London Urban Tree Species Classification Data

This dataset was created as part of the ongoing study on urban trees species classification in the UK. This study is a sub-project under the PhD programme titled 'Geospatial Data and AI for Enhanced Property Information Database in the UK'. The dataset includes multi-temporal spectral reflectance values of selected tree instances in the central London area. The dataset is in two parts. The first group contains spectral signatures derived from PlanetScope satellite images from 2021 to 2025, while the second group include multi-temporal spectral signatures derived from Sentinel 2A imagery from 2021 to 2025.The goal of releasing this dataset is to contribute to the remote sensing and ecological research community to advance research aimed at accurately classifying urban tree species using the multi-temporal spectral signatures approach.This dataset is released also to support the 2026 IGARSS Conference paper titled 'Towards Urban Tree Species Classification in the UK: A machine learning Instance Segmentation Approach to Multimodal Species-Classification Dataset Creation and Algorithms Development'. The International Geoscience and Remote Sensing Symposium (IGARSS) is the flagship conference of the IEEE Geoscience and Remote Sensing Society (GRSS).本数据集系为英国境内城市树木物种分类的持续研究项目所构建。本研究为题为《英国地理空间数据与人工智能赋能增强型房产信息数据库》的博士研究项目的子课题。本数据集包含伦敦中心城区选定树木样本的多时间序列光谱反射率数据。本数据集分为两部分：第一组包含2021年至2025年期间基于PlanetScope卫星影像提取的光谱特征；第二组则包含同期（2021年至2025年）基于Sentinel 2A影像提取的多时间序列光谱特征。本数据集发布的目的在于为遥感与生态研究领域提供支持，推动基于多时间序列光谱特征方法精准分类城市树木物种的相关研究进展。本次数据集发布同时用于支撑2026年国际地球科学与遥感研讨会（International Geoscience and Remote Sensing Symposium, IGARSS）的会议论文，该论文题为《面向英国城市树木物种分类：基于机器学习实例分割的多模态物种分类数据集构建与算法开发》。国际地球科学与遥感研讨会（IGARSS）是国际电气与电子工程师协会（IEEE）地球科学与遥感学会（GRSS）的旗舰学术会议。