Use este identificador para citar ou linkar para este item:
http://repositorio.ufla.br/jspui/handle/1/59862
Título: | Soil-environment digital information to provide solutions for solid waste disposal and coffee yield modeling |
Autores: | Menezes, Michele Duarte de Giasson, Elvio Rezende, Tiago Teruel Andrade, Renata Silva, Sergio Henrique Godinho |
Palavras-chave: | Digital soil mapping Environmental covariate Machine learning Coffee system Land suitability Mapeamento digital de solo Covariável ambiental Aprendizagem de máquina Cafeicultura Aptidão agrícola |
Data do documento: | 18-Mar-2025 |
Editor: | Universidade Federal de Lavras |
Citação: | COSTA, Luana Sousa. Soil-environment digital information to provide solutions for solid waste disposal and coffee yield modeling. 2024. 66 p. Tese (Doutorado em Ciência do Solo) - Universidade Federal de Lavras, Lavras, 2024. |
Resumo: | The first article was developed in collaboration with the Regional Consortium for Basic Sanitation (CONSANE) involving students, faculty, and municipal authorities. By developing a method to delimitate suitable areas for the disposal of construction and demolition waste, this work directly contributed to the Municipal Solid Waste Management Plan, offering a solution to the limited technical and financial resources in small municipalities, which hinder effective waste management and compliance with current regulations. By supporting integrated solid waste management (aligned with SDG 6 - Clean Water and Sanitation), the article provides a sustainable approach to managing construction and demolition waste, reducing environmental impact, and promoting responsible land use. The thematic areas of university extension covered include Environment and Health. The direct beneficiaries included municipal decision-makers and the local population of Nepomuceno municipality, in Minas Gerais state, totaling over 25,000 residents, with potential applications for neighboring municipalities. The second article presents a study carried out in collaboration with a commercial coffee farm in the Campos das Vertentes indication of origin region. It explored machine learning algorithms to predict coffee yield based on soil topography, parent material, vegetation indexes, climate data, and along with a dataset of historical yield values. This study enhances the understanding of factors influencing yield at site-specific, enabling data-driven decisions for sustainable resource management. It directly supports SDG 2 – Zero Hunger and Sustainable Agriculture by proposing methods to improve yield prediction, optimize soil inputs management, and implement precision agriculture strategies. The results impact local coffee farmers and the regional economy, with potential applications for broader agricultural sectors. Overall, this dissertation contributes to SDG 15 – Life on Land, focusing on sustainable land use and conservation practices. It exemplifies the integration of academic research, extension activities, and technological innovation to address pressing environmental and agricultural challenges. |
URI: | http://repositorio.ufla.br/jspui/handle/1/59862 |
Aparece nas coleções: | Ciência do Solo - Doutorado (Teses) |
Arquivos associados a este item:
Este item está licenciada sob uma Licença Creative Commons