Busca avançada
Ano de início
Entree


Mitigation Strategies to Improve Reproducibility of Poverty Estimations From Remote Sensing Images Using Deep Learning

Texto completo
Autor(es):
Mostrar menos -
Machicao, J. ; Ben Abbes, A. ; Meneguzzi, L. ; Correa, P. L. P. ; Specht, A. ; David, R. ; Subsol, G. ; Vellenich, D. ; Devillers, R. ; Stall, S. ; Mouquet, N. ; Chaumont, M. ; Berti-Equille, L. ; Mouillot, D.
Número total de Autores: 14
Tipo de documento: Artigo Científico
Fonte: EARTH AND SPACE SCIENCE; v. 9, n. 8, p. 16-pg., 2022-08-01.
Resumo

The challenges of Reproducibility and Replicability (R & R) in computer science experiments have become a focus of attention in the last decade, as efforts to adhere to good research practices have increased. However, experiments using Deep Learning (DL) remain difficult to reproduce due to the complexity of the techniques used. Challenges such as estimating poverty indicators (e.g., wealth index levels) from remote sensing imagery, requiring the use of huge volumes of data across different geographic locations, would be impossible without the use of DL technology. To test the reproducibility of DL experiments, we report a review of the reproducibility of three DL experiments which analyze visual indicators from satellite and street imagery. For each experiment, we identify the challenges found in the data sets, methods and workflows used. As a result of this assessment we propose a checklist incorporating relevant FAIR principles to screen an experiment for its reproducibility. Based on the lessons learned from this study, we recommend a set of actions aimed to improve the reproducibility of such experiments and reduce the likelihood of wasted effort. We believe that the target audience is broad, from researchers seeking to reproduce an experiment, authors reporting an experiment, or reviewers seeking to assess the work of others. (AU)

Processo FAPESP: 18/24017-3 - Desenvolvimento de novas ferramentas para o compartilhamento e reúso de dados através de pesquisa transnacional sobre o impacto socioeconômico das áreas protegidas (PARSEC)
Beneficiário:Pedro Luiz Pizzigatti Corrêa
Modalidade de apoio: Auxílio à Pesquisa - Regular
Processo FAPESP: 20/03514-9 - Avaliação dos efeitos das áreas protegidas brasileiras nas comunidades locais com base no uso e reutilização de dados biológicos, ambientais e socioeconômicos
Beneficiário:Marina Jeaneth Machicao Justo
Modalidade de apoio: Bolsas no Brasil - Pós-Doutorado