High-resolution land use/cover forecasts for Switzerland in the 21st century
Abstract We present forecasts of land-use/land-cover (LULC) change for Switzerland for three time-steps in the 21st century under the representative concentration pathways 4.5 and 8.5, and at 100-m spatial and 14-class thematic resolution. We modelled the spatial suitability for each LULC class with...
| Main Authors: | , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Nature Portfolio
2024-02-01
|
| Series: | Scientific Data |
| Online Access: | https://doi.org/10.1038/s41597-024-03055-z |
| _version_ | 1827328687578546176 |
|---|---|
| author | Luca Bütikofer Antoine Adde Davnah Urbach Silvia Tobias Matthias Huss Antoine Guisan Christophe Randin |
| author_facet | Luca Bütikofer Antoine Adde Davnah Urbach Silvia Tobias Matthias Huss Antoine Guisan Christophe Randin |
| author_sort | Luca Bütikofer |
| collection | DOAJ |
| description | Abstract We present forecasts of land-use/land-cover (LULC) change for Switzerland for three time-steps in the 21st century under the representative concentration pathways 4.5 and 8.5, and at 100-m spatial and 14-class thematic resolution. We modelled the spatial suitability for each LULC class with a neural network (NN) using > 200 predictors and accounting for climate and policy changes. We improved model performance by using a data augmentation algorithm that synthetically increased the number of cells of underrepresented classes, resulting in an overall quantity disagreement of 0.053 and allocation disagreement of 0.15, which indicate good prediction accuracy. These class-specific spatial suitability maps outputted by the NN were then merged in a single LULC map per time-step using the CLUE-S algorithm, accounting for LULC demand for the future and a set of LULC transition rules. As the first LULC forecast for Switzerland at a thematic resolution comparable to available LULC maps for the past, this product lends itself to applications in land-use planning, resource management, ecological and hydraulic modelling, habitat restoration and conservation. |
| first_indexed | 2024-03-07T15:21:00Z |
| format | Article |
| id | doaj.art-7ace6b82f9ac409bafd835baa56970b5 |
| institution | Directory Open Access Journal |
| issn | 2052-4463 |
| language | English |
| last_indexed | 2024-03-07T15:21:00Z |
| publishDate | 2024-02-01 |
| publisher | Nature Portfolio |
| record_format | Article |
| series | Scientific Data |
| spelling | doaj.art-7ace6b82f9ac409bafd835baa56970b52024-03-05T17:39:37ZengNature PortfolioScientific Data2052-44632024-02-0111111010.1038/s41597-024-03055-zHigh-resolution land use/cover forecasts for Switzerland in the 21st centuryLuca Bütikofer0Antoine Adde1Davnah Urbach2Silvia Tobias3Matthias Huss4Antoine Guisan5Christophe Randin6Centre alpien de phytogéographie CAP, Fondation AubertInstitute of Earth Surface Dynamics, University of Lausanne, Geopolis, Quartier MoulineGlobal Mountain Biodiversity Assessment, Institute of Plant Sciences, University of BernSwiss Federal Research Institute WSLSwiss Federal Research Institute WSLInstitute of Earth Surface Dynamics, University of Lausanne, Geopolis, Quartier MoulineCentre alpien de phytogéographie CAP, Fondation AubertAbstract We present forecasts of land-use/land-cover (LULC) change for Switzerland for three time-steps in the 21st century under the representative concentration pathways 4.5 and 8.5, and at 100-m spatial and 14-class thematic resolution. We modelled the spatial suitability for each LULC class with a neural network (NN) using > 200 predictors and accounting for climate and policy changes. We improved model performance by using a data augmentation algorithm that synthetically increased the number of cells of underrepresented classes, resulting in an overall quantity disagreement of 0.053 and allocation disagreement of 0.15, which indicate good prediction accuracy. These class-specific spatial suitability maps outputted by the NN were then merged in a single LULC map per time-step using the CLUE-S algorithm, accounting for LULC demand for the future and a set of LULC transition rules. As the first LULC forecast for Switzerland at a thematic resolution comparable to available LULC maps for the past, this product lends itself to applications in land-use planning, resource management, ecological and hydraulic modelling, habitat restoration and conservation.https://doi.org/10.1038/s41597-024-03055-z |
| spellingShingle | Luca Bütikofer Antoine Adde Davnah Urbach Silvia Tobias Matthias Huss Antoine Guisan Christophe Randin High-resolution land use/cover forecasts for Switzerland in the 21st century Scientific Data |
| title | High-resolution land use/cover forecasts for Switzerland in the 21st century |
| title_full | High-resolution land use/cover forecasts for Switzerland in the 21st century |
| title_fullStr | High-resolution land use/cover forecasts for Switzerland in the 21st century |
| title_full_unstemmed | High-resolution land use/cover forecasts for Switzerland in the 21st century |
| title_short | High-resolution land use/cover forecasts for Switzerland in the 21st century |
| title_sort | high resolution land use cover forecasts for switzerland in the 21st century |
| url | https://doi.org/10.1038/s41597-024-03055-z |
| work_keys_str_mv | AT lucabutikofer highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT antoineadde highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT davnahurbach highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT silviatobias highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT matthiashuss highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT antoineguisan highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury AT christopherandin highresolutionlandusecoverforecastsforswitzerlandinthe21stcentury |