Urban change detection: assessing biophysical drivers using machine learning and Google Earth Engine
Bibliographic record
Abstract
Urban areas are experiencing rapid transformations, driven by population growth, economic development, and policy changes. Understanding and monitoring these dynamic changes is crucial for sustainable urban planning and management. This study leverages machine learning and Google Earth Engine to investigate urban dynamics and its interactions with biophysical conditions in the Kaduna River Basin (KRB), Nigeria. This study utilized a dataset of 192 points, initially extracted from Google Earth Engine, to analyze urban transitions between 1987 and 2020, incorporating biophysical and environmental variables such as population density, precipitation, and surface temperature. The dataset was processed in R using the CARET package, with missing data imputed via K-nearest neighbors (KNN), categorical variables transformed using One-Hot Encoding, and numerical variables rescaled for consistency. A tenfold cross-validation approach was used to train and validate machine learning models, including random forest, support vector machine, KNN, and multivariate adaptive regression splines, ensuring optimal model performance. Model evaluation metrics such as overall accuracy, kappa, F1 score, and area under the curve confirmed the reliability of the models in identifying the biophysical factors influencing urban changes. The findings revealed overall accuracy of 0.80, 0.73, 0.71, and 0.72 and kappa statistics of 0.60, 0.46, 0.42, and 0.45 for random forest (RF), multivariate adaptive regression splines, support vector machine, and KNN, respectively, with RF emerging as the most accurate model (80%) for predicting urban change patterns in KRB. Land cover changes reveal rapid urban expansion (154.81%), declining water bodies (- 95.79%), and vegetation growth (174%). Machine learning models identify population density and water stress index as key urban change drivers, with climate factors like temperature and precipitation playing crucial roles. The results of this study offer valuable insights into the processes driving urban transformation and present a robust methodology for monitoring and predicting future urban development. This study aids in the creation of strategies for sustainable urban growth and the mitigation of adverse environmental impacts.
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 | 0.000 |
| 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".