in order
- Landing page
-
https://arxiv.org/abs/2511.04474Publisher landing page
- PDF URL
-
https://arxiv.org/pdf/2511.04474Direct link to full text PDF
- Open access
-
YesWhether a free full text is available
- OA status
-
greenOpen access status per OpenAlex
- OA URL
-
https://arxiv.org/pdf/2511.04474Direct OA link when available
- Cited by
-
0Total citation count in OpenAlex
Full payload
| id | https://openalex.org/W4416026364 |
|---|---|
| doi | https://doi.org/10.48550/arxiv.2511.04474 |
| ids.doi | https://doi.org/10.48550/arxiv.2511.04474 |
| ids.openalex | https://openalex.org/W4416026364 |
| fwci | |
| type | preprint |
| title | Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band Adaptability |
| biblio.issue | |
| biblio.volume | |
| biblio.last_page | |
| biblio.first_page | |
| is_xpac | False |
| apc_list | |
| apc_paid | |
| language | |
| locations[0].id | pmh:oai:arXiv.org:2511.04474 |
| locations[0].is_oa | True |
| locations[0].source.id | https://openalex.org/S4306400194 |
| locations[0].source.issn | |
| locations[0].source.type | repository |
| locations[0].source.is_oa | True |
| locations[0].source.issn_l | |
| locations[0].source.is_core | False |
| locations[0].source.is_in_doaj | False |
| locations[0].source.display_name | arXiv (Cornell University) |
| locations[0].source.host_organization | https://openalex.org/I205783295 |
| locations[0].source.host_organization_name | Cornell University |
| locations[0].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[0].license | cc-by-nc-nd |
| locations[0].pdf_url | https://arxiv.org/pdf/2511.04474 |
| locations[0].version | submittedVersion |
| locations[0].raw_type | text |
| locations[0].license_id | https://openalex.org/licenses/cc-by-nc-nd |
| locations[0].is_accepted | False |
| locations[0].is_published | False |
| locations[0].raw_source_name | |
| locations[0].landing_page_url | http://arxiv.org/abs/2511.04474 |
| locations[1].id | doi:10.48550/arxiv.2511.04474 |
| locations[1].is_oa | True |
| locations[1].source.id | https://openalex.org/S4306400194 |
| locations[1].source.issn | |
| locations[1].source.type | repository |
| locations[1].source.is_oa | True |
| locations[1].source.issn_l | |
| locations[1].source.is_core | False |
| locations[1].source.is_in_doaj | False |
| locations[1].source.display_name | arXiv (Cornell University) |
| locations[1].source.host_organization | https://openalex.org/I205783295 |
| locations[1].source.host_organization_name | Cornell University |
| locations[1].source.host_organization_lineage | https://openalex.org/I205783295 |
| locations[1].license | |
| locations[1].pdf_url | |
| locations[1].version | |
| locations[1].raw_type | article |
| locations[1].license_id | |
| locations[1].is_accepted | False |
| locations[1].is_published | |
| locations[1].raw_source_name | |
| locations[1].landing_page_url | https://doi.org/10.48550/arxiv.2511.04474 |
| indexed_in | arxiv, datacite |
| authorships[0].author.id | https://openalex.org/A5100338178 |
| authorships[0].author.orcid | https://orcid.org/0000-0003-1868-1302 |
| authorships[0].author.display_name | Wenwen Li |
| authorships[0].author_position | first |
| authorships[0].raw_author_name | Li, Wenwen |
| authorships[0].is_corresponding | False |
| authorships[1].author.id | https://openalex.org/A5101536427 |
| authorships[1].author.orcid | https://orcid.org/0000-0002-3385-5246 |
| authorships[1].author.display_name | Sizhe Wang |
| authorships[1].author_position | middle |
| authorships[1].raw_author_name | Wang, Sizhe |
| authorships[1].is_corresponding | False |
| authorships[2].author.id | https://openalex.org/A5102019817 |
| authorships[2].author.orcid | https://orcid.org/0000-0002-7602-1639 |
| authorships[2].author.display_name | Hyunho Lee |
| authorships[2].author_position | middle |
| authorships[2].raw_author_name | Lee, Hyunho |
| authorships[2].is_corresponding | False |
| authorships[3].author.id | https://openalex.org/A5065936389 |
| authorships[3].author.orcid | https://orcid.org/0000-0002-8225-6311 |
| authorships[3].author.display_name | Cheng-Ze Lu |
| authorships[3].author_position | middle |
| authorships[3].raw_author_name | Lu, Chenyan |
| authorships[3].is_corresponding | False |
| authorships[4].author.id | https://openalex.org/A5045276240 |
| authorships[4].author.orcid | https://orcid.org/0000-0002-5592-4011 |
| authorships[4].author.display_name | Sujit Roy |
| authorships[4].author_position | middle |
| authorships[4].raw_author_name | Roy, Sujit |
| authorships[4].is_corresponding | False |
| authorships[5].author.id | https://openalex.org/A5010966122 |
| authorships[5].author.orcid | https://orcid.org/0000-0002-0647-1941 |
| authorships[5].author.display_name | Rahul Ramachandran |
| authorships[5].author_position | middle |
| authorships[5].raw_author_name | Ramachandran, Rahul |
| authorships[5].is_corresponding | False |
| authorships[6].author.id | https://openalex.org/A5104282931 |
| authorships[6].author.orcid | |
| authorships[6].author.display_name | Chia-Yu Hsu |
| authorships[6].author_position | last |
| authorships[6].raw_author_name | Hsu, Chia-Yu |
| authorships[6].is_corresponding | False |
| has_content.pdf | True |
| has_content.grobid_xml | False |
| is_paratext | False |
| open_access.is_oa | True |
| open_access.oa_url | https://arxiv.org/pdf/2511.04474 |
| open_access.oa_status | green |
| open_access.any_repository_has_fulltext | False |
| created_date | 2025-11-08T00:00:00 |
| display_name | Landslide Hazard Mapping with Geospatial Foundation Models: Geographical Generalizability, Data Scarcity, and Band Adaptability |
| has_fulltext | False |
| is_retracted | False |
| updated_date | 2025-11-09T23:09:16.995542 |
| primary_topic | |
| cited_by_count | 0 |
| locations_count | 2 |
| best_oa_location.id | pmh:oai:arXiv.org:2511.04474 |
| best_oa_location.is_oa | True |
| best_oa_location.source.id | https://openalex.org/S4306400194 |
| best_oa_location.source.issn | |
| best_oa_location.source.type | repository |
| best_oa_location.source.is_oa | True |
| best_oa_location.source.issn_l | |
| best_oa_location.source.is_core | False |
| best_oa_location.source.is_in_doaj | False |
| best_oa_location.source.display_name | arXiv (Cornell University) |
| best_oa_location.source.host_organization | https://openalex.org/I205783295 |
| best_oa_location.source.host_organization_name | Cornell University |
| best_oa_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| best_oa_location.license | cc-by-nc-nd |
| best_oa_location.pdf_url | https://arxiv.org/pdf/2511.04474 |
| best_oa_location.version | submittedVersion |
| best_oa_location.raw_type | text |
| best_oa_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| best_oa_location.is_accepted | False |
| best_oa_location.is_published | False |
| best_oa_location.raw_source_name | |
| best_oa_location.landing_page_url | http://arxiv.org/abs/2511.04474 |
| primary_location.id | pmh:oai:arXiv.org:2511.04474 |
| primary_location.is_oa | True |
| primary_location.source.id | https://openalex.org/S4306400194 |
| primary_location.source.issn | |
| primary_location.source.type | repository |
| primary_location.source.is_oa | True |
| primary_location.source.issn_l | |
| primary_location.source.is_core | False |
| primary_location.source.is_in_doaj | False |
| primary_location.source.display_name | arXiv (Cornell University) |
| primary_location.source.host_organization | https://openalex.org/I205783295 |
| primary_location.source.host_organization_name | Cornell University |
| primary_location.source.host_organization_lineage | https://openalex.org/I205783295 |
| primary_location.license | cc-by-nc-nd |
| primary_location.pdf_url | https://arxiv.org/pdf/2511.04474 |
| primary_location.version | submittedVersion |
| primary_location.raw_type | text |
| primary_location.license_id | https://openalex.org/licenses/cc-by-nc-nd |
| primary_location.is_accepted | False |
| primary_location.is_published | False |
| primary_location.raw_source_name | |
| primary_location.landing_page_url | http://arxiv.org/abs/2511.04474 |
| publication_date | 2025-11-06 |
| publication_year | 2025 |
| referenced_works_count | 0 |
| abstract_inverted_index.a | 47, 69, 152 |
| abstract_inverted_index.To | 41 |
| abstract_inverted_index.as | 131, 151 |
| abstract_inverted_index.it | 76 |
| abstract_inverted_index.of | 37, 51, 71, 138 |
| abstract_inverted_index.on | 63, 95 |
| abstract_inverted_index.or | 34 |
| abstract_inverted_index.to | 4, 104 |
| abstract_inverted_index.we | 45, 73, 125 |
| abstract_inverted_index.The | 92 |
| abstract_inverted_index.and | 7, 12, 19, 54, 87, 99, 112, 119, 134, 157, 164 |
| abstract_inverted_index.for | 16, 56, 65, 143, 160 |
| abstract_inverted_index.our | 147 |
| abstract_inverted_index.the | 8, 135 |
| abstract_inverted_index.CNNs | 80 |
| abstract_inverted_index.also | 126 |
| abstract_inverted_index.cost | 133 |
| abstract_inverted_index.data | 142 |
| abstract_inverted_index.deep | 23 |
| abstract_inverted_index.more | 114, 155 |
| abstract_inverted_index.risk | 162 |
| abstract_inverted_index.show | 74 |
| abstract_inverted_index.step | 153 |
| abstract_inverted_index.such | 130 |
| abstract_inverted_index.that | 75 |
| abstract_inverted_index.when | 28 |
| abstract_inverted_index.built | 94 |
| abstract_inverted_index.cause | 1 |
| abstract_inverted_index.data. | 40 |
| abstract_inverted_index.label | 110 |
| abstract_inverted_index.often | 26 |
| abstract_inverted_index.other | 88 |
| abstract_inverted_index.study | 148 |
| abstract_inverted_index.these | 43, 123 |
| abstract_inverted_index.under | 35, 109 |
| abstract_inverted_index.GeoFMs | 89, 150 |
| abstract_inverted_index.across | 30, 116 |
| abstract_inverted_index.damage | 3 |
| abstract_inverted_index.domain | 55 |
| abstract_inverted_index.global | 96 |
| abstract_inverted_index.label, | 53 |
| abstract_inverted_index.lives, | 5 |
| abstract_inverted_index.making | 10 |
| abstract_inverted_index.model, | 93 |
| abstract_inverted_index.models | 25, 60 |
| abstract_inverted_index.proved | 102 |
| abstract_inverted_index.robust | 156 |
| abstract_inverted_index.series | 70 |
| abstract_inverted_index.severe | 2 |
| abstract_inverted_index.timely | 13 |
| abstract_inverted_index.toward | 154 |
| abstract_inverted_index.vision | 83 |
| abstract_inverted_index.(U-Net, | 81 |
| abstract_inverted_index.Through | 68 |
| abstract_inverted_index.address | 42 |
| abstract_inverted_index.applied | 29 |
| abstract_inverted_index.diverse | 117 |
| abstract_inverted_index.limited | 38, 136 |
| abstract_inverted_index.mapping | 14 |
| abstract_inverted_index.present | 46 |
| abstract_inverted_index.sensor, | 52 |
| abstract_inverted_index.AI-ready | 140 |
| abstract_inverted_index.However, | 21 |
| abstract_inverted_index.Overall, | 146 |
| abstract_inverted_index.SatMAE). | 91 |
| abstract_inverted_index.accuracy | 108 |
| abstract_inverted_index.accurate | 11 |
| abstract_inverted_index.adapting | 57 |
| abstract_inverted_index.datasets | 118 |
| abstract_inverted_index.disaster | 17 |
| abstract_inverted_index.focusing | 62 |
| abstract_inverted_index.learning | 24 |
| abstract_inverted_index.mapping. | 67 |
| abstract_inverted_index.regions, | 33 |
| abstract_inverted_index.reliably | 115 |
| abstract_inverted_index.reusable | 139 |
| abstract_inverted_index.scalable | 158 |
| abstract_inverted_index.sensors, | 32 |
| abstract_inverted_index.spectral | 105 |
| abstract_inverted_index.struggle | 27 |
| abstract_inverted_index.training | 39, 141 |
| abstract_inverted_index.(GeoFMs), | 61 |
| abstract_inverted_index.Alongside | 122 |
| abstract_inverted_index.U-Net++), | 82 |
| abstract_inverted_index.adaptable | 100 |
| abstract_inverted_index.different | 31 |
| abstract_inverted_index.essential | 15 |
| abstract_inverted_index.framework | 50 |
| abstract_inverted_index.highlight | 127 |
| abstract_inverted_index.landslide | 66, 144, 161 |
| abstract_inverted_index.positions | 149 |
| abstract_inverted_index.reduction | 163 |
| abstract_inverted_index.remaining | 128 |
| abstract_inverted_index.research. | 145 |
| abstract_inverted_index.resilient | 103 |
| abstract_inverted_index.response. | 20 |
| abstract_inverted_index.scarcity, | 111 |
| abstract_inverted_index.settings. | 121 |
| abstract_inverted_index.Landslides | 0 |
| abstract_inverted_index.SwinV2-B), | 86 |
| abstract_inverted_index.analytical | 49 |
| abstract_inverted_index.approaches | 159 |
| abstract_inverted_index.challenges | 129 |
| abstract_inverted_index.conditions | 36 |
| abstract_inverted_index.foundation | 59 |
| abstract_inverted_index.geographic | 120 |
| abstract_inverted_index.geospatial | 58 |
| abstract_inverted_index.maintained | 107 |
| abstract_inverted_index.strengths, | 124 |
| abstract_inverted_index.three-axis | 48 |
| abstract_inverted_index.variation, | 106 |
| abstract_inverted_index.(Segformer, | 85 |
| abstract_inverted_index.(TerraMind, | 90 |
| abstract_inverted_index.challenges, | 44 |
| abstract_inverted_index.generalized | 113 |
| abstract_inverted_index.monitoring. | 166 |
| abstract_inverted_index.outperforms | 78 |
| abstract_inverted_index.availability | 137 |
| abstract_inverted_index.consistently | 77 |
| abstract_inverted_index.conventional | 22 |
| abstract_inverted_index.environment, | 9 |
| abstract_inverted_index.experiments, | 72 |
| abstract_inverted_index.fine-tuning, | 101 |
| abstract_inverted_index.preparedness | 18 |
| abstract_inverted_index.pretraining, | 97 |
| abstract_inverted_index.transformers | 84 |
| abstract_inverted_index.computational | 132 |
| abstract_inverted_index.environmental | 165 |
| abstract_inverted_index.task-specific | 79 |
| abstract_inverted_index.Prithvi-EO-2.0 | 64 |
| abstract_inverted_index.infrastructure, | 6 |
| abstract_inverted_index.self-supervision, | 98 |
| cited_by_percentile_year | |
| countries_distinct_count | 0 |
| institutions_distinct_count | 7 |
| citation_normalized_percentile |