Geospatial Clustering for Balanced and Proximal Schools

Abstract

Public school boundaries are redrawn from time to time to ensure effective functioning of school systems. This process, also called school redistricting, is non-trivial due to (1) the presence of multiple design criteria such as capacity utilization, proximity and travel time which are hard for planners to consider simultaneously, (2) the fixed locations of schools with widely differing capacities that need to be balanced, (3) the spatial nature of the data and the need to preserve contiguity in school zones, and (4) the difficulty in quantifying local factors that may arise. Motivated by these challenges and the intricacy of the process, we propose a geospatial clustering algorithm called GeoKmeans for assisting planners in designing school boundaries such that students are assigned to proximal schools while ensuring effective utilization of school capacities. The algorithm operates on polygonal geometries and connects them into geographically contiguous school boundaries while balancing problem-specific constraints. We evaluate our approach on real-world data of two rapidly growing school districts in the US. Results indicate the efficacy of our approach in designing boundaries. Additionally, a case study is included to demonstrate the potential of GeoKmeans to assist planners in drawing boundaries.

“This is not going to be a quick fix”: a grounded theory study of superintendents leading school integration through redistricting

“…Redistricting plans may also address factors besides demographics, such as school capacity, walkability and neighborhood cohesion (Mendez and Quark, 2022). With multiple factors involved, contemporary redistricting initiatives typically rely on geospatial technologies and algorithms to draw maps that can be assessed using “multiple design criteria” (Biswas et al. , 2020, p. 13,415).…”

Memetic algorithms for Spatial Partitioning problems

“…For instance, in school districting, the capacity of the schools and the student population corresponding to the graph nodes can vary considerably. Also, compactness is preferred to distance-based measures due to arbitrary shapes of spatial units forming a school district [11].…”

Incorporating domain knowledge into Memetic Algorithms for solving Spatial Optimization problems

“…This has led to an increased adoption of metaheuristics for solving mid-to large-sized combinatorial optimization problems [2]. In this work, we devise a population-based metaheuristic for solving SOPs inspired by the emerging eld of Swarm Intelligence 1 . These methods instantiate search moves the closely mimic the complex social behavior of animals such as ant colonies, beehives, bird ocks, and so on, which may lead to an improved exploration of the decision or search space [5].…”

“…The linear search moves of the original ABC algorithm are modi ed to perform spatially-aware search with provision for solution repair. The resulting hybrid metaheuristics, commonly known as memetic algorithm [29], is called Swarmbased sPAatial memeTIc ALgorithm (SPATIAL) and is tested on the problem of school boundary formation [1,35], a well-known SOP encountered in zone design. It involves the delineation of the public school attendance zones (boundaries) in a school district based on a series of factors, including operational e ciency, stability, geographic proximity, accessibility, contiguity, transportation cost, and so on.…”