# Replication code and data for: Tracking green space along streets of world cities

# Replication code and data for: Tracking green space along streets of world citiesFalchetta, G., & Hammad, A. T. (2025). Tracking green space along streets of world cities. Environmental Research: Infrastructure and Sustainability. https://doi.org/10.1088/2634-4505/add9c4 The file "gvi_358cities_2016_2023_yearly_falchetta_hammad.csv" contains output data, reporting sampling-point level data on the yearly (2016-2023) values of the Green View Index for the 190 cities covered in the paper AND an additional number of world cities (for a total of 358 cities). The "README_gvi_358cities_2016_2023_yearly_falchetta_hammad.txt" file contains a dictionary of each column name and units. ____ To replicate the analysis, the results, and the figures of the paper: Download input data from this Zenodo repository and code from Github https://github.com/giacfalk/urban_green_space_mapping_and_tracking *Optional data extraction steps* (processed output data are already available in the Zenodo repository): Adjust your working directory Run [lines 4-11] of workflow/sourcer.R Run the Javascript scripts written by the string_generator_training.R and string_generator_prediction.R files in Google Earth Engine (https://code.earthengine.google.com) and complete the export to Drive tasks to generate the output .csv files Run workflow/sourcer.R [lines 15-46] to train the ML model and make predictions (including figures and tables replication)# 配套复现代码与数据集：《Tracking green space along streets of world cities》 Falchetta, G. 与 Hammad, A. T. (2025). 《Tracking green space along streets of world cities》发表于 *Environmental Research: Infrastructure and Sustainability*，DOI：10.1088/2634-4505/add9c4 文件"gvi_358cities_2016_2023_yearly_falchetta_hammad.csv"为输出数据集，包含采样点级别的绿地景观指数（Green View Index, GVI）年度数值数据，覆盖论文提及的190座全球城市及额外新增城市，总计358座城市，时间跨度为2016至2023年。文件"README_gvi_358cities_2016_2023_yearly_falchetta_hammad.txt"包含各列名称与单位的说明词典。 --- 若需复现论文中的分析过程、计算结果与可视化图表，请执行以下操作： 从该Zenodo仓储下载输入数据集，并从Github仓库https://github.com/giacfalk/urban_green_space_mapping_and_tracking获取复现代码。 *可选数据提取步骤*（Zenodo仓储中已提供预处理后的输出数据集）： 调整工作目录路径。 执行`workflow/sourcer.R`的第4至11行代码。 在谷歌地球引擎（Google Earth Engine, GEE，https://code.earthengine.google.com）中运行由`string_generator_training.R`与`string_generator_prediction.R`生成的JavaScript脚本，并完成导出至谷歌云端硬盘（Google Drive）的任务以生成输出CSV文件。 执行`workflow/sourcer.R`的第15至46行代码，以训练机器学习（Machine Learning, ML）模型并完成预测，同时复现论文中的图表与表格。