Comparison of Statistical Approaches for Modelling Land-Use Change
Bibliographic record
Abstract
Land-use change can have local-to-global environment impacts such as loss of biodiversity and climate change as well as social-economic impacts such as social inequality. Models that are built to analyze land-use change can help us understand the causes and effects of change, which can provide support and evidence to land-use planning and land-use policies to eliminate or alleviate potential negative outcomes. A variety of modelling approaches have been developed and implemented to represent land-use change, in which statistical methods are often used in the classification of land use as well as to test hypotheses about the significance of potential drivers of land-use change. The utility of statistical models is found in the ease of their implementation and application as well as their ability to provide a general representation of land-use change given a limited amount of time, resources, and data. Despite the use of many different statistical methods for modelling land-use change, comparison among more than two statistical methods is rare and an evaluation of the performance of a combination of different statistical methods with the same dataset is lacking. The presented research fills this gap in land-use modelling literature using four statistical methods—Markov chain, logistic regression, generalized additive models and survival analysis—to quantify their ability to represent land-use change. The four methods were compared across three dimensions: accuracy (overall and by land-use type), sample size, and spatial independence via conventional and spatial cross-validation. Our results show that the generalized additive model outperformed the other three models in terms of overall accuracy and was the best for modelling most land-use changes with both conventional and spatial cross-validation regardless of sample size. Logistic regression and survival analysis were more accurate for specific land-use types, and Markov chain was able to represent those changes that could not be modeled by other approaches due to sample size restrictions. Spatial cross-validation accuracies were slightly lower than the conventional cross-validation accuracies. Our results demonstrate that not only is the choice of model by land-use type more important than sample size, but also that a hybrid land-use model comprising the best statistical modelling approaches for each land-use change can outperform individual statistical approaches. While Markov chain was not competitive, it was useful in providing representation using other methods or in other cases where there is no predictor data.
Fetched live from OpenAlex and de-inverted. Abstracts are not stored in this database: the inverted indexes are 8.6 GB of the frame’s 9.3 GB of text, and the host has 13 GB free.
How this classification was reachedexpand
Full frame machine prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. The Gemma side is a direct model label for every work in the frame, read from the title-only record. The Codex side is a classifier learned from the 10,348 direct Codex labels and calibrated to design-weighted sample rates; fields without enough sample support carry no Codex call. Candidate is the union of the two sides; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels.
Distilled classifier scores by category (both heads)
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.028 | 0.073 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.003 |
| Bibliometrics | 0.006 | 0.005 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.003 | 0.003 |
| Open science | 0.003 | 0.002 |
| Research integrity | 0.001 | 0.002 |
| Insufficient payload (model declined to judge) | 0.002 | 0.001 |
Machine scores (provisional)
The two teacher heads of the student model, read on this work. A score orders the frame for review; it never asserts a category, and the validation status ships verbatim with every row.
Baseline scores from an immature model (maturity gate not passed, 7 training rounds). Scores rank; they never assert a category.
score_only:v0-immature-baseline · verbatim from the scoring run: score_only means the number may rank works, and no category label ships from itClassification
machine, unvalidatedMachine predicted; a candidate call from one source (direct Gemma or distilled Codex), not a consensus.
How this classification was reached, model by model and score by score, is at the end of the page under "How this classification was reached".