Land Use Land Cover Change Prediction of Tansen Municipality Using Multi-Layer Perceptron-Markov Chain (MLP-MC) Model
Bibliographic record
Abstract
LULC is dynamic across all-time series, and precise modelling of LULC dynamics can contribute to more effective planning for a sustainable future. This study aimed to examine the LULC change from 2003 to 2023 and further predict the LULC dynamics of 2033 for Tansen Municipality. Random Forest algorithm in Google Earth Engine (GEE) was used for the supervised image classification for three different years, i.e., 2003, 2013 and 2023. Land Change Modeler (LCM) of TerrSet was used for model development, prediction & its validation. Based on the Cramer's V values, candidate explanatory variables demonstrating a higher association with LULC transitions occurring between 2003 and 2013 were subsequently incorporated into the predictive model's construction. The developed model was then used to predict the LULC map of 2023. After model validation, LULC map for year 2033 was predicted using MLP-MC method. Overall, from 2003 to 2023, forest area continuously decreased, losing a total of 952.38 ha, while agricultural land, barren land and built-up areas steadily increased, by gaining a total of 412.11 ha, 336.18 ha & 206.64 ha respectively. However, the trend of water was unpredictable with a slight decrease of 3.58 ha. Comparing the LULC of 2003 & prediction for 2033, it is predicted that forest area will gradually decline by a total of 25.16%. Interestingly, water area is expected to remain constant with slight increase of 1.57%. But, agricultural land, barren land and built-up areas are projected to increase by 12.53%, 42.15% and 2175% respectively with a boost by the end of 2033. This model is based on the business-as-usual scenario and appropriate interventions can be implemented to reverse undesirable LULC changes and move towards a more sustainable future. This study offers valuable insights into both current & future land use dynamics, aiding policy makers & land use planners in developing better land use management plans.
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 distilled prediction
Teacher imitationNot calibrated prevalence, not ground truth. Human validation pending. Learned from the 10,348 direct Codex labels and 10,348 direct Gemma labels. Candidate is the union of thresholded teacher heads; consensus is their intersection. These outputs are machine_predicted_unvalidated and are not human labels or direct frontier model labels.
Codex and Gemma teacher scores by category
| Category | Codex | Gemma |
|---|---|---|
| Metaresearch | 0.000 | 0.000 |
| Meta-epidemiology (narrow) | 0.000 | 0.000 |
| Meta-epidemiology (broad) | 0.000 | 0.000 |
| Bibliometrics | 0.000 | 0.000 |
| Science and technology studies | 0.000 | 0.000 |
| Scholarly communication | 0.000 | 0.001 |
| Open science | 0.000 | 0.000 |
| Research integrity | 0.000 | 0.000 |
| Insufficient payload (model declined to judge) | 0.000 | 0.000 |
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 teacher head, 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".