Exploring machine learning techniques to predict deforestation to enhance the decision‐making of road construction projects. (24th August 2021)

• Record Type: Journal Article
• Authors: Larrea‐Gallegos, Gustavo; Vázquez‐Rowe, Ian
• Other Names: Majeau‐Bettez Guillaume guestEditor.; Frayret Jean‐Marc guestEditor.; Ramaswami Anu guestEditor.; Li Yang guestEditor.; Heeren Niko guestEditor.
• Is Part Of: Journal of industrial ecology. Volume 26:Number 1(2022)
• Page Start: 225
• Page End: 239
• Publication Date: 2021-08-24
• Subjects: Amazon rainforest -- climate change -- industrial ecology -- life cycle assessment -- Peru -- random forest; Industrial ecology -- Periodicals; Product life cycle -- Environmental aspects -- Periodicals; Industrial management -- Environmental aspects -- Periodicals; Écologie industrielle -- Périodiques; 658.56
• DOI: 10.1111/jiec.13185
• Languages: English
• ISSNs: 1088-1980

Abstract

Abstract: Land use changes (LUCs), which are defined as the modification in the use of land due to anthropogenic activities, are important sources of GHG emissions. In this context, understanding future trends of LUCs, such as deforestation, in a spatial manner is relevant. The main objective of this study is to generate a deforestation prediction model for a given period of time (i.e., 2002–2017 and 2010–2017) to estimate the potential carbon emissions associated with different anthropogenic variables in the Peruvian Amazon using machine learning (ML) algorithms. This study was motivated in the analysis of a road project previously studied using life cycle assessment (LCA). Models using neural networks and random forest algorithms were trained and evaluated in a fully cloud‐based environment using Google Earth Engine. ML‐related results demonstrated that random forest is a quicker and straightforward response to model the system under study, especially considering that data do not require additional processing during the modeling and prediction stages. Predicted results suggest that expected road expansion may be related to considerable carbon emissions in the future. Calculated values are relevant especially if the mitigation efforts that Peru has complied with in the Paris Agreement are considered. The increased complexity of the framework is justified since it allows identifying the location of hotspots and may potentially complement the utility of LCA in policy support in the areas of territorial planning and tropical road expansion.