Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning
Accurate information on forest distribution is an essential basis for the protection of forest resources. Recent advances in remote sensing and machine learning have contributed to the monitoring of forest-cover distribution cost-effectively, but reliable methods for rapid forest-cover mapping over...
| Main Authors: | , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
MDPI AG
2022-10-01
|
| Series: | Remote Sensing |
| Subjects: | |
| Online Access: | https://www.mdpi.com/2072-4292/14/21/5470 |
| _version_ | 1797466597211766784 |
|---|---|
| author | Yu Wang Han Liu Lingling Sang Jun Wang |
| author_facet | Yu Wang Han Liu Lingling Sang Jun Wang |
| author_sort | Yu Wang |
| collection | DOAJ |
| description | Accurate information on forest distribution is an essential basis for the protection of forest resources. Recent advances in remote sensing and machine learning have contributed to the monitoring of forest-cover distribution cost-effectively, but reliable methods for rapid forest-cover mapping over mountainous areas are still lacking. In addition, the forest landscape pattern has proven to be closely related to the functioning of forest ecosystems, yet few studies have explicitly measured the forest landscape pattern or revealed its driving forces in mountainous areas. To address these challenges, we developed a framework for forest-cover mapping with multi-source remote sensing data (Sentinel-1, Sentinel-2) and an automated ensemble learning method. We also designed a scheme for forest landscape pattern evaluation and driver attribution based on landscape metrics and random forest regression. Results in the Qilian Mountains showed that the proposed framework and scheme could accurately depict the distribution and pattern of forest cover. The overall accuracy of the obtained level-1 and level-2 forest-cover maps reached 95.49% and 78.05%, respectively. The multi-classifier comparison revealed that for forest classification, the ensemble learning method outperformed base classifiers such as LightGBM, random forests, CatBoost, XGBoost, and neural networks. Integrating multi-dimensional features, including spectral, phenological, topographic, and geographic information, helped distinguish forest cover. Compared with other land-cover products, our mapping results demonstrated high quality and rich spatial details. Furthermore, we found that forest patches in the Qilian Mountains were concentrated in the eastern regions with low-to-medium elevations and shady aspects. We also identified that climate was the critical environmental determent of the forest landscape pattern in the Qilian Mountains. Overall, the proposed framework and scheme have strong application potential for characterizing forest cover and landscape patterns. The mapping and evaluation results can further support forest resource management, ecological assessment, and regional sustainable development. |
| first_indexed | 2024-03-09T18:42:01Z |
| format | Article |
| id | doaj.art-662db019b73b4b8ab064fcce3d11bf54 |
| institution | Directory Open Access Journal |
| issn | 2072-4292 |
| language | English |
| last_indexed | 2024-03-09T18:42:01Z |
| publishDate | 2022-10-01 |
| publisher | MDPI AG |
| record_format | Article |
| series | Remote Sensing |
| spelling | doaj.art-662db019b73b4b8ab064fcce3d11bf542023-11-24T06:39:32ZengMDPI AGRemote Sensing2072-42922022-10-011421547010.3390/rs14215470Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble LearningYu Wang0Han Liu1Lingling Sang2Jun Wang3Ministry of Education Key Laboratory for Earth Surface Processes, College of Urban and Environmental Sciences, Peking University, Beijing 100871, ChinaLand Consolidation and Rehabilitation Center, Ministry of Natural Resources, Beijing 100035, ChinaLand Consolidation and Rehabilitation Center, Ministry of Natural Resources, Beijing 100035, ChinaLand Consolidation and Rehabilitation Center, Ministry of Natural Resources, Beijing 100035, ChinaAccurate information on forest distribution is an essential basis for the protection of forest resources. Recent advances in remote sensing and machine learning have contributed to the monitoring of forest-cover distribution cost-effectively, but reliable methods for rapid forest-cover mapping over mountainous areas are still lacking. In addition, the forest landscape pattern has proven to be closely related to the functioning of forest ecosystems, yet few studies have explicitly measured the forest landscape pattern or revealed its driving forces in mountainous areas. To address these challenges, we developed a framework for forest-cover mapping with multi-source remote sensing data (Sentinel-1, Sentinel-2) and an automated ensemble learning method. We also designed a scheme for forest landscape pattern evaluation and driver attribution based on landscape metrics and random forest regression. Results in the Qilian Mountains showed that the proposed framework and scheme could accurately depict the distribution and pattern of forest cover. The overall accuracy of the obtained level-1 and level-2 forest-cover maps reached 95.49% and 78.05%, respectively. The multi-classifier comparison revealed that for forest classification, the ensemble learning method outperformed base classifiers such as LightGBM, random forests, CatBoost, XGBoost, and neural networks. Integrating multi-dimensional features, including spectral, phenological, topographic, and geographic information, helped distinguish forest cover. Compared with other land-cover products, our mapping results demonstrated high quality and rich spatial details. Furthermore, we found that forest patches in the Qilian Mountains were concentrated in the eastern regions with low-to-medium elevations and shady aspects. We also identified that climate was the critical environmental determent of the forest landscape pattern in the Qilian Mountains. Overall, the proposed framework and scheme have strong application potential for characterizing forest cover and landscape patterns. The mapping and evaluation results can further support forest resource management, ecological assessment, and regional sustainable development.https://www.mdpi.com/2072-4292/14/21/5470remote sensingforest mappingautomatic ensemble learninglandscape pattern analysisnatural resource management |
| spellingShingle | Yu Wang Han Liu Lingling Sang Jun Wang Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning Remote Sensing remote sensing forest mapping automatic ensemble learning landscape pattern analysis natural resource management |
| title | Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning |
| title_full | Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning |
| title_fullStr | Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning |
| title_full_unstemmed | Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning |
| title_short | Characterizing Forest Cover and Landscape Pattern Using Multi-Source Remote Sensing Data with Ensemble Learning |
| title_sort | characterizing forest cover and landscape pattern using multi source remote sensing data with ensemble learning |
| topic | remote sensing forest mapping automatic ensemble learning landscape pattern analysis natural resource management |
| url | https://www.mdpi.com/2072-4292/14/21/5470 |
| work_keys_str_mv | AT yuwang characterizingforestcoverandlandscapepatternusingmultisourceremotesensingdatawithensemblelearning AT hanliu characterizingforestcoverandlandscapepatternusingmultisourceremotesensingdatawithensemblelearning AT linglingsang characterizingforestcoverandlandscapepatternusingmultisourceremotesensingdatawithensemblelearning AT junwang characterizingforestcoverandlandscapepatternusingmultisourceremotesensingdatawithensemblelearning |