An Advanced Terrain Vegetation Signal Detection Approach for Forest Structural Parameters Estimation Using ICESat-2 Data DOI Creative Commons
Yifan Li, Xin Shen, Lin Cao

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(11), С. 1822 - 1822

Опубликована: Май 21, 2024

Accurate forest structural parameters (such as height and canopy cover) support carbon monitoring, sustainable management, the implementation of silvicultural practices. The Ice, Cloud, land Elevation Satellite-2 (ICESat-2), which is a spaceborne Light Detection Ranging (LiDAR) satellite, offers significant potential for acquiring precise extensive information on parameters. However, ICESat-2 ATL08 product significantly influenced by geographical environment characteristics, maintaining considerable enhancing accuracy estimation. Meanwhile, it does not focus providing cover data. To acquire accurate parameters, Terrain Signal Neural Network (TSNN) framework was proposed, integrating Computer Vision (CV), Ordering Points to Identify Clustering Structure (OPTICS), deep learning. It encompassed an advanced approach detecting terrain vegetation signals constructing learning models estimating using ATL03 raw First, footprints were visualized Profile Raster Images Footprints (PRIF), implementing image binarization through adaptive thresholding median filtering denoising detect terrain. Second, rough buffers created based terrain, combining with OPTICS clustering Gaussian algorithms recognize signal footprints. Finally, (convolutional neural network (CNN), ResNet50, EfficientNetB3) constructed, training standardized PRIF estimate (including cover). results indicated that TSNN achieved high in detection (coefficient determination (R2) = 0.97) recognition (F-score 0.72). EfficientNetB3 model highest estimation (R2 0.88, relative Root Mean Squared Error (rRMSE) 13.5%), while CNN 0.80, rRMSE 18.5%). Our have enhanced also proposing original CV utilizing LiDAR

Язык: Английский

Improving extraction of forest canopy height through reprocessing ICESat-2 ATLAS and GEDI data in sparsely forested plain regions DOI Creative Commons
Ruoqi Wang, Yagang Lu, Dengsheng Lu

и другие.

GIScience & Remote Sensing, Год журнала: 2024, Номер 61(1)

Опубликована: Авг. 27, 2024

Forest canopy height (FCH) is one of the most important variables for carbon stock estimation. While many studies have focused on extracting FCH from spaceborne LiDAR in regions with spatially continuous and large patch sizes forested lands, limited research has addressed challenges extraction plain sparse fragmented forest distributions. In this study, we proposed innovative processing approaches to extract ICESat-2 photons GEDI footprints Anhui Province, China. Specifically, a sectional photon denoising method data geolocation error correction data. Airborne were used validate extracted products across typical regions. The results demonstrated effectiveness methods improving accuracy. Evaluation indicated that directly ATL08 L2A had Pearson's correlation coefficients (r) 0.6 0.93, respectively. After methods, 2019 exhibited r 0.82 relative root mean square (rRMSE) 31.11% based 3,217 segments, showed 0.96 rRMSE 18.35% 4,862 footprints. Further application these years 2020, 2021, 2022 their promise addressing vegetation coverage

Язык: Английский

Процитировано

9
Error-Reduced Digital Elevation Model of the Qinghai-Tibet Plateau using ICESat-2 and Fusion Model DOI Creative Commons
Xingang Zhang, Shanchuan Guo, Bo Yuan

и другие.

Scientific Data, Год журнала: 2024, Номер 11(1)

Опубликована: Июнь 5, 2024

Abstract The Qinghai-Tibet Plateau (QTP) holds significance for investigating Earth’s surface processes. However, due to rugged terrain, forest canopy, and snow accumulation, open-access Digital Elevation Models (DEMs) exhibit considerable noise, resulting in low accuracy pronounced data inconsistency. Furthermore, the glacier regions within QTP undergo substantial changes, necessitating updates. This study employs a fusion of DEMs high-accuracy photons from Ice, Cloud, land Satellite-2 (ICESat-2). Additionally, cover canopy heights are considered, an ensemble learning model is presented harness complementary information multi-sensor elevation observations. innovative approach results creation HQTP30, most accurate representation 2021 terrain. Comparative analysis with high-resolution imagery, UAV-derived DEMs, control points, ICESat-2 highlights advantages HQTP30. Notably, non-glacier regions, HQTP30 achieved Mean Absolute Error (MAE) 0.71 m, while it reduced MAE by 4.35 m compared state-of-the-art Copernicus DEM (COPDEM), demonstrating its versatile applicability.

Язык: Английский

Процитировано

5
ALCSF: An adaptive and anti-noise filtering method for extracting ground and top of canopy from ICESat-2 LiDAR data along single tracks DOI
Bingtao Chang, Hao Xiong, Yuan Li

и другие.

ISPRS Journal of Photogrammetry and Remote Sensing, Год журнала: 2024, Номер 215, С. 80 - 98

Опубликована: Июль 5, 2024

Язык: Английский

Процитировано

5
Performance evaluation and improvement of ICESat-2 and GEDI forest canopy height retrievals in Northeast China DOI Creative Commons
Cancan Yang,

Peng Dao-li,

Nan Zhang

и другие.

GIScience & Remote Sensing, Год журнала: 2025, Номер 62(1)

Опубликована: Май 4, 2025

Язык: Английский

Процитировано

0
Integrating optimal terrain representations from public DEMs using spaceborne LiDAR DOI Creative Commons
Xingang Zhang, Shanchuan Guo, Haowei Mu

и другие.

International Journal of Digital Earth, Год журнала: 2025, Номер 18(1)

Опубликована: Май 21, 2025

Язык: Английский

Процитировано

0
Computational imaging based on single-photon detection: a survey DOI Creative Commons
Yanyun Pu, Chengyuan Zhu, Gongxin Yao

и другие.

Artificial Intelligence Review, Год журнала: 2025, Номер 58(8)

Опубликована: Май 23, 2025

Язык: Английский

Процитировано

0
Derivation and Evaluation of LAI from the ICESat-2 Data over the NEON Sites: The Impact of Segment Size and Beam Type DOI Creative Commons
Yao Wang, Hongliang Fang

Remote Sensing, Год журнала: 2024, Номер 16(16), С. 3078 - 3078

Опубликована: Авг. 21, 2024

The leaf area index (LAI) is a critical variable for forest ecosystem processes. Passive optical and active LiDAR remote sensing have been used to retrieve LAI. data good penetration provide vertical structure distribution deliver the ability estimate LAI, such as Ice, Cloud, Land Elevation Satellite-2 (ICESat-2). Segment size beam type are important ICESat-2 LAI estimation, they affect amount of signal photons returned. However, current estimation only covered limited number sites, performance with different segment sizes has not clearly compared. Moreover, LAIs derived from strong weak beams lack comparative analysis. This study evaluated over National Ecological Observatory Network (NEON) sites in North America. estimated (20, 100, 200 m) types (strong beam) were compared those airborne laser scanning (ALS) Copernicus Global Service (CGLS). results show that performs better than because more photon signals received. at m shows highest consistency ALS (R = 0.67). Weak also present potential moderate agreement 0.52). most types, except evergreen forest. satisfactory CGLS 300 product 0.67, RMSE 1.94) presents higher upper boundary. Overall, can characterize canopy structural parameters provides which may promote generated photon-counting LiDAR.

Язык: Английский

Процитировано

2
Verification of the Accuracy of Sentinel-1 for Dem Extraction Error Analysis Under Complex Terrain Conditions DOI
Shuangcheng Zhang, Jie Wang,

Zhijie Feng

и другие.

Опубликована: Янв. 1, 2024

Download This Paper Open PDF in Browser Add to My Library Share: Permalink Using these links will ensure access this page indefinitely Copy URL DOI

Язык: Английский

Процитировано

1
Verification of the accuracy of Sentinel-1 for DEM extraction error analysis under complex terrain conditions DOI Creative Commons
Shuangcheng Zhang,

Jie Wang,

Zhijie Feng

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 133, С. 104157 - 104157

Опубликована: Сен. 1, 2024

Язык: Английский

Процитировано

1
An Advanced Terrain Vegetation Signal Detection Approach for Forest Structural Parameters Estimation Using ICESat-2 Data DOI Creative Commons
Yifan Li, Xin Shen, Lin Cao

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(11), С. 1822 - 1822

Опубликована: Май 21, 2024

Accurate forest structural parameters (such as height and canopy cover) support carbon monitoring, sustainable management, the implementation of silvicultural practices. The Ice, Cloud, land Elevation Satellite-2 (ICESat-2), which is a spaceborne Light Detection Ranging (LiDAR) satellite, offers significant potential for acquiring precise extensive information on parameters. However, ICESat-2 ATL08 product significantly influenced by geographical environment characteristics, maintaining considerable enhancing accuracy estimation. Meanwhile, it does not focus providing cover data. To acquire accurate parameters, Terrain Signal Neural Network (TSNN) framework was proposed, integrating Computer Vision (CV), Ordering Points to Identify Clustering Structure (OPTICS), deep learning. It encompassed an advanced approach detecting terrain vegetation signals constructing learning models estimating using ATL03 raw First, footprints were visualized Profile Raster Images Footprints (PRIF), implementing image binarization through adaptive thresholding median filtering denoising detect terrain. Second, rough buffers created based terrain, combining with OPTICS clustering Gaussian algorithms recognize signal footprints. Finally, (convolutional neural network (CNN), ResNet50, EfficientNetB3) constructed, training standardized PRIF estimate (including cover). results indicated that TSNN achieved high in detection (coefficient determination (R2) = 0.97) recognition (F-score 0.72). EfficientNetB3 model highest estimation (R2 0.88, relative Root Mean Squared Error (rRMSE) 13.5%), while CNN 0.80, rRMSE 18.5%). Our have enhanced also proposing original CV utilizing LiDAR

Язык: Английский

Процитировано

0