A Framework with Improved Spatial Optimization Algorithms to Support China’s “Multiple-plan Integration” Planning at the County Level
Bibliographic record
Abstract
The “Multiple-plan integration” planning is proposed by the Chinese government to coordinate various planning projects in managing spatial development and protecting agricultural and ecological resources. It can be treated as a multi-objective land allocation (MOLA) problem that aims to optimize the land allocation pattern to maximize land suitability for agriculture, construction, and conservation while encouraging compact land allocation. However, there is a lack of applicable methodology or frameworks to support the “Multiple-plan integration” planning at the county level. This dissertation is intended to develop and test a framework to solve this “Multiple-plan integration” problem with improved spatial optimization algorithms. The criteria for land suitability evaluation in China’s county-level “Multiple-plan integration” were first reviewed and established. Then, the performance of three classical heuristic optimization algorithms including simulated annealing (SA), genetic algorithm (GA), and particle swarm optimization (PSO) was compared in solving a simplified MOLA problem. The comparison results show that classical NSGA-II in the GA family performs the best, but its computational cost is high in maintaining compact land allocation. Next, an improved knowledge-informed NSGA-II was developed by integrating patch-based, edge growing/decreasing, neighborhood, and constraint steering rules. The improved algorithm is more effective and efficient than classical NSGA-II in encouraging compact land allocation while its capability of maximizing land suitability is not sacrificed. Finally, a Multiple-plan Integration with Spatial Optimization (MPI-SOP) framework was proposed to support China’s “Multiple-plan integration” planning at the county level. This framework is composed of five steps: mathematically formulating the spatial optimization problem, land suitability evaluation, optimization problem solving, post-processing of land allocation solutions, and applying post-processed solutions to planning. The spatial optimization problem was solved by a patch-based and knowledge-informed NSGA-II. The case study in Dongxihu District of Wuhan City shows that the framework is feasible and effective in supporting the “Multiple-plan integration” decision making. This dissertation has made two major contributions. Practically, it has proposed and tested a framework to support China’s “Multiple-plan integration” planning with spatial optimization at the county level; methodologically, knowledge-informed heuristic optimization algorithms have been developed to solve the MOLA problem more effectively and efficiently.
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 | 0.001 | 0.001 |
| Meta-epidemiology (narrow) | 0.001 | 0.000 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.001 | 0.001 |
| Scholarly communication | 0.001 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.002 | 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 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".