{"doi":"10.1038/s41597-024-03366-1","title":"A multimodal framework for extraction and fusion of satellite images and public health data","abstract":"In low- and middle-income countries, the substantial costs associated with traditional data collection pose an obstacle to facilitating decision-making in the field of public health. Satellite imagery offers a potential solution, but the image extraction and analysis can be costly and requires specialized expertise. We introduce SatelliteBench, a scalable framework for satellite image extraction and vector embeddings generation. We also propose a novel multimodal fusion pipeline that utilizes a series of satellite imagery and metadata. The framework was evaluated generating a dataset with a collection of 12,636 images and embeddings accompanied by comprehensive metadata, from 81 municipalities in Colombia between 2016 and 2018. The dataset was then evaluated in 3 tasks: including dengue case prediction, poverty assessment, and access to education. The performance showcases the versatility and practicality of SatelliteBench, offering a reproducible, accessible and open tool to enhance decision-making in public health.","journal":"Scientific Data","year":2024,"id":484281,"datarank":0.0,"base_score":0.0,"endowment":0.0,"self_citation_contribution":0.0,"citation_network_contribution":0.0,"self_endowment_contribution":0.0,"citer_contribution":0.0,"corpus_percentile":null,"corpus_rank":null,"citation_count":12,"citer_count":0,"citers_with_citation_signal":0,"citers_with_endowment":0,"datacite_reuse_total":0,"is_dataset":false,"is_dataset_confidence":0.949,"is_data_producer":false,"deposit_databanks":null,"is_oa":true,"file_count":0,"downloads":0,"has_version_chain":false,"published_date":"2024-01-01","fair_score":null,"fair_percentile":null,"algorithm_id":"datarank_citation_only_1hop_v6","ranking_scope":"data_only","authors":[{"id":1325953,"name":"David Restrepo","orcid":"0000-0002-3789-1957","position":1,"is_corresponding":false},{"id":1325954,"name":"Sebastián Andrés Cajas","orcid":"0000-0003-0579-6178","position":2,"is_corresponding":false},{"id":1325955,"name":"María Patricia Arbeláez","orcid":"0000-0003-2435-4658","position":3,"is_corresponding":false},{"id":4662,"name":"Leo Anthony Celi","orcid":"0000-0001-6712-6626","position":4,"is_corresponding":false},{"id":97251,"name":"Kuan-Ting Kuo","orcid":null,"position":5,"is_corresponding":false},{"id":706162,"name":"Diego M. López","orcid":"0000-0001-9425-4375","position":6,"is_corresponding":false},{"id":819427,"name":"Lama Moukheiber","orcid":null,"position":7,"is_corresponding":false},{"id":984520,"name":"Mira Moukheiber","orcid":"0000-0001-8475-6048","position":8,"is_corresponding":false},{"id":1023373,"name":"Sulaiman Moukheiber","orcid":null,"position":9,"is_corresponding":false},{"id":1324827,"name":"Juan Sebastian Osorio-Valencia","orcid":"0000-0002-2973-8290","position":10,"is_corresponding":false},{"id":719356,"name":"Saptarshi Purkayastha","orcid":"0000-0003-3625-534X","position":11,"is_corresponding":false},{"id":1325956,"name":"Atika Rahman Paddo","orcid":"0000-0001-7068-8726","position":12,"is_corresponding":false},{"id":1229194,"name":"Chenwei Wu","orcid":"0000-0001-5145-4123","position":13,"is_corresponding":false},{"id":706161,"name":"Po‐Chih Kuo","orcid":"0000-0003-4020-3147","position":14,"is_corresponding":false},{"id":728076,"name":"Dana Moukheiber","orcid":null,"position":0,"is_corresponding":true}],"reference_count":70,"raw_metadata":null,"created_at":"2026-07-19T02:07:38.055693Z","pmid":"38879585","pmcid":null,"fwci":null,"citation_percentile":null,"influential_citations":0,"oa_status":null,"license":null,"views":0,"total_file_size_bytes":0,"version_count":0,"fair_f":null,"fair_a":null,"fair_i":null,"fair_r":null,"fair_zscore":null,"fair_rationale":null,"fair_model":null,"fair_agent_version":null,"fair_fulltext_source":null,"fair_has_llm":null,"fair_computed_at":null,"clinical_trials":[],"software_tools":[],"db_accessions":[],"linked_datasets":[],"topics":[]}