Scholarlink

Objective: This study aims to test the applicability of content related to moving average models, as taught in higher education, in the implementation of SDG 15 (Life on Land) and SDG 13 (Climate Action). Method: Monthly observations from August 2015 to July 2023 were analyzed to adjust the data sets. A descriptive analysis is provided, and models are fitted to the data. Using information criteria, the models were compared to identify the best predictive model. Main Results: In analyzing deforestation alert areas in the Brazilian Amazon, the Seasonal autoregressive integrated moving average ARIMA (1, 0, 0) (2, 2, 0) 12 model exhibited the best performance. This model was chosen for evaluating its effectiveness in forecasting future data points in the series, yielding satisfactory results. Contributions: The study underscores the importance of content taught in universities, particularly on topics related to sustainability, in training innovative citizens capable of transforming realities and enhancing quality of life. The teaching and application of forecasting models are crucial across various fields, enabling predictions about future behaviors regarding events of interest. This study gains additional relevance as it intersects with SDG 4 (Quality Education) and SDG 17 (Partnerships for the Goals), contributing to the attainment of SDG 13 (Climate Action) and SDG 15 (Life on Land) by modeling deforestation alert data in the Brazilian Amazon.

错误：搜索内容不能为空，请输入英文关键词
错误：关键词超出字数限制，请精简
高级检索

Sustainability in Universities: A Study of Time Series Models and Their Application to the Modeling of Deforestation Alert Data from the Brazilian Amazon

  • 章节

  • 发表日期：

    2025年

查看全文
  • Diego Marques Cavalcante,
  • Miguel Peña-Ramírez,
  • Adriano Mendonça Souza,
  • Lucas Veiga Ávila,
  • Marceli Schvartz

摘要

Objective: This study aims to test the applicability of content related to moving average models, as taught in higher education, in the implementation of SDG 15 (Life on Land) and SDG 13 (Climate Action). Method: Monthly observations from August 2015 to July 2023 were analyzed to adjust the data sets. A descriptive analysis is provided, and models are fitted to the data. Using information criteria, the models were compared to identify the best predictive model. Main Results: In analyzing deforestation alert areas in the Brazilian Amazon, the Seasonal autoregressive integrated moving average ARIMA (1, 0, 0) (2, 2, 0) 12 model exhibited the best performance. This model was chosen for evaluating its effectiveness in forecasting future data points in the series, yielding satisfactory results. Contributions: The study underscores the importance of content taught in universities, particularly on topics related to sustainability, in training innovative citizens capable of transforming realities and enhancing quality of life. The teaching and application of forecasting models are crucial across various fields, enabling predictions about future behaviors regarding events of interest. This study gains additional relevance as it intersects with SDG 4 (Quality Education) and SDG 17 (Partnerships for the Goals), contributing to the attainment of SDG 13 (Climate Action) and SDG 15 (Life on Land) by modeling deforestation alert data in the Brazilian Amazon.