Vol.: (0123456789) 1 3 Environ Monit Assess (2023) 195:1452 https://doi.org/10.1007/s10661-023-12066-z RESEARCH Machine learning for modeling forest canopy height and cover from multi‑sensor data in Northwestern Ethiopia Zerihun Chere  · Worku Zewdie · Dereje Biru Received: 23 August 2023 / Accepted: 28 October 2023 / Published online: 10 November 2023 © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2023 Sentinel-1, Sentinel-2, and topographic measure- ments to model forest canopy cover and height. The produced canopy height and cover maps had a resolu- tion of 30 m with R 2 = 0.86 and an RMSE of 3.65 m for forest canopy height and R 2 = 0.87 and an RMSE of 0.15 for canopy cover for the year 2022. These results suggest that combining multiple variables and data sources improves canopy cover and height pre- diction accuracy compared to relying on a single data source. The output of this study could be helpful in creating forest management plans that support sus- tainable utilization of the forest resources. Keywords Canopy height · Sentinel-2 · Canopy cover · Random forest · GEDI · Sentinel-1 Introduction Forests are among the most widespread ecosystems on Earth, accounting for one-third of the land surface (Bond et al., 2008), and are crucial for maintaining global ecological balance, supporting biodiversity, and allowing for the natural regeneration of forest resources (Huang et al., 2019; Zhang et al., 2022). Deforestation activities have resulted in the loss of forests for decades, reducing ecosystem services (Kacic et al., 2021). Though Ethiopia is home to a vast range of indigenous flora species (Gebremedhin et al., 2018), forest biodiversity is being harmed by a significant decline in forest resources (Hassen et al., Abstract Continuous mapping of the height and canopy cover of forests is vital for measuring forest biomass, monitoring forest degradation and restora- tion. In this regard, the contribution of Light Detec- tion and Ranging (LiDAR) sensors, which were developed to obtain detailed data on forest compo- sition across large geographical areas, is immense. Accordingly, this study aims to predict forest canopy cover and height in tropical forest areas utilizing Global Ecosystem Dynamics Investigation (GEDI) LIDAR, multisensor images, and random forest regression. To achieve this, we gathered predictor variables from the Shuttle Radar Topography Mis- sion (SRTM) digital elevation model (DEM), Senti- nel-2 multispectral datasets, and Sentinel-1 synthetic aperture radar (SAR) backscatters. The model’s accu- racy was evaluated based on a validation dataset of GEDI Level 2A and Level 2B. The random forest method was used the combination of data layers from Z. Chere (*)  Department of Geography and Environmental Studies, Dire Dawa University, P.O.Box 1362, Dire Dawa, Ethiopia e-mail: zerihunchere@gmail.com W. Zewdie  Remote Sensing Research and Development Department, Space Science and Geospatial Institute (SSGI), P.O.Box 33679, Addis Ababa, Ethiopia D. Biru  Department of Geography and Environmental Studies, Bonga University, P.O. Box 334, Bonga, Ethiopia