LAMACLIMA Experiments for Training TIMBER v0.1: Land-Use Change Climate Responses

LAMACLIMA experiments provide climate model outputs for training the TIMBER v0.1 model. The data includes local climate signals extracted from simulations of full cropland and forest expansion scenarios. Datasets were authored by Shruti Nath of ETH Zurich and include surface temperature responses from models like MPI-ESM, EC-EARTH, and CESM2.

Use Cases

• Training machine learning models to predict local temperature changes based on land-use conversion.
• Analyzing differences in surface temperature responses between major climate models like CESM2 and MPI-ESM.
• Studying the local climatic signals associated with specific land cover changes, such as forest-to-cropland conversion.
• Comparing minimum, mean, and maximum temperature responses to land-use changes within a single model framework.

Strengths

• Data is derived from established climate models including MPI-ESM, EC-EARTH, and CESM2.
• Provides separate, structured datasets for cropland and forest expansion scenarios.
• Includes absolute tree cover maps alongside maps of tree cover change.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and overall dataset size are unknown, which may limit suitability assessment.
• Last update date is unknown; freshness unverified.

Provenance

Source

ETH Zurich

Collection Method

Outputs from climate model experiments (LAMACLIMA) simulating land-use changes.