A PyTorch implementation of the Geographically Neural Network Weighted Regression (GNNWR) and its extensions

Fast Geographically Weighted Regression (FastGWR)

A Shiny application for visualizing Geographically Weighted Regression (GWR) results in an interactive 3D environment. Ideal for educational purposes and exploring spatial data relationships. Built with R, Shiny, and plotly.

A lightweight Python tool for visualizing coefficient surfaces and uncertainty estimates from spatially varying coefficient (SVC) models. Designed for simplicity, clarity, and reproducibility, svc-viz lets users generate interpretable maps with minimal code and supports outputs from MGWR, GWR, and other SVC frameworks.

All source of R codes for the replication of our results and figures on the paper, published in the journal of Health & Place.

Compared Ordinary Least Square (OLS) and Geographically Weighted Regression (GWR) using R programming with interpretation

LH공모전 : [오산시]어린이 교통사고 위험지역 도출 최우수(1위) Repo

Volkswirtschaft.

Universal agent skill for GNNWR spatial intelligent regression — spatially varying coefficients, GTNNWR spatiotemporal models, coefficient mapping, and diagnostic analysis. Part of geoscience-skills.

MUSA 5000 homeworks.

Estimate building volumes and gross floor areas from Swiss elevation models (swissALTI3D + swissSURFACE3D) and cadastral footprints. Voxel-based pipeline with optional GWR-based floor area estimation.

No description provided.

A prototype web application for validating and managing property data.

GWR model analysing the relationship between access to greenspace and deprivation in Bradford

Data-driven EV charging site suitability model for California using DBSCAN gap detection, Multi-Criteria Evaluation, and Geographically Weighted Regression across 2,007 ZCTAs. Python · GeoPandas · mgwr · Folium.

GWR provides a local model of the variable or process you are trying to understand or predict by fitting a regression equation to every point in the DataFrame.

Assignment 2 for MUSA 5000