Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain)
Land abandonment is a global phenomenon whose environmental consequences are difficult to assess. The Murcia region is one of the most arid regions in southern Europe and also one of the most prone to land abandonment. This study researches which environmental features are more relevant to explain a...
| Main Authors: | , , , , |
|---|---|
| Format: | info:eu-repo/semantics/article |
| Language: | English |
| Published: |
2024
|
| Subjects: | |
| Online Access: | https://onlinelibrary.wiley.com/doi/full/10.1002/ldr.2447 http://hdl.handle.net/10835/15254 https://doi.org/10.1002/ldr.2447 |
| _version_ | 1789406579332743168 |
|---|---|
| author | Alonso Sarría, Francisco Martínez Hernández, Carlos Romero Díaz, Asunción Cánovas García, Fulgencio Gomariz Castillo, Francisco |
| author_facet | Alonso Sarría, Francisco Martínez Hernández, Carlos Romero Díaz, Asunción Cánovas García, Fulgencio Gomariz Castillo, Francisco |
| author_sort | Alonso Sarría, Francisco |
| collection | DSpace |
| description | Land abandonment is a global phenomenon whose environmental consequences are difficult to assess. The Murcia region is one of the most arid regions in southern Europe and also one of the most prone to land abandonment. This study researches which environmental features are more relevant to explain abandonment at the agricultural plot scale. Geomorphometric features were measured at different scales to investigate which scales could be more relevant. Two different models have been used: logistic regression, a statistical model that allows the interpretation of the involved features, and Random Forest, a machine learning model with a higher predictive power but lower interpretability. The combined use of both such models allows a set of predictors to be selected, which, when used with Random Forest, produce a map that is highly accurate for predicting abandonment and, when used with logistic regression, produce an interpretable model. The main conclusion is that climate is the most relevant factor to explain land abandonment. |
| format | info:eu-repo/semantics/article |
| id | oai:repositorio.ual.es:10835-15254 |
| institution | Universidad de Cuenca |
| language | English |
| publishDate | 2024 |
| record_format | dspace |
| spelling | oai:repositorio.ual.es:10835-152542024-01-19T09:44:56Z Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) Alonso Sarría, Francisco Martínez Hernández, Carlos Romero Díaz, Asunción Cánovas García, Fulgencio Gomariz Castillo, Francisco land abandonment feature selection data analysis random forest logistic regression Land abandonment is a global phenomenon whose environmental consequences are difficult to assess. The Murcia region is one of the most arid regions in southern Europe and also one of the most prone to land abandonment. This study researches which environmental features are more relevant to explain abandonment at the agricultural plot scale. Geomorphometric features were measured at different scales to investigate which scales could be more relevant. Two different models have been used: logistic regression, a statistical model that allows the interpretation of the involved features, and Random Forest, a machine learning model with a higher predictive power but lower interpretability. The combined use of both such models allows a set of predictors to be selected, which, when used with Random Forest, produce a map that is highly accurate for predicting abandonment and, when used with logistic regression, produce an interpretable model. The main conclusion is that climate is the most relevant factor to explain land abandonment. 2024-01-19T09:44:56Z 2024-01-19T09:44:56Z 2015-08-28 info:eu-repo/semantics/article 1099-145X https://onlinelibrary.wiley.com/doi/full/10.1002/ldr.2447 http://hdl.handle.net/10835/15254 https://doi.org/10.1002/ldr.2447 en 15233/PI/10 info:eu-repo/semantics/openAccess |
| spellingShingle | land abandonment feature selection data analysis random forest logistic regression Alonso Sarría, Francisco Martínez Hernández, Carlos Romero Díaz, Asunción Cánovas García, Fulgencio Gomariz Castillo, Francisco Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title | Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title_full | Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title_fullStr | Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title_full_unstemmed | Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title_short | Main Environmental Features Leading to Recent Land Abandonment in Murcia Region (Southeast Spain) |
| title_sort | main environmental features leading to recent land abandonment in murcia region (southeast spain) |
| topic | land abandonment feature selection data analysis random forest logistic regression |
| url | https://onlinelibrary.wiley.com/doi/full/10.1002/ldr.2447 http://hdl.handle.net/10835/15254 https://doi.org/10.1002/ldr.2447 |
| work_keys_str_mv | AT alonsosarriafrancisco mainenvironmentalfeaturesleadingtorecentlandabandonmentinmurciaregionsoutheastspain AT martinezhernandezcarlos mainenvironmentalfeaturesleadingtorecentlandabandonmentinmurciaregionsoutheastspain AT romerodiazasuncion mainenvironmentalfeaturesleadingtorecentlandabandonmentinmurciaregionsoutheastspain AT canovasgarciafulgencio mainenvironmentalfeaturesleadingtorecentlandabandonmentinmurciaregionsoutheastspain AT gomarizcastillofrancisco mainenvironmentalfeaturesleadingtorecentlandabandonmentinmurciaregionsoutheastspain |