Posted in | News | Imaging

Remote Sensing Helps Monitor Bamboo Forest Damage

In an article published in Remote Sensing, researchers used Sentinel-1, Sentinel-2, and field inventory data to construct machine learning models monitoring Pantana phyllostachysae Chao (PPC) damage.

Study: Monitoring Damage Caused by Pantana phyllostachysae Chao to Moso Bamboo Forests Using Sentinel-1 and Sentinel-2 Images. Image Credit: Yarygin/Shutterstock.com

The bamboo forest type is significant from an ecological and economic standpoint and is primarily found in Africa, South America, and Asia.

With 6.41 million hectares, China has the most extensive bamboo forest area in the world, with Moso bamboo (Phyllostachys pubescens) making up 72.96% of the total. The short harvest season of Moso bamboo guarantees that farmers may profit from various bamboo products yearly. Bamboo has great potential for sequestering carbon and might significantly increase the terrestrial carbon sink.

How Pantana Phyllostachysae Chao (PPC) Damages Bamboo Forests

Bamboo's distinct growth pattern and human changes to the forest's structure often result in poor biodiversity in bamboo forests. Due to a lack of predators, bamboo forests encounter various insect disturbance events every year.

More than 630 insect species, of which PPC is the most harmful, pose a danger to bamboo forests. Its larvae, which typically appear three times a year, feed primarily on bamboo leaves. After hatching, the larvae climb the trunk to the canopy's top, where they begin to feed on the leaves. When the larval population reaches epidemic proportions, the host's leaves are rapidly devoured. The host's photosynthetic activity and nutrition transfer capacity are severely compromised, and its resistance to subsequent assaults is diminished. After many defoliation episodes, the host's physiological processes fail, ultimately causing death. The volume and substance of young bamboo in the damaged regions dramatically declines, and the host's shoot output in the following year suffers significantly.

Difficulties for PPC Damage Monitoring

Bamboo's natural environment often has complicated geographic features, which makes it difficult to carefully check for PPC damage. Most often, the data gathered are incomplete and out of date. By the time it is discovered, irreversible and substantial harm has already occurred. The bamboo canopy in the off-year morphology is similar to bamboo in the on-year that PPC has harmed. Previous research has shown that the physiological state of bamboo leaves in the off-years differs significantly from that of regular on-year bamboo leaves, which may alter the precision with which PPC damage is identified. As a result, differentiating off-year bamboo is crucial for enhancing remote sensing-based PPC damage diagnosis.

How the Research was Conducted

This study aimed to map the spread of PPC damage using a combination of Sentinel-2 optical and Sentinel-1 SAR photos. The researchers studied the capacity of SAR and visual characteristics to differentiate between PPC damage and analyzed the influence of bamboo phenology on the mapping accuracy concerning pest damage.

Research Area

The research was conducted in Shunchang county, located in the southeast of China. The primary kinds of woods found in this area include those composed of coniferous trees, broadleaf, and moso bamboo. Observations were carried out between the 28th of September and the 15th of October in 2020. Within the bamboo forest, observation sites of 15 by 15 meters were randomly selected.

Processing the Satellite's Data

The European Space Agency's (ESA) Sentinel Application Platform version 7.0 was used to do preliminary processing on the Sentinel-1 data set. The ESA's Sen2Cor plugin performed atmospheric corrections on Sentinel-2 images. 35 spectral indices and five SAR indicators, shown to have a close relationship with canopy structure, humidity, and pigment concentrations, were calculated. The XGBoost technique, one of the most typical examples of ensemble machine learning algorithms, was used while developing the PPC damage diagnosis model.

To monitor PPC damage with a resolution of 10 meters, the researchers merged the data from Sentinel-1 and Sentinel-2. It was shown that the phenology of bamboo may significantly impact the diagnosis of PPC damage.

Significant Findings of the Study

Overall (OA) Accuracies

The overall accuracy (OA) value was enhanced by 4% due to the difference between bamboo harvested during the growing season and bamboo harvested during the off-growing season. Compared to the double-time observation feature-based model, the single-time observation feature-based approach was superior regarding PPC monitoring's applicability. However, the overall accuracy of the former was at least 3% and 10% lower than those of the latter for samples taken during the on and off years, respectively.

Optical and SAR Features

The chosen optical and SAR characteristics revealed distinct reactions to PPC damage, with the optical features presenting consistent decreases or rising trends with the rise in damage severity. The SAR features, on the other hand, did not demonstrate any discernible changes in response to PPC damage. The SAR data were insufficient to differentiate the various degrees of damage severity. Furthermore, there was a noticeable gap between the SAR signals of healthy samples and those of damaged ones. The model's performance for mildly damaged and healthy samples might improve by adding SAR data to the optical characteristics.

Reference

Xuying Huang, Qi Zhang, Lu Hu, Tingting Zhu, Xin Zhou, Yiwei Zhang, Zhanghua Xu and Weimin Ju (2022) Monitoring Damage Caused by Pantana phyllostachysae Chao to Moso Bamboo Forests Using Sentinel-1 and Sentinel-2 Images. Remote Sensing. https://www.mdpi.com/2072-4292/14/19/5012

Disclaimer: The views expressed here are those of the author expressed in their private capacity and do not necessarily represent the views of AZoM.com Limited T/A AZoNetwork the owner and operator of this website. This disclaimer forms part of the Terms and conditions of use of this website.

Taha Khan

Written by

Taha Khan

Taha graduated from HITEC University Taxila with a Bachelors in Mechanical Engineering. During his studies, he worked on several research projects related to Mechanics of Materials, Machine Design, Heat and Mass Transfer, and Robotics. After graduating, Taha worked as a Research Executive for 2 years at an IT company (Immentia). He has also worked as a freelance content creator at Lancerhop. In the meantime, Taha did his NEBOSH IGC certification and expanded his career opportunities.  

Citations

Please use one of the following formats to cite this article in your essay, paper or report:

  • APA

    Khan, Taha. (2022, October 11). Remote Sensing Helps Monitor Bamboo Forest Damage. AZoOptics. Retrieved on December 05, 2024 from https://www.azooptics.com/News.aspx?newsID=28016.

  • MLA

    Khan, Taha. "Remote Sensing Helps Monitor Bamboo Forest Damage". AZoOptics. 05 December 2024. <https://www.azooptics.com/News.aspx?newsID=28016>.

  • Chicago

    Khan, Taha. "Remote Sensing Helps Monitor Bamboo Forest Damage". AZoOptics. https://www.azooptics.com/News.aspx?newsID=28016. (accessed December 05, 2024).

  • Harvard

    Khan, Taha. 2022. Remote Sensing Helps Monitor Bamboo Forest Damage. AZoOptics, viewed 05 December 2024, https://www.azooptics.com/News.aspx?newsID=28016.

Tell Us What You Think

Do you have a review, update or anything you would like to add to this news story?

Leave your feedback
Your comment type
Submit

While we only use edited and approved content for Azthena answers, it may on occasions provide incorrect responses. Please confirm any data provided with the related suppliers or authors. We do not provide medical advice, if you search for medical information you must always consult a medical professional before acting on any information provided.

Your questions, but not your email details will be shared with OpenAI and retained for 30 days in accordance with their privacy principles.

Please do not ask questions that use sensitive or confidential information.

Read the full Terms & Conditions.