YCYan Cheng

Yan Cheng

*This is an algorithmically generated author record based on publicly available information.

Current Organizations / Institutes

The organizations/institutes from the scholar's latest article


Yan Cheng has a total of 294 co-authors. Here are the top co-authors by number of shared publications:


Latest Publications

  • Open Access

    Remote sensing and deep learning for standing dead-tree detection and mapping: a review of advances, challenges, and future directions

    by Anwarul Islam Chowdhury, Mirela Beloiu, Teja Kattenborn, Clemens Mosig, Mete Ahishali, Mikko Vastaranta, Eetu Puttonen, Eija Honkavaara, Langning Huo, Md. Jamal Uddin, et al.

  • Open Access

    An update on deadtrees.earth: A community-driven infrastructure for tree mortality monitoring from local to global scales

    by Jonathan Schmid, Clemens Mosig, Janusch Vajna-Jehle, Miguel Mahecha, Yan Cheng, Henrik Hartmann, David Montero, Samuli Junttila, Stéphanie Horion, Mirela Beloiu Schwenke, et al.

    Tree mortality rates are increasing across many regions of the world, driven by interacting abiotic and biotic stressors such as global warming, climate extremes, pests, and pathogens. Despite growing evidence of widespread forest change, major data gaps persist regarding where trees are dying, at what intensity, and how mortality patterns evolve across space and time. Field-based observations remain essential but are often sparse, inconsistent, and spatially incomplete, while satellite observations provide dense temporal sampling but are commonly too coarse to directly resolve individual dead tree crowns. Integrating drone imagery with satellite Earth observation and machine learning offers a scalable pathway to monitor standing dead trees and to support attribution and forecasting of mortality dynamics.Here we present an update of deadtrees.earth, a community-driven platform for multi-scale tree mortality mapping that curates centimeter-scale RGB aerial imagery and provides end-to-end processing and publication workflows. Over the past year, the database has grown beyond 5,000 drone-based forest datasets. Our platform now enables users to generate georeferenced orthomosaics directly from raw drone imagery via an automated workflow, and to immediately obtain AI-based semantic segmentations for both standing deadwood cover and forest cover.A key new capability is persistent publishing and long-term archiving: users can now permanently publish selected datasets and obtain citable DOIs through FreiData. In parallel, the platform has expanded community feedback and crowdsourcing functionality, including structured issue flagging and web-based tools to review and refine model outputs, enabling continuous improvement of training data and model robustness.Finally, we report progress toward satellite-based monitoring at continental and global scales. Prototype products for Europe, derived from Sentinel data, now provide annual maps of forest cover and standing deadwood cover at 10-meter resolution. These products incorporate an interactive feedback system, enabling users to validate predictions against known disturbance events and contribute local expertise to improve model robustness and transferability. Together, these updates move deadtrees.earth from a database toward an integrated, community-validated infrastructure for tracking forest mortality trends, contributing to climate change impact assessments, and enhancing predictive capabilities for ecosystem resilience.

  • Top Cited Papers
    Open Access

    deadtrees.earth — An open-access and interactive database for centimeter-scale aerial imagery to uncover global tree mortality dynamics

    by Clemens Mosig, Janusch Vajna-Jehle, Miguel D. Mahecha, Yan Cheng, Henrik Hartmann, David Montero, Samuli Junttila, Stéphanie Horion, Mirela Beloiu Schwenke, Michael J. Koontz, et al.


  • Open Access

    Global, multi-scale standing deadwood segmentation in centimeter-scale aerial images

    by Jakobus Möhring, Teja Kattenborn, Miguel D. Mahecha, Yan Cheng, Mirela Beloiu Schwenke, Myriam Cloutier, Martin Denter, Julian Frey, Matthias Gassilloud, Anna Göritz, et al.


  • Open Access

    TreeAI: a global database for tree species annotations and high-resolution aerial imagery

    by Martin Mokros, Zhongyu Xia, Yan Cheng, Arthur Gessler, Teja Kattenborn, Xinlian Liang, Clemens Mosig, Stefano Puliti, Nataliia Rehush, Lars T. Waser, et al.

    Accurate and scalable tree species identification remains a critical challenge for global forest monitoring and management. Despite the increasing availability of remotely sensed data, the lack of standardized, high-quality ground truth datasets limits the potential of supervised machine learning models in capturing the tree diversity of forest ecosystems across different environmental and geographic contexts. Prior studies have highlighted the need for global-scale, high-resolution datasets to develop robust algorithms capable of capturing the diversity of forest ecosystems.Towards a benchmark dataset for tree species identification in high-resolution aerial imagery. To address this critical gap, we introduce the TreeAI database, an open-access dataset designed to support advanced research in tree species identification and forest dynamics. The database comprises 53 datasets (47 publicly available) from 32 countries, representing 61,158 annotated trees across 5,000 ha of forest ecosystems, and it is still growing.The TreeAI database provides annotations paired with high-resolution imagery (RGB and near-infrared bands at 1–10 cm spatial resolution, with an average of 3.5 cm). The database offers three key advancements. First, its global representation spans diverse ecosystems, climates, and species, enhancing its applicability across regions. Second, including centimetre-scale orthophotos ensures sufficient detail for identifying subtle differences between species. Finally, its community-driven design fosters ongoing contributions and ensures a dynamic dataset that evolves with the field's needs.Preliminary tree species identification analysis using deep learning algorithms conducted for Switzerland, with very heterogeneous forest ecosystems and challenging topography, yielded promising results. The average F1-score for nine common species was 0.72, with Larix spp., Picea abies, and Tilia spp. exceeding 0.80. The mean average precision (mAP) across all the species was 0.76. These findings underscore the potential of the TreeAI. To further harness TreeAI’s potential, a scientific competition will be launched in 2025, challenging participants to develop deep-learning algorithms that maximize tree species identification accuracy across a broad range of forest ecosystems.The impact of a global database for tree species annotations. The TreeAI database serves as a benchmark dataset for advancing artificial intelligence models, enabling automated forest inventory systems. This capability allows for the creation of high-resolution maps detailing tree species distributions, which can be used by researchers and practitioners for applications such as forest management, biodiversity monitoring, and ecosystem conservation. Moreover, the dataset complements existing National Forest Inventory (NFI) data, providing additional resources for point-based regional studies and enhancing ecological research at finer scales. Furthermore, the database promotes the refinement of AI models for practical forestry applications, fostering innovation in open science and collaborative research.Further needs and collaboration potential: i.) expanding its geographic and tree species coverage, such as tropical forests, which remain inadequately sampled in existing datasets. ii.) integrating TreeAI with Earth observation platforms, such as Planet Scope, Sentinel-2, and GEDI. iii.) exploring methods to enhance data accessibility and interoperability, ensuring that the database meets the evolving needs of its users. Feedback from the broader forestry community will be instrumental in shaping these developments, emphasising addressing challenges related to data standardization, processing efficiency, and algorithm performance.

  • Open Access

    Mapping individual tree mortality using sub-meter Earth observation data: Advances toward a large-scale global database

    by Samuli Junttila, Anis Rahman, Einari Heinaro, Antti Polvivaara, Mete Ahishali, Minna Blomqvist, Tuomas Yrttimaa, Nataliia Rehush, Markus Holopainen, Eija Honkavaara, et al.

    The increasing frequency and intensity of droughts and heat waves driven by climate change have led to a significant increase in tree mortality worldwide. However, the lack of accurate and consistent data on the location, timing, species, and structure of dead trees across vast geographical areas limits our understanding of climate-induced tree mortality. Furthermore, standing dead and dying trees are crucial indicators of forest health and biodiversity but are often overlooked in existing forest resource mapping systems.To address this, we present novel advancements in mapping individual tree mortality events using high-resolution (≤ 0.5 m) multi-temporal Earth Observation data, including both satellite and aerial imagery, combined with deep learning techniques. Our approach represents the first steps towards building an open large-scale database of individual tree mortality events across time. We have trained several U-Net-based deep learning models for detecting individual dead and dying trees from a wide array of imagery, including high-resolution aerial and satellite imagery from boreal, temperate, and Mediterranean forest biomes, enabling the creation of wall-to-wall datasets on tree mortality at national scales. We show results from the first nationwide individual tree mortality mapping, demonstrating the accuracy of sub-meter resolution satellite imagery in providing annual tree mortality data. We also discuss the challenges and limitations associated with detecting and characterizing detected dead trees across entire countries. Currently, our database already includes tree mortality data for 10 years in boreal, temperate, and Mediterranean forest biomes for several countries. We welcome scientists from around the globe to contribute to creating a database on individual tree mortality events to support a wide range of tree mortality data needs in different scientific disciplines.

  • Open Access

    deadtrees.earth: tree mortality monitoring from local to global scales with AI and remote sensing

    by Teja Kattenborn, Clemens Mosig, Janusch Vajna-Jehle, Yan Cheng, Henrik Hartmann, David Montero, Samuli Juntilla, Stéphanie Horion, Mirela Beloiu Schwenke, Miguel Mahecha

    Tree mortality rates are rising across many regions of the world. These are driven by the complex interplay of abiotic and biotic factors, including global warming, climate extremes, pests, pathogens, and other environmental stressors. Despite the urgency of understanding these dynamics, critical gaps remain in our ability to determine where trees are dying, why they are dying, and to predict future mortality hotspots. These knowledge gaps are primarily caused by missing data on tree mortality events. Ground-based observations, such as national forest inventories, are often sparse, inconsistent, and lack the spatial precision needed for comprehensive analysis. By contrast, satellite observations have a high temporal resolution, but their spatial resolution is often too coarse to identify individual trees. Earth observations combining drones and satellites, using machine learning, offer a promising avenue for mapping standing dead trees and uncovering the underlying drivers of tree mortality.Here we introduce deadtrees.earth, an initiative focusing on multi-scale remote sensing of tree mortality across scales. At its core, deadtrees.earth curates the largest archive of centimeter-scale RGB aerial imagery of forests, with over 2,000 orthoimages representing diverse forest biomes across continents and major forest types. Using extensive annotations of dead canopies, we develop computer vision models capable of automated semantic and instance segmentation of dead tree canopies in RGB orthoimages. These model variants demonstrate robustness across varying resolutions, biomes, and forest types, and can be applied to any orthoimage imagery submitted to the platform, enabling users to exploit these tools for their analysis.These local-scale predictions derived from drone and airplane imagery form the foundation for training satellite-based AI models to monitor tree mortality and forest cover on a global scale. We showcase recent advancements in spatiotemporal transformer models utilizing Sentinel-1 and Sentinel-2 data to produce global-scale, annual maps of forest cover and standing deadwood fractions at 10-meter resolution.A recent key functionality of the deadtrees.earth platform is its web-based annotation tools, which allow users to contribute additional training data or provide feedback on existing predictions. This crowdsourcing functionality promotes community engagement, facilitating continuous improvement and fostering trust in the provided aerial image-based and satellite-based models and products.Future work will also include expanding the coverage of aerial imagery, particularly in underrepresented regions such as Asia and Africa, which remains a cardinal priority to ensure the inclusivity and representativeness of the platform’s global-scale analyses. Moreover, we aim to apply the data products in a range of use-cases, ranging from attribution and forecasting of mortality to calibrating mortality in dynamic vegetation models. By bridging local and global scales, this work offers a critical tool for monitoring forest mortality trends, contributing to climate change impact assessments, and enhancing predictive capabilities for ecosystem resilience.


  • Open Access

    Mapping Fractional Tree Mortality and Tree Cover at Global Scale Using Sentinel-1 and 2

    by Clemens Mosig, Miguel Mahecha, Yan Cheng, Janusch Jehle, Samuli Junttila, Henrik Hartmann, Stéphanie Horion, David Montero, Mirela Beloiu Schwenke, Teja Kattenborn

    In the wake of extreme heat and drought events, excess tree mortality is increasing globally. While forest inventories provide valuable data for geolocating tree mortality, they are sparse and do not identify individual tree mortality. Aerial data captured by drones and airplanes provide precise centimeter-scale imagery that can be used to map individual tree mortality and fractional forest cover. The deadtrees.earth platform provides a comprehensive archive of annotated high-resolution orthoimages captured around the globe for different ecosystems and biomes. By using the imagery from deadtrees.earth, it is possible to detect and predict individual tree mortality and forest cover using high-resolution RGB orthoimagery at the regional scale. Here we present a methodology that allows generating global maps of tree mortality and fractional cover using satellite imagery from high-resolution aerial orthoimagery. The Sentinel-2 satellite fleet, equipped with the MultiSpectral Instrument (MSI), covers the entire Earth within five days at spatial resolutions ranging from 10 m to 60 m. The Sentinel-1 satellite fleet offers global temporally continuous radar coverage that penetrates clouds. Tree mortality and forest cover reference data in diverse ecosystems is obtained by using multiple segmentation models on the globally distributed high-resolution aerial orthoimagery database deadtrees.earth. Spatio-temporal signatures of Sentinel 1/2 satellites are then translated into forest properties by using novel Transformer architectures. In this study, we highlight how to map the share of standing deadwood and forest cover at 10 m resolution annually, generalizing to all ecosystems. This will enable us to map tree mortality and forest cover at a global scale at a new level of precision.

  • Open Access

    deadtrees.earth - an open, dynamic database for accessing, contributing, analyzing, and visualizing remote sensing-based tree mortality data.

    by Teja Kattenborn, Clemens Mosig, Kc Pratima, Julian Frey, Oscar Perez-Priego, Felix Schiefer, Yan Cheng, Alastair Potts, Janusch Jehle, Mirko Mälicke, et al.

    Excessive tree mortality rates prevail in many regions of the world. Understanding tree mortality dynamics remains elusive as this multifaceted phenomenon is influenced by an interplay of abiotic and biotic factors including, but not limited to, global warming, climate extremes, pests, pathogens, and other environmental stressors. Earth observation satellites, coupled with machine learning, present a promising avenue to unravel map standing dead trees and lay the foundation for explaining the underlying dynamics.However, the lack of globally comprehensive, georeferenced training data spanning various biomes and forest types has hindered the development of a unified global product detailing tree mortality patterns. Present ground-based observations, e.g., sourced from national inventories, are often sparse, lack standardization, and spatial specificity. Alternatively, aerial imagery captured via drones or airplanes in concert with computer vision methods offers a potent resource for mapping standing deadwood with high precision and efficiency on local scales. Such products can subsequently be used to train models based on satellite data to infer standing deadwood on large spatial scales.In pursuit of harnessing this potential to enhance our global comprehension of tree mortality patterns, we initiated the development of a dynamic database (https://deadtrees.earth), which enables to 1) upload and download aerial imagery with optional labels on standing deadwood, 2) automatically detect (semantic segmentation) standing dead trees in uploaded aerial imagery through a generic detection computer vision model, 3) Visualization and download of extensive spatiotemporal tree mortality products derived from extrapolating standing deadwood using Earth observation data.This presentation provides an in-depth overview of the deadtrees.earth database, outlining its motivation, current status, and future perspectives. By integrating Earth observation, machine learning, and ground-based data sources, this initiative aims to bridge the existing gaps in understanding global tree mortality dynamics, fostering a comprehensive and accessible resource for researchers and stakeholders alike.


  • Open Access

    High-resolution mapping of tree mortality in European forests

    by Yan Cheng, Stefan Oehmcke, Clemens Mosig, Beloiu Mirela, Teja Kattenborn, Christin Abel, Dimitri Gominski, Thomas Nord-Larsen, Rasmus Fensholt, Stephanie Horion

    Tree mortality has escalated worldwide in recent years due to climate warming and unprecedented drought events. However, mapping tree mortality across forest ecosystems has not yet been achieved. Aerial photos provide opportunities to reveal the spatial and spectral characteristics of canopy death at local to landscape scales. In this work, we present a deep learning model for mapping tree mortality from aerial photos in various forested ecosystems across Europe. This model builds on a baseline model trained with data on dead tree canopies from California using sub-meter resolution aerial photos and allows the use of various spatial resolutions of the input images (ranging from 10 to 60 cm). By comparing our results to ground observations and/or state-of-the-art forest disturbance and loss products, we will discuss the advantages and limitations of aerial photo-based tree mortality mapping. The proposed framework can be used for large-scale mapping of tree mortality from multi-year aerial photos. The tree mortality maps provide detailed information that can help understand the mechanisms of tree mortality under climate change. Furthermore, aerial photo-based maps can serve as training labels for mapping pixel-level deadwood fractions from satellite images, which enables seamless spatial coverage and could be an essential step towards a global map of tree mortality.