| Affiliation: | 1. Institute for Advanced Development Studies (INESAD), Av. Hector Ormachea, #6115, entre C. 15 y 16, Obrajes, La Paz, Bolivia;2. Department of Geography and Environment, London School of Economics and Political Science, Houghton Street, London WC2A 2AE, UK;3. University of Sussex, Sussex House, Falmer, Brighton, BN1 9RH, UK;4. Conservation International Bolivia, Calle 13 de Calacoto Nro. 8008 entre Sanchez Bustamante y Julio C. Patino, 13593 La Paz, Bolivia;5. Department of International Development, London School of Economics and Political Science, Houghton Street, London WC2A 2AE, UK |
| Abstract: | The range and quality of freely available geo-referenced datasets is increasing. We evaluate the usefulness of free datasets for deforestation prediction by comparing generalised linear models and generalised linear mixed models (GLMMs) with a variety of machine learning models (Bayesian networks, artificial neural networks and Gaussian processes) across two study regions. Freely available datasets were able to generate plausible risk maps of deforestation using all techniques for study zones in both Mexico and Madagascar. Artificial neural networks outperformed GLMMs in the Madagascan (average AUC 0.83 vs 0.80), but not the Mexican study zone (average AUC 0.81 vs 0.89). In Mexico and Madagascar, Gaussian processes (average AUC 0.89, 0.85) and structured Bayesian networks (average AUC 0.88, 0.82) performed at least as well as GLMMs (average AUC 0.89, 0.80). Bayesian networks produced more stable results across different sampling methods. Gaussian processes performed well (average AUC 0.85) with fewer predictor variables. |
