A Comparison of Machine-Learning Methods to Select Socioeconomic Indicators in Cultural Landscapes

Abstract

Cultural landscapes are regarded to be complex socioecological systems that originated as a result of the interaction between humanity and nature across time. Cultural landscapes present complex-system properties, including nonlinear dynamics among their components. There is a close relationship between socioeconomy and landscape in cultural landscapes, so that changes in the socioeconomic dynamic have an effect on the structure and functionality of the landscape. Several numerical analyses have been carried out to study this relationship, with linear regression models being widely used. However, cultural landscapes comprise a considerable amount of elements and processes, whose interactions might not be properly captured by a linear model. In recent years, machine-learning techniques have increasingly been applied to the field of ecology to solve regression tasks. These techniques provide sound methods and algorithms for dealing with complex systems under uncertainty. The term ‘machine learning’ includes a wide variety of methods to learn models from data. In this paper, we study the relationship between socioeconomy and cultural landscape (in Andalusia, Spain) at two different spatial scales aiming at comparing different regression models from a predictive-accuracy point of view, including model trees and neural or Bayesian networks.

Examining Potential Environmental Consequences of Climate Change and Other Driving Forces on the Sustainability of Spanish Olive Groves under a Socio-Ecological Approach

“…Historically, traditional agricultural landscapes in Europe evolved from mono-agricultural systems to multi-rural systems (i.e., diverse agricultural uses) adapted to the structure and function of the landscape. In this way, a social and ecological co-evolution was established that gave rise to productive work landscapes, with rural cultural landscapes and land uses being adapted to local environmental conditions [49,50]. These types of multi-rural landscapes are the foundation of the multifunctional agriculture approach (MFA), based not only on the supply of agricultural products, but also the environmental and social functions, which are related to environmental protection and the preservation of the socio-economic services of rural areas [5].…”

Using Bayesian Networks to Provide Educational Implications: Mobile Learning and Ethnomathematics to Improve Sustainability in Mathematics Education

“…BNs have been widely used in decision-making domains, including but not limited to computer sciences, medical, and telecommunication applications [54][55][56]. They are now being used in the analysis of survey data in social and socio-economic disciplines [57,58].…”

A Soft Clustering Approach to Detect Socio-Ecological Landscape Boundaries Using Bayesian Networks

“…Cultural landscapes are the result of slow, long-term complex interactions between social and natural systems [1]. They are adaptive socioecological systems [2][3][4], having properties of complex systems [5]: cross-scale linkages, uncertainty, nonlinear dynamics, system memory, and heterogeneity (these landscapes are frequently a mosaic with different degrees of ecological maturity [6]). Cultural landscapes are multi-functional heterogeneous systems, where traditional agriculture, with extensive and semi-extensive land-uses, is an essential part.…”