Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Equity-Aware Geospatial AI for Forecasting Demand-Driven Hospital Locations in Germany

Piyush Pant, Marcellius William Suntoro, Ayesha Siddiqua, Muhammad Shehryaar Sharif, Daniyal Ahmed

TL;DR

The paper addresses inequitable access to hospital care in Saarland by integrating forecasting, equity measurement, and optimization into an Equity-Aware Geospatial AI (EA-GeoAI) framework. It introduces Equity and Accessibility Indices and an agentic AI planner that jointly minimizes travel time and unmet need under constraints, guided by CMA-ES-tuned weights and ARIMA-based demand forecasts. The approach is validated against baselines and ablations, showing improved equity (lower unmet need in vulnerable districts) and balanced capacity alongside reduced travel burdens. The work provides a scalable, transparent tool for policymakers to plan demand-driven hospital networks, with a reproducible pipeline and resources for broader deployment.

Abstract

This paper presents EA-GeoAI, an integrated framework for demand forecasting and equitable hospital planning in Germany through 2030. We combine district-level demographic shifts, aging population density, and infrastructure balances into a unified Equity Index. An interpretable Agentic AI optimizer then allocates beds and identifies new facility sites to minimize unmet need under budget and travel-time constraints. This approach bridges GeoAI, long-term forecasting, and equity measurement to deliver actionable recommendations for policymakers.

Equity-Aware Geospatial AI for Forecasting Demand-Driven Hospital Locations in Germany

TL;DR

The paper addresses inequitable access to hospital care in Saarland by integrating forecasting, equity measurement, and optimization into an Equity-Aware Geospatial AI (EA-GeoAI) framework. It introduces Equity and Accessibility Indices and an agentic AI planner that jointly minimizes travel time and unmet need under constraints, guided by CMA-ES-tuned weights and ARIMA-based demand forecasts. The approach is validated against baselines and ablations, showing improved equity (lower unmet need in vulnerable districts) and balanced capacity alongside reduced travel burdens. The work provides a scalable, transparent tool for policymakers to plan demand-driven hospital networks, with a reproducible pipeline and resources for broader deployment.

Abstract

This paper presents EA-GeoAI, an integrated framework for demand forecasting and equitable hospital planning in Germany through 2030. We combine district-level demographic shifts, aging population density, and infrastructure balances into a unified Equity Index. An interpretable Agentic AI optimizer then allocates beds and identifies new facility sites to minimize unmet need under budget and travel-time constraints. This approach bridges GeoAI, long-term forecasting, and equity measurement to deliver actionable recommendations for policymakers.

Paper Structure

This paper contains 6 sections, 6 figures.

Table of Contents

  1. Introduction
  2. Related Work
  3. Methodology
  4. Experiments
  5. Results
  6. Conclusion

Figures (6)

  • Figure 1: Agentic Model Pipeline
  • Figure 2: Elderly population share (age 65+) by Saarland district in 2021
  • Figure 3: Trends of hospital inpatients, population history, and per-capita demand across the years
  • Figure 4: Existing hospitals (red markers) and predicted new facilities (blue markers) under the main model. District boundaries are outlined in black.
  • Figure 5: Evaluation graphs with the baselines
  • ...and 1 more figures