Testing Forestry Digital Twinning Workflow Based on Mobile LiDAR Scanner and AI Platform

Niţă, M. D.

doi:10.3390/f12111576

Cited by 21 publications

(7 citation statements)

References 50 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This new method employs LiDAR (light detection furthermore, ranging) technology to generate individual models of reallife environments. Nita [36] studied the use of GeoSLAM mobile LiDAR scanners and VirtSilv AI to produce digital twins of individual trees in a plot. This method was evaluated for around 1.4 thousand trees, showing a high accuracy compared to existing methods.…”

Section: Three-dimensional Simulation Platformmentioning

confidence: 99%

SWIFT: Simulated Wildfire Images for Fast Training Dataset

Fernando,

Ghali,

Akhloufi

2024

Remote Sensing

View full text Add to dashboard Cite

Wildland fires cause economic and ecological damage with devastating consequences, including loss of life. To reduce these risks, numerous fire detection and recognition systems using deep learning techniques have been developed. However, the limited availability of annotated datasets has decelerated the development of reliable deep learning techniques for detecting and monitoring fires. For such, a novel dataset, namely, SWIFT, is presented in this paper for detecting and recognizing wildland smoke and fires. SWIFT includes a large number of synthetic images and videos of smoke and wildfire with their corresponding annotations, as well as environmental data, including temperature, humidity, wind direction, and speed. It represents various wildland fire scenarios collected from multiple viewpoints, covering forest interior views, views near active fires, ground views, and aerial views. In addition, three deep learning models, namely, BoucaNet, DC-Fire, and CT-Fire, are adopted to recognize forest fires and address their related challenges. These models are trained using the SWIFT dataset and tested using real fire images. BoucaNet performed well in recognizing wildland fires and overcoming challenging limitations, including the complexity of the background, the variation in smoke and wildfire features, and the detection of small wildland fire areas. This shows the potential of sim-to-real deep learning in wildland fires.

show abstract

Section: Three-dimensional Simulation Platformmentioning

confidence: 99%

SWIFT: Simulated Wildfire Images for Fast Training Dataset

Fernando,

Ghali,

Akhloufi

2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…(1) the risk of reversals impacting the asset value provided by an ecosystem service shared with a potential buyer (e.g., risk of wind storm hindering the forest's potential of carbon sequestration); (2) signals of the forest's health degradation for the scientific community (e.g., increasing episodes of hydraulic failure, carbon starvation, insects, and pathogens). Forest management Field measurements and metadata [53] Hydrological basin parameters Remote sensing, IoT [54] Species diversity Remote sensing [55,56] Stand structure Remote sensing, IoT [57][58][59][60][61][62] Weather IoT [63] Wildlife and herbivores IoT [64,65] Ideally, by adopting common standards for tracking and reporting, multiple implementations of FDT could build a global network like Fluxnet [49], thus, generating a distinctive globally data-driven repository for the scientific community. Furthermore, reliable data on threats affecting forest ecosystems can improve risk awareness and foster the implementation of mitigation actions [66].…”

Section: Risk Management and Early-warningsmentioning

confidence: 99%

A Proposal for a Forest Digital Twin Framework and Its Perspectives

Buonocore

Yates

Валентини

2022

Forests

View full text Add to dashboard Cite

The increasing importance of forest ecosystems for human society and planetary health is widely recognized, and the advancement of data collection technologies enables new and integrated ways for forest ecosystems monitoring. Therefore, the target of this paper is to propose a framework to design a forest digital twin (FDT) that, by integrating different state variables at both tree and forest levels, creates a virtual copy of the forest. The integration of these data sets could be used for scientific purposes, for reporting the health status of forests, and ultimately for implementing sustainable forest management practices on the basis of the use cases that a specific implementation of the framework would underpin. Achieving such outcomes requires the twinning of single trees as a core element of the FDT by recording the physical and biotic state variables of the tree and of the near environment via real–virtual digital sockets. Following a nested approach, the twinned trees and the related physical and physiological processes are then part of a broader twinning of the entire forest realized by capturing data at forest scale from sources such as remote sensing technologies and flux towers. Ultimately, to unlock the economic value of forest ecosystem services, the FDT should implement a distributed ledger-based on blockchain and smart contracts to ensure the highest transparency, reliability, and thoroughness of the data and the related transactions and to sharpen forest risk management with the final goal to improve the capital flow towards sustainable practices of forest management.

show abstract

“…Some of the most relevant studies regarding vegetation properties address the estimation of biomass (Walter et al, 2019;Wang et al, 2021), phenotyping (Tefera et al, 2022) as well as coarse-grained and leaf-related parameters (Rosell et al, 2009). Furthermore, the reconstruction of trees represents a baseline for predicting and modeling the state of an environment, thus providing a background for precision agriculture, soil, forestry (Nită, 2021) and urban management (Gobeawan et al, 2021).…”

Section: Related Workmentioning

confidence: 99%

Reconstruction of tree branching structures from UAV-LiDAR data

Cárdenas

López²,

Ogáyar³

et al. 2022

Front. Environ. Sci.

View full text Add to dashboard Cite

The reconstruction of tree branching structures is a longstanding problem in Computer Graphics which has been studied over several data sources, from photogrammetry point clouds to Terrestrial and Aerial Laser Imaging Detection and Ranging technology. However, most data sources present acquisition errors that make the reconstruction more challenging. Among them, the main challenge is the partial or complete occlusion of branch segments, thus leading to disconnected components whether the reconstruction is resolved using graph-based approaches. In this work, we propose a hybrid method based on radius-based search and Minimum Spanning Tree for the tree branching reconstruction by handling occlusion and disconnected branches. Furthermore, we simplify previous work evaluating the similarity between ground-truth and reconstructed skeletons. Using this approach, our method is proved to be more effective than the baseline methods, regarding reconstruction results and response time. Our method yields better results on the complete explored radii interval, though the improvement is especially significant on the Ground Sampling Distance In terms of latency, an outstanding performance is achieved in comparison with the baseline method.

show abstract

Testing Forestry Digital Twinning Workflow Based on Mobile LiDAR Scanner and AI Platform

Cited by 21 publications

References 50 publications

SWIFT: Simulated Wildfire Images for Fast Training Dataset

SWIFT: Simulated Wildfire Images for Fast Training Dataset

A Proposal for a Forest Digital Twin Framework and Its Perspectives

Reconstruction of tree branching structures from UAV-LiDAR data

Contact Info

Product

Resources

About