联合星载高光谱影像和堆栈集成学习回归算法的红树林冠层叶绿素含量遥感反演
Estimation of mangrove canopy chlorophyll content using hyperspectral image and stacking ensemble regression algorithm
- 2022年26卷第6期 页码：1182-1205
纸质出版日期： 2022-06-07
DOI： 10.11834/jrs.20211374
扫 描 看 全 文
浏览全部资源
扫码关注微信
摘要
红树林是世界上生产力最高、价值最高的湿地生态系统之一。冠层叶绿素含量CCC（Canopy Chlorophyll Content）作为红树林重要的生物物理参量，是估算其生产力和评价其健康状况的重要指标。本文利用珠海一号高光谱卫星（OHS）影像与Sentinel-2A多光谱数据计算传统植被指数与组合植被指数并构建了高维数据集，综合利用正态分布检验、最大相关系数法与变量重要性评价进行数据降维和变量优选；分别基于单一线性回归算法、机器学习回归算法和堆栈集成学习回归算法构建了红树林CCC遥感反演模型，探明北部湾红树林CCC的最佳遥感反演模型，验证OHS高光谱影像与Sentinel-2A数据反演红树林CCC的精度差异，评估SNAP-SL2P算法反演红树林CCC的适用性。研究结果表明：（1）通过数据降维和变量选择处理，从高维度OHS数据集选取了8个特征变量，其中RSI
（12，17）
、DSI
（12，18）
和NDSI
（6，12）
组合植被指数对红树林CCC反演精度的贡献率较高；（2）联合OHS数据和最优堆栈GBRT集成学习回归模型（Score=0.999，RMSE=0.963 μg/cm
2
）的训练精度优于最优RF机器学习回归模型（RMSE降低了7.531 μg/cm
2
），明显优于最优Lasso线性回归模型（RMSE降低了19.383 μg/cm
2
）；（3）在最优堆栈集成学习回归模型下，OHS数据反演红树林CCC的精度（
R
2
=0.761，RMSE=16.738 μg/cm
2
）高于Sentinel-2A影像（
R
2
=0.615，RMSE=20.701 μg/cm
2
）；（4）联合OHS和Sentinel-2A数据的最优堆栈集成学习回归模型反演红树林CCC的精度都明显优于SNAP-SL2P算法（
R
2
=0.356，RMSE=49.419 μg/cm
2
）。研究结果论证了正态分布检验、最大相关系数法和基于XGBoost的特征选择方法有效降低了高维数据集的维度，并得到了最优特征变量；OHS数据的最优堆栈GBRT集成学习回归模型训练精度最高，是估算红树林CCC的最优反演模型；OHS和Sentinel-2A数据都能有效反演红树林CCC（
R
2
均大于0.61），而OHS数据的估算精度更高（
R
2
大于0.75）；SNAP-SL2P算法不能有效反演红树林CCC（
R
2
小于0.4），且对红树林CCC数值存在系统性低估。
Abstract
Mangroves are one of the most productive and valuable wetland ecosystems in the world. Canopy Chlorophyll Content (CCC)
as an important biophysical parameter
is an important indicator to evaluate mangroves’ productivity and health status.
This study calculated traditional vegetation index
combined vegetation index using Zhuhai-1 Hyperspectral Satellite (OHS) and Sentinel-2A multispectral images
and produced high-dimensional datasets. Dimension reduction and variable selection were carried out by combining normal distribution test
correlation analysis
and importance evaluation of feature variables. The optimal inversion model of mangrove CCC in the Beibu Gulf was built using single linear regression
machine learning regression
and stacking ensemble learning regression algorithm. This study demonstrated the inversing accuracy difference between OHS image and Sentinel-2A data
and evaluated the applicability of SNAP-SL2P algorithm in mangrove CCC inversion.
Results showed that (1) eight optimal feature variables are selected from the high-dimensional datasets of OHS image by statistical test
maximum correlation coefficient
and variable importance evaluation. Combining vegetation indexes (RSI
(12
17)
DSI
(12
18)
and NDSI
(6
12)
) highly contributes to the inversion of mangrove CCC. (2) The training accuracy of the GBRT-based optimal stacking ensemble learning regression model using OHS data (Score=0.999
RMSE=0.963 μg/cm
2
) was higher than that of the optimal RF regression model (RMSE reduced by 7.531 μg/cm
2
)
which is better than the optimal Lasso linear regression model (RMSE reduced by 19.383 μg/cm
2
). (3) The inversion accuracy of the optimal stacking ensemble learning regression model using OHS data (
R
2
=0.761
RMSE=16.738 μg/cm
2
) is higher than that from Sentinel-2A image (
R
2
=0.615
RMSE=20.701 μg/cm
2
). (4) The optimal stacking ensemble learning regression model using OHS and Sentinel-2A data in estimating mangrove CCC outperforms the SNAP-SL2P algorithm (
R
2
=0.356
RMSE=49.419 μg/cm
2
).
The conclusion demonstrated that normal distribution test
maximum correlation coefficient method
and XGBoost-based feature selection method can effectively reduce the redundancy of high-dimensional datasets
and obtain the optimal feature variables. The optimal stack GBRT ensemble learning regression model with the OHS data has the highest training accuracy
which is the optimal inversion model for estimating CCC of the mangrove. The
R
2
of OHS and Sentinel-2A data is over 0.61
which indicated that OHS and Sentinel-2A data can effectively estimate mangrove CCC. SNAP-SL2P algorithm cannot effectively inverse mangrove CCC (
R
2
is less than 0.4) and systematically underestimates CCC value.
关键词
红树林冠层叶绿素含量珠海一号高光谱卫星堆栈集成学习回归算法特征降维遥感反演
Keywords
mangrovecanopy chlorophyll contentZhuhai-1 Hyperspectral Satellitestacking ensemble learning regression algorithmfeature dimension reductionremote sensing inversion
references
Ali A M, Darvishzadeh R, Skidmore A, Heurich M, Paganini M, Heiden U and Mücher S. 2020. Evaluating prediction models for mapping canopy chlorophyll content across biomes. Remote Sensing, 12(11): 1788 [DOI: 10.3390/rs12111788http://dx.doi.org/10.3390/rs12111788]
Cao J J, Liu K, Liu L, Zhu Y H, Li J and He Z. 2018. Identifying mangrove species using field close-range snapshot hyperspectral imaging and machine-learning techniques. Remote Sensing, 10(12): 2047 [DOI: 10.3390/rs10122047http://dx.doi.org/10.3390/rs10122047]
Chen Z L, Jia K, Xiao C C, Wei D D, Zhao X, Lan J H, Wei X Q, Yao Y J, Wang B, Sun Y and Wang L. 2020. Leaf area index estimation algorithm for GF-5 hyperspectral data based on different feature selection and machine learning methods. Remote Sensing, 12(13): 2110 [DOI: 10.3390/rs12132110http://dx.doi.org/10.3390/rs12132110]
Cheng Z Q, Zhang J S, Meng P, Li Y Q, Wang H S and Li C Y. 2015. Improvement of algorithm used for extraction hyperspectral feature bands of vegetation. Transactions of the Chinese Society of Agricultural Engineering, 31(12): 179-185
程志庆, 张劲松, 孟平, 李岩泉, 王鹤松, 李春友. 2015. 植被参数高光谱遥感反演最佳波段提取算法的改进. 农业工程学报, 31(12): 179-185 [DOI: 10.11975/j.issn.1002-6819.2015.12.024http://dx.doi.org/10.11975/j.issn.1002-6819.2015.12.024]
Christensen S W. 2003. Ensemble construction via designed output distortion//Proceedings of the 4th International Workshop on Multiple Classifier Systems. Guildford: Springer: 286-295 [DOI: 10.1007/3-540-44938-8_29http://dx.doi.org/10.1007/3-540-44938-8_29]
Dash J and Curran P J. 2004. The MERIS terrestrial chlorophyll index. International Journal of Remote Sensing, 25(23): 5403-5413 [DOI: 10.1080/0143116042000274015http://dx.doi.org/10.1080/0143116042000274015]
Daughtry C S T, Walthall C L, Kim M S, De Colstoun E B and McMurtrey III J E. 2000. Estimating corn leaf chlorophyll concentration from leaf and canopy reflectance. Remote Sensing of Environment, 74(2): 229-239. [DOI: 10.1016/s0034-4257(00)00113-9http://dx.doi.org/10.1016/s0034-4257(00)00113-9]
Dietterich T G. 2000. Ensemble methods in machine learning//Proceedings of the First International Workshop on Multiple Classifier Systems. Cagliari: Springer: 1-15 [DOI: 10.1007/3-540-45014-9_1http://dx.doi.org/10.1007/3-540-45014-9_1]
George R, Padalia H, Sinha S K and Kumar A S. 2018. Evaluation of the use of hyperspectral vegetation indices for estimating mangrove leaf area index in middle Andaman Island, India. Remote Sensing Letters, 9(11): 1099-1108 [DOI: 10.1080/2150704X.2018.1508910http://dx.doi.org/10.1080/2150704X.2018.1508910]
Ghosh S M, Behera M D, Jagadish B, Das A K and Mishra D R. 2021. A novel approach for estimation of aboveground biomass of a carbon-rich mangrove site in India. Journal of Environmental Management, 292: 112816 [DOI: 10.1016/j.jenvman.2021.112816http://dx.doi.org/10.1016/j.jenvman.2021.112816]
Gitelson A A, Viña A, Ciganda V, Rundquist D C and Arkebauer T J. 2005. Remote estimation of canopy chlorophyll content in crops. Geophysical Research Letters, 32(8): L08403 [DOI: 10.1029/2005gl022688http://dx.doi.org/10.1029/2005gl022688]
Haboudane D, Miller J R, Tremblay N, Zarco-Tejada P J and Dextrazec L. 2002. Integrated narrow-band vegetation indices for prediction of crop chlorophyll content for application to precision agriculture. Remote Sensing of Environment, 81(2/3): 416-426 [DOI: 10.1016/s0034-4257(02)00018-4http://dx.doi.org/10.1016/s0034-4257(02)00018-4]
Inoue Y, Guérif M, Baret F, Skidmore A, Gitelson A, Schlerf M, Darvishzadeh R and Olioso A. 2016. Simple and robust methods for remote sensing of canopy chlorophyll content: a comparative analysis of hyperspectral data for different types of vegetation. Plant, Cell and Environment, 39(12): 2609-2623 [DOI: 10.1111/pce.12815http://dx.doi.org/10.1111/pce.12815]
Jain A K, Duin R P W and Mao J. 2000. Statistical pattern recognition: a review. IEEE Transactions on Pattern Analysis and Machine Intelligence, 22(1): 4-37 [DOI: 10.1109/34.824819http://dx.doi.org/10.1109/34.824819]
Jiang Z Y, Huete A R, Didan K and Miura T. 2008. Development of a two-band enhanced vegetation index without a blue band. Remote Sensing of Environment, 112(10): 3833-3845 [DOI: 10.1016/j.rse.2008.06.006http://dx.doi.org/10.1016/j.rse.2008.06.006]
Kamal M, Phinn S and Johansen K. 2016. Assessment of multi-resolution image data for mangrove leaf area index mapping. Remote Sensing of Environment, 176: 242-254 [DOI: 10.1016/j.rse.2016.02.013http://dx.doi.org/10.1016/j.rse.2016.02.013]
Lee K S, Cohen W B, Kennedy R E, Maiersperger T K and Gower S T. 2004. Hyperspectral versus multispectral data for estimating leaf area index in four different biomes. Remote Sensing of Environment, 91(3/4): 508-520 [DOI: 10.1016/j.rse.2004.04.010http://dx.doi.org/10.1016/j.rse.2004.04.010]
Lin C Y and Lin C. 2019. Using ridge regression method to reduce estimation uncertainty in chlorophyll models based on worldview multispectral data//IGARSS 2019-2019 IEEE International Geoscience and Remote Sensing Symposium. Yokohama: IEEE: 1777-1780 [DOI: 10.1109/IGARSS.2019.8900593http://dx.doi.org/10.1109/IGARSS.2019.8900593]
Liu H Q and Huete A. 1995. A feedback based modification of the NDVI to minimize canopy background and atmospheric noise. IEEE Transactions on Geoscience and Remote Sensing, 33(2): 457-465 [DOI: 10.1109/tgrs.1995.8746027http://dx.doi.org/10.1109/tgrs.1995.8746027]
Liu K, Zhou Q B, Wu W B, Xia T and Tang H J. 2016. Estimating the crop leaf area index using hyperspectral remote sensing. Journal of Integrative Agriculture, 15(2): 475-491 [DOI: 10.1016/S2095-3119(15)61073-5http://dx.doi.org/10.1016/S2095-3119(15)61073-5]
Lou P Q, Fu B L, He H C, Chen J J, Wu T H, Lin X C, Liu L L, Fan D L and Deng T F. 2021. An effective method for canopy chlorophyll content estimation of marsh vegetation based on multiscale remote sensing data. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 14: 5311-5325 [DOI: 10.1109/JSTARS.2021.3081565http://dx.doi.org/10.1109/JSTARS.2021.3081565]
Pham T D, Yokoya N, Nguyen T T T, Le N N, Ha N T, Xia J S, Takeuchi W and Pham T D. 2021. Improvement of mangrove soil carbon stocks estimation in North Vietnam using sentinel-2 data and machine learning approach. GIScience and Remote Sensing, 58(1): 68-87 [DOI: 10.1080/15481603.2020.1857623http://dx.doi.org/10.1080/15481603.2020.1857623]
Qi J, Chehbouni A, Huete A R, Kerr Y H and Sorooshian S. 1994. A modified soil adjusted vegetation index. Remote Sensing of Environment, 48(2): 119-126 [DOI: 10.1016/0034-4257(94)90134-1http://dx.doi.org/10.1016/0034-4257(94)90134-1]
Rondeaux G, Steven M and Baret F. 1996. Optimization of soil-adjusted vegetation indices. Remote Sensing of Environment, 55(2): 95-107 [DOI: 10.1016/0034-4257(95)00186-7http://dx.doi.org/10.1016/0034-4257(95)00186-7]
Sylvester E V A, Bentzen P, Bradbury I R, Clément M, Pearce J, Horne J and Beiko R G. 2018. Applications of random forest feature selection for fine-scale genetic population assignment. Evolutionary Applications, 11(2): 153-165 [DOI: 10.1111/eva.12524http://dx.doi.org/10.1111/eva.12524]
Tang S F, Tian Q J, Xu K J, Xu N X and Yue J B. 2020. Age information retrieval of Larix gmelinii forest using Sentinel-2 data. Journal of Remote Sensing, 24(12): 1511-1524
唐少飞, 田庆久, 徐凯健, 徐念旭, 岳继博. 2020. Sentinel-2卫星落叶松林龄信息反演. 遥感学报, 24(12): 1511-1524 [DOI: 10.11834/jrs.20208500http://dx.doi.org/10.11834/jrs.20208500]
Tong Q X, Zhang B and Zhang L F. 2016. Current progress of hyperspectral remote sensing in China. Journal of Remote Sensing, 20(5): 689-707
童庆禧, 张兵, 张立福. 2016. 中国高光谱遥感的前沿进展. 遥感学报, 20(5): 689-707 [DOI: 10.11834/jrs.20166264http://dx.doi.org/10.11834/jrs.20166264]
Tucker C J. 1979. Red and photographic infrared linear combinations for monitoring vegetation. Remote Sensing of Environment, 8(2): 127-150 [DOI: 10.1016/0034-4257(79)90013-0http://dx.doi.org/10.1016/0034-4257(79)90013-0]
Wang B J, Chen J M, Ju W M, Qiu F, Zhang Q, Fang M H and Chen F G. 2017. Limited effects of water absorption on reducing the accuracy of leaf nitrogen estimation. Remote Sensing, 9(3): 291 [DOI: 10.3390/rs9030291http://dx.doi.org/10.3390/rs9030291]
Wang L, Jia M M, Yin D M and Tian J Y. 2019. A review of remote sensing for mangrove forests: 1956—2018. Remote Sensing of Environment, 231: 111223 [DOI: 10.1016/j.rse.2019.111223http://dx.doi.org/10.1016/j.rse.2019.111223]
Wu C Y, Wang L, Niu Z, Gao S and Wu M Q. 2010. Nondestructive estimation of canopy chlorophyll content using Hyperion and Landsat/TM images. International Journal of Remote Sensing, 31(8): 2159-2167 [DOI: 10.1080/01431161003614382http://dx.doi.org/10.1080/01431161003614382]
Zhang Y K, Luo B, Pan D Y, Song P, Lu W C, Wang C and Zhao C J. 2018. Estimation of canopy nitrogen content of soybean crops based on fractional differential algorithm. Spectroscopy and Spectral Analysis, 38(10): 3221-3230
张亚坤, 罗斌, 潘大宇, 宋鹏, 路文超, 王成, 赵春江. 2018. 基于分数阶微分算法的大豆冠层氮素含量估测研究. 光谱学与光谱分析, 38(10): 3221-3230 [DOI: 10.3964/j.issn.1000-0593(2018)10-3221-10http://dx.doi.org/10.3964/j.issn.1000-0593(2018)10-3221-10]
Zhen J N, Jiang X P, Xu Y, Miao J, Zhao D M, Wang J J, Wang J Z and Wu G F. 2021. Mapping leaf chlorophyll content of mangrove forests with Sentinel-2 images of four periods. International Journal of Applied Earth Observation and Geoinformation, 102: 102387 [DOI: 10.1016/j.jag.2021.102387http://dx.doi.org/10.1016/j.jag.2021.102387]
Zhu Y H, Liu K, Liu L, Myint S W, Wang S G, Liu H X and He Z. 2017. Exploring the potential of worldview-2 red-edge band-based vegetation indices for estimation of mangrove leaf area index with machine learning algorithms. Remote Sensing, 9(10): 1060 [DOI: 10.3390/rs9101060http://dx.doi.org/10.3390/rs9101060]
文章被引用时，请邮件提醒。
提交
相关作者
暂无数据
相关机构
桂林理工大学 测绘地理信息学院
中国科学院空天信息创新研究院
中国科学院空天信息创新研究院 国家遥感应用工程技术研究中心
生态环境部卫星环境应用中心 水生态环境遥感部
河海大学 地球科学与工程学院
选择翻译语言
- 地址：北京市海淀区北四环西路19号 《遥感学报》编辑部 邮编：100190
- 联系电话：010-58887052 Email：nrsb@aircas.ac.cn
- 技术支持由北京北大方正电子有限公司提供 京ICP备20021838号-9
京公网安备11010802024621 - 本系统建议在Chrome、 IE9+ 以上版本浏览器阅读本站内容，360浏览器请切换至极速模式
- Cookies帮助我们提供服务并提供个性化体验。使用本网站，即表示您同意我们使用Cookies
0
回到顶部