Terrestrial and Airborne Laser Scanning Dataset of Trees in the Shivalik Range, India with Field Measurements and Leaf–Wood Classifications

Abstract

Abstract Annotated datasets are essential for training and evaluating machine learning models in forest ecology. This dataset provides high-resolution, annotated LiDAR point clouds of 674 individual trees from 12 forest plots in the Shivalik Range of northern Haryana, India, representing 24 species. Data were acquired using Terrestrial Laser Scanning (TLS) and Airborne Laser Scanning (ALS), include field-measured attributes such as species identity and Diameter at Breast Height (DBH), and terrestrial and aerial RGB imagery. TLS point clouds were georeferenced and co-registered with centimetre-level accuracy, enabling precise integration with ALS data. The dataset includes segmented individual trees and wood–leaf classifications, suitable for applications such as tree morphology analysis, biomass estimation, and species classification. To support benchmarking, outputs from established classification algorithms (LeWoS, TLSeparation, CANUPO, and Random Forest) are included. As one of the first open-access LiDAR datasets from Indian tropical forests, it provides critical reference data for developing and validating forest structure models. It can also aid biomass mapping efforts in support of large-scale missions such as NASA-ISRO’s NISAR and ESA’s BIOMASS.

Plant phenotyping relevance

個体樹木のLiDAR点群・RGB画像と樹木セグメンテーションを含む公開データセットで、樹形解析や森林構造モデルの開発・検証、分類アルゴリズムのベンチマークを目的としており、植物形質取得が中心です。

Code and data availability

The paper's authors explicitly state that all code used for data processing, wood-leaf classification, feature extraction, and tree volume estimation is openly available on GitHub at https://github.com/moonis-ali/Dataset, which is an allowed URL. The paper's core LiDAR dataset is deposited on Zenodo (10.5281/zenodo.153