AI-Driven Optimization for Urban and Vertical Agriculture Planning: A Multi-Model Approach
Bibliographic record
Abstract
Urban agriculture has emerged as a critical strategy for enhancing food security, mitigating urban heat islands, and promoting community well-being in densely populated areas. However, the complexity of urban environments poses significant challenges for effective planning and implementation. This paper presents an AI-driven framework to optimize urban and vertical agriculture planning by leveraging advanced machine learning models, including Artificial Neural Networks (ANN), Spiking Neural Networks (SNN), and Large Language Models (LLM). The proposed framework integrates diverse dataset that includes as socioeconomic data, geographic information, and urban zoning regulations to provide actionable insights for decision-makers. The Spiking Neural Network model demon-strated superior predictive accuracy in identifying optimal sites for urban agriculture by effectively handling complex patterns and temporal dynamics in the data. Additionally, the integration of an LLM-powered chatbot into a user-friendly web application enhances interactivity and supports real-time decision-making, guiding users through the prediction process with context-specific recommendations. Experimental results validate the robustness and scalability of the framework across various urban settings, demonstrating its potential to transform urban agriculture practices by providing precise, data-driven recommendations. The findings of this study highlight the transformative potential of AI in urban planning and agriculture, offering a novel approach to fostering sustainable urban development and food security. Future research will focus on expanding the dataset, refining model performance, and enhancing the application's capabilities to support more complex user queries.
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 | 0.002 |
| Meta-epidemiology (narrow) | 0.001 | 0.001 |
| Meta-epidemiology (broad) | 0.001 | 0.001 |
| Bibliometrics | 0.001 | 0.001 |
| Science and technology studies | 0.000 | 0.001 |
| Scholarly communication | 0.002 | 0.001 |
| Open science | 0.002 | 0.001 |
| Research integrity | 0.001 | 0.001 |
| Insufficient payload (model declined to judge) | 0.003 | 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".