Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning
NASA's (National Aeronautics and Space Administration) ICESat-2 with a Photon Counting LiDAR (Light Detection And Ranging) Sensor sensitively detects signal photons at high speed with an advanced detection system called the Advanced Topographic Laser Altimeter System (ATLAS). However, the senso...
| Main Authors: | , , , , , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IEEE
2024-01-01
|
| Series: | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| Subjects: | |
| Online Access: | https://ieeexplore.ieee.org/document/10168243/ |
| _version_ | 1797448891095842816 |
|---|---|
| author | Bo Zhang Li Zhang Yong Pang Peter North Min Yan Hongge Ren Linlin Ruan Zhenyu Yang Bowei Chen |
| author_facet | Bo Zhang Li Zhang Yong Pang Peter North Min Yan Hongge Ren Linlin Ruan Zhenyu Yang Bowei Chen |
| author_sort | Bo Zhang |
| collection | DOAJ |
| description | NASA's (National Aeronautics and Space Administration) ICESat-2 with a Photon Counting LiDAR (Light Detection And Ranging) Sensor sensitively detects signal photons at high speed with an advanced detection system called the Advanced Topographic Laser Altimeter System (ATLAS). However, the sensor also extracts a large amount of background photon noise coming from the atmosphere, ground, sun, or other radiation. This condition is particularly evident in forest areas. This study proposes an automatic machine learning approach to utilize data for forestry applications to improve data availability compared to NASA's official product.</p> <p>Our method uses only a very limited number (10%) of sample points for training, ensuring operational efficiency and training accuracy. We conclude that the integrated learning performance generally outperforms single models, and the mean F1 score of all tests is approximately 0.9. The mean F1 score of the Stacked Ensembles model is 0.957 ahead of the other models. The top three variables used in training models are kNNdist5, kNNdist10, and h. These three variables could explain 51.6% of the components of the models. Over the regions tested, the proposed method could improve the proportion of signals correctly identified by 6.4%, 12.2%, 2.7%, 9.3%, and 1.4% in five datasets. The model performs better in low signal-to-noise (SNR) datasets less than 7.5. The method would be largely unaffected by differences in topography, noise distribution, and SNR. The classifiers could correct misclassified labels in ATL08 products and show good stability in different conditions. |
| first_indexed | 2024-03-09T14:16:58Z |
| format | Article |
| id | doaj.art-9c4cb487e978460ab1355adf2e412f94 |
| institution | Directory Open Access Journal |
| issn | 2151-1535 |
| language | English |
| last_indexed | 2024-03-09T14:16:58Z |
| publishDate | 2024-01-01 |
| publisher | IEEE |
| record_format | Article |
| series | IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing |
| spelling | doaj.art-9c4cb487e978460ab1355adf2e412f942023-11-29T00:01:03ZengIEEEIEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing2151-15352024-01-011711310.1109/JSTARS.2023.329068010168243Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine LearningBo Zhang0https://orcid.org/0000-0002-7226-1088Li Zhang1https://orcid.org/0000-0002-5880-7507Yong Pang2https://orcid.org/0000-0002-9760-6580Peter North3https://orcid.org/0000-0001-9933-6935Min Yan4https://orcid.org/0000-0001-7234-1590Hongge Ren5Linlin Ruan6https://orcid.org/0009-0003-4602-5326Zhenyu Yang7Bowei Chen8https://orcid.org/0000-0002-6377-1094Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaInstitute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing, ChinaGlobal Environmental Modelling and Earth Observation (GEMEO), Department of Geography, Swansea University, Swansea, U.K.Key Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaSchool of Marine Technology and Geomatics, Jiangsu Ocean University, Lianyungang, ChinaKey Laboratory of Digital Earth Science, Aerospace Information Research Institute, Chinese Academy of Sciences, Beijing, ChinaNASA's (National Aeronautics and Space Administration) ICESat-2 with a Photon Counting LiDAR (Light Detection And Ranging) Sensor sensitively detects signal photons at high speed with an advanced detection system called the Advanced Topographic Laser Altimeter System (ATLAS). However, the sensor also extracts a large amount of background photon noise coming from the atmosphere, ground, sun, or other radiation. This condition is particularly evident in forest areas. This study proposes an automatic machine learning approach to utilize data for forestry applications to improve data availability compared to NASA's official product.</p> <p>Our method uses only a very limited number (10%) of sample points for training, ensuring operational efficiency and training accuracy. We conclude that the integrated learning performance generally outperforms single models, and the mean F1 score of all tests is approximately 0.9. The mean F1 score of the Stacked Ensembles model is 0.957 ahead of the other models. The top three variables used in training models are kNNdist5, kNNdist10, and h. These three variables could explain 51.6% of the components of the models. Over the regions tested, the proposed method could improve the proportion of signals correctly identified by 6.4%, 12.2%, 2.7%, 9.3%, and 1.4% in five datasets. The model performs better in low signal-to-noise (SNR) datasets less than 7.5. The method would be largely unaffected by differences in topography, noise distribution, and SNR. The classifiers could correct misclassified labels in ATL08 products and show good stability in different conditions.https://ieeexplore.ieee.org/document/10168243/Automated machine learningICESat-2/ATLASphoton point cloud filteringspace-borne light detection and ranging (LiDAR) |
| spellingShingle | Bo Zhang Li Zhang Yong Pang Peter North Min Yan Hongge Ren Linlin Ruan Zhenyu Yang Bowei Chen Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing Automated machine learning ICESat-2/ATLAS photon point cloud filtering space-borne light detection and ranging (LiDAR) |
| title | Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning |
| title_full | Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning |
| title_fullStr | Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning |
| title_full_unstemmed | Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning |
| title_short | Improved Forest Signal Detection for Space-Borne Photon-Counting LiDAR Using Automatic Machine Learning |
| title_sort | improved forest signal detection for space borne photon counting lidar using automatic machine learning |
| topic | Automated machine learning ICESat-2/ATLAS photon point cloud filtering space-borne light detection and ranging (LiDAR) |
| url | https://ieeexplore.ieee.org/document/10168243/ |
| work_keys_str_mv | AT bozhang improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT lizhang improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT yongpang improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT peternorth improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT minyan improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT honggeren improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT linlinruan improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT zhenyuyang improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning AT boweichen improvedforestsignaldetectionforspacebornephotoncountinglidarusingautomaticmachinelearning |