随机森林算法在湿地研究中的应用
|
摘要
湿地处于陆地与水域之间的过渡地带,是具有复杂景观空间结构和变化过程的重要生态系统。遥感技术在湿地空间格局演变研究中得到了广泛应用。随机森林(Random Forests,RF)算法具有强大的运算能力,能较好地捕捉破碎信息,模拟复杂的非线性关系,是提取湿地信息的有力手段。根据国内外已有研究,总结了随机森林算法的发展历程及其在生态学应用中的改进;在"Web of Science"数据库中,查阅了随机森林算法应用于湿地的相关文献;归纳了随机森林算法在判别湿地土地覆盖类型、预测湿地植物分布和生长、预测水鸟巢址选择和迁徙中的应用;指出了已有相关研究的不足。
Wetland ecosystem, located in the transition zone of terrestrial and aquatic ecosystems, has complex spatial structure and changing process. Remote sensing technology has been widely used in the exploration of the spatial pattern evolution of the wetlands. Random Forests algorithm is a powerful method in extracting information from wetlands for its strong ability of capturing fragmentary information and simulating nonlinear relationship. Thus, in this study, literatures related to random forests algorithm were consulted in the Web of Science data base. And we reviewed the development of random forests algorithm and its improvement in the application of wetland ecology based on existing researches, especially for land cover mapping, wetland vegetation distribution and growth predicating, waterfowl nest site selection and migratory behavior predicating.Additionally, the shortages of past researches were pointed out.
Wetland ecosystem, located in the transition zone of terrestrial and aquatic ecosystems, has complex spatial structure and changing process. Remote sensing technology has been widely used in the exploration of the spatial pattern evolution of the wetlands. Random Forests algorithm is a powerful method in extracting information from wetlands for its strong ability of capturing fragmentary information and simulating nonlinear relationship. Thus, in this study, literatures related to random forests algorithm were consulted in the Web of Science data base. And we reviewed the development of random forests algorithm and its improvement in the application of wetland ecology based on existing researches, especially for land cover mapping, wetland vegetation distribution and growth predicating, waterfowl nest site selection and migratory behavior predicating.Additionally, the shortages of past researches were pointed out.
引文
[1]Kusler J A,Mitsch W J,Larson J S.Wetlands[M].New York:John Wiley&Sons,2007.
[2]贾大成,毛永新,姜奇刚,等.吉林省西部湿地形成的地质条件[J].湿地科学,2012,1010(3):327-331.
[3]贾维馨,姜琦刚,李远华,等.图们江下游湿地形成的地质条件及成因[J].湿地科学,2017,1515(3):337-342.
[4]崔桢,沈红,章光新.3个时期莫莫格国家级自然保护区景观格局和湿地水文连通性变化及其驱动因素分析[J].湿地科学,2016,1414(6):866-873.
[5]Liu H,Bu R,Liu J,et al.Predicting the wetland distributions under climate warming in the Great Xing’an Mountains,northeastern China[J].Ecological Research,2011,2626(3):605-613.
[6]Breiman L,Friedman J H,Olshen R A,et al.Classification and Regression Trees(CART)[J].Encyclopedia of Ecology,1984,40(3):582-588.
[7]Ho T K.The random subspace method for constructing decision forests[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,2020(8):832-844.
[8]Ho T K.Random Decision Forest[M].Boston,MA:Springer US,2010.
[9]Breiman L.Random forests[J].Machine Learning,2001,4545(1):5-32.
[10]Cutler A,Cutler D R,Stevens J R.Random forests[J].Machine Learning,2004,4545(1):157-176.
[11]Cutler R D,Edwards T C,Beard K H,et al.Random Forests for Classification in Ecology[J].Ecology,2007,8888(11):2783-2792.
[12]Mi C,Huettmann F,Guo Y,et al.Why choose random forest to predict rare species distribution with few samples in large undersampled areas?Three Asian crane species models provide supporting evidence[J].The Journal of Life and environmental Sciences,2017,55:e2849.
[13]Chen C,Liaw A,Breiman L.Using random forest to learn imbalanced data[J].Journalof Machine Learning Research,2004,1616:1-12.
[14]Robinson O J,Ruiz-Gutierrez V,Fink D.Correcting for bias in distribution modelling for rare species using citizen science data[J].Diversity&Distributions,2018,2424(4):460-472.
[15]Shotton J,Johnson M,Cipolla R.Semantic texton forests for image categorization and segmentation[C]//IEEE,2008 IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,AK,USA:IEEE,2008:255-262.
[16]雷震.随机森林及其在遥感影像处理中的应用[D].上海:上海交通大学,2012.
[17]Lei Z,Fang T,Li D.Land cover classification for remote sensing imagery using conditional textonforest with historical land cover map[J].IEEE Geoscience and Remote Sensing Letters,2011,88(4):720-724.
[18]Liaw A,Wiener M.Classification and regression by random forest[J].R news,2002,22(3):18-22.
[19]付柏霖.基于多源遥感的沼泽湿地水文边界界定方法研究[D].北京:中国科学院大学,2017.
[20]刘蕾,臧淑英,那晓东,等.兼容光学雷达影像及地形辅助数据的扎龙湿地遥感分类[J].地理与地理信息科学,2013,2929(1):36-40.
[21]Arnesen A S,Silva T S F,Hess L L,et al.Monitoring flood extent in the lower Amazon River floodplain using ALOS/PAL-SAR/ScanSAR images[J].Remote Sensing of Environment,2013,13030(4):51-61.
[22]Wehr A,Lohr U.Airborne laser scanning:An introduction and overview[J].Isprs Journal of Photogrammetry&Remote Sensing,1999,544(2-3):68-82.
[23]Bai J H,Ou Y H,Cui B S,et al.Changes in landscape pattern of alpine wetlands on the ZoigêPlateau in the past four decades[J].Acta Ecologica Sinica,2008,2828(5):2245-2252.
[24]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆盖分类[J].生态学报,2013,3333(23):7496-7504.
[25]Chan J C W,Paelinckx D.Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery[J].Remote Sensing of Environment,2008,11212(6):2999-3011.
[26]Gislason P O,Benediktsson J A,Sveinsson J R.Random Forests for land cover classification[J].Pattern Recognition Letters,2006,2727(4):294-300.
[27]Maxwell A E,Warner T A,Strager M P.Predicting palustrine wetland probability using random forest machine learning and digital elevation data-derived terrain variables[J].Photogrammetric Engineering&Remote Sensing,2016,8282(6):437-447.
[28]Larocque A,Leblon B,Woodward R,et al.Use of Radarsat-2and ALOS-PALSAR SAR Images for Wetland Mapping in New Brunswick[C]//IEEE,IGARSS 2014-2014 IEEE International Geoscience and Remote Sensing Symposium,Quebec City,CANADA:IEEE,2014:1226-1229.
[29]Kloiber S M,Macleod R D,Smith A J.A semi-automated,multisource data fusion update of a wetland inventory for east-central Minnesota,USA[J].Wetlands,2015,3535(2):335-348.
[30]王书玉,张羽威,于振华.基于随机森林的洪河湿地遥感影像分类研究[J].测绘与空间地理信息,2014,3737(4):83-85.
[31]刘蕾,臧淑英,那晓东,等.兼容光学雷达影像及地形辅助数据的扎龙湿地遥感分类[J].地理与地理信息科学,2013,2929(1):36-40.
[32]Tian S H.Random forest classification of wetland landcovers from multi-sensor data in the arid region of Xinjiang,China[J].Remote Sensing,2016,88(11):UNSP 954.
[33]Na X D,Zang S Y,Wu C S,et al.Mapping forested wetlands in the Great Zhan River Basin through integrating optical,radar,and topographical data classification techniques[J].Environmental Monitoring&Assessment,2015,187187(11):696.
[34]Berhane T M,Lane C R,Wu Q,et al.Comparing pixel-and object-based approaches in effectively classifying wetland-dominated landscapes[J].Remote Sensing,2017,1010(1):46.
[35]Song R,Lin H,Wang G,et al.Improving selection of spectral variables for vegetation classification of east Dongting Lake,China,using a gaofen-1 image[J].Remote Sensing,2018,1010(50):50.
[36]Van Beijma S,Comber A,Lamb A.Random forest classification of salt marsh vegetation habitats using quad-polar metric airborne SAR,elevation and optical RS data[J].Remote Sensing of Environment,2014,149149:118-129.
[37]Corcoran J M,Knight J F,Gallant A L.Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification ofwetlands in northern Minnesota[J].Remote Sensing,2013,55(7):3212-3238.
[38]Dubeau P,King D,Unbushe D.Mapping the Dabus wetlands,Ethiopia,using random forest classification of landsat,palsar and topographic data[J].Remote Sensing,2017,99(10):1056.
[39]Millard K,Richardson M.Wetland mapping with Li DAR derivatives,SAR polarimetric decompositions,and Li DAR-SAR fusion using a random forest classifier[J].Canadian Journal of Remote Sensing,2013,3939(4):290-307.
[40]Blaschke H,Hay G J.Object-oriented image analysis and scalespace:theory and methods for modeling and evaluating multiscale landscape structure[J].International Archives of Photogrammetry and Remote Sensing,2001,344(4):22-29.
[41]Brisco B,Kapfer M,Hirose T T B,et al.Evaluation of C-band polarization diversity and polarimetry for wetland mapping[J].Canadian Journal of Remote Sensing,2011,3737(1):82-92.
[42]Bolin Fu.Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data[J].Ecological Indicators,2017,733:105-117.
[43]Mahdavi S.Object-based classification of wetlands in newfoundland and labrador using multi-temporal Polsar data[J].Canadian Journal of Remote Sensing,2017,433(5):432-450.
[44]Lei Z,Fang T,Li D.Land cover classification for remote sensing imagery using Conditional Texton Forest with historical land cover map[J].IEEE Geoscience and Remote Sensing Letters,2011,88(4):720-724.
[45]Liu J,Gong J,Gong J,et al.Land-cover classification of the Yellow River Delta wetland based on multiple end-member spectral mixture analysis and a Random Forest classifier[J].International Journal of Remote Sensing,2016,377(8):1845-1867.
[46]Masoud Mahdianpari,Bahram Salehi,Fariba Mohammadimanesh,et al.Random forest wetland classification using ALOS-2 L-band,RADARSAT-2 C-band,and TerraSAR-X imagery[J].Isprs Journal of Photogrammetry and Remote Sensing,2017,130130:13-31.
[47]赵天舸,于瑞宏,张志磊.湿地植被地上生物量遥感估算方法研究进展[J].生态学杂志,2016,3535(7):1936-1946.
[48]Rushton S P,Ormerod S J,Kerby G.New paradigms for modeling species distributions?[J].Journal of Applied Ecology,2004,4141(2):193-200.
[49]Peters J,De Baets B,Samson R,et al.Verhoest NEC.Modelling groundwater-dependent vegetation patterns using ensemble learning[J].Hydrology&Earth System Sciences,2008,12(2):603-613.
[50]Hudak A T,Crookston N L,Evans J S,et al.Nearest neighbor imputation of species-level,plot-scale forest structure attributes from Li DAR data[J].Remote Sensing of Environment,2008,11212(5):2232-2245.
[51]Peters J,Verhoest N E C,Samson R,et al.Samson Wetland vegetation distribution modelling for the identification of constraining environmental variables[J].Landscape Ecology,2008,2323(9):1049-1065.
[52]Long A L,Kettenring K M,Hawkins C P,et al.Distribution and drivers of a widespread,invasive wetland grass,Phragmites australis,in wetlands of the Great Salt Lake,Utah,USA[J].Wetlands,2017,3737(1):45-57.
[53]Mutanga O,Adam E,Cho M A.High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm[J].International Journal of Applied Earth Observation and Geoinformation,2012,1818(1):399-406.
[54]Pham L T H,Brabyn L.Monitoring mangrove biomass change in Vietnam using SPOT images and an object-based approach combined with machine learning algorithms[J].Isprs Journal of Photogrammetry and Remote Sensing,2017,128128:86-97.
[55]Cabezas J,Galleguillos M,Perez-Quezada J F.Predicting vascular plant richness in a heterogeneous wetland using spectral and textural features and a random forest algorithm[J].IEEE Geoscience&Remote Sensing Letters,2016,1313(5):646-650.
[56]Zhu Y H,Liu K,Liu L,et al.Exploring the potential of Worldview-2 red-edge band-based vegetation indices for estimation of mangrove leaf area index with machine learning algorithms[J].Remote Sensing,2017,99(10):1060.
[57]Jagodziński A M,Horodecki P,Rawlik K,et al.Do understorey or overstorey traits drive tree encroachment on a drained raised bog?[J].Plant Biology,2017,1919(4):571-583.
[58]Castillo-Riffart I,Galleguillos M,Lopatin J,et al.Predicting vascular plant diversity in anthropogenic peatlands:comparison of modeling methods with free satellite data[J].Remote Sensing,2017,99(7):UNSP 681.
[59]Prasad A M,Iverson L R,Liaw A.Newer classification and regression tree techniques:bagging and random forests for ecological prediction[J].Ecosystems,2006,99(2):181-199.
[60]MilsomT P,Langton S D,Parkin W K,et al.Habitat models of bird species'distribution:an aid to the management of coastal grazing marshes[J].Journal of Applied Ecology,2000,3737(5):706-727.
[61]邹丽丽,陈晓翔,陈洪全,等.BP神经网络改进湿地水鸟生态位模型分布模拟研究[J].海洋环境科学,2017,3636(3):422-426.
[62]翟天庆,李欣海.用组合模型综合比较的方法分析气候变化对朱鹮潜在生境的影响[J].生态学报,2012,3232(8):2361-2370.
[63]Barbet-Massin M,Jiguet F,Albert C H,et al.Selecting pseudoabsences for species distribution models:how,where and how many?[J].Methods in Ecology&Evolution,2012,33(2):327-338.
[64]Saalfeld S T,Fischer J B,et al.Predicting waterbird nest distributions on the Yukon-Kuskokwim delta of Alaska[J].Journal of Wildlife Management,2017,8181(8):1468-1481.
[65]Kreakie BJ,Fan Y,Keitt T H.Enhanced migratory waterfowl distribution modeling by inclusion of depth to water table data[J].Plos One,2012,77(1):e30142.
[66]Nam H K,Choi S H,Yoo J C.Patterning waterbird assemblages on rice fields using self-organizing map and random forest[J].Korean Journal of Environmental Agriculture,2015,3434(3):168-177.
[67]Lieske D J,Macintosh M,Millet L,et al.Modelling the impacts of agriculture in mixed-use landscapes:a review and case study involving two species of dabbling ducks[J].Landscape Ecology,2017,333(1):35-57.
[68]Mcevoy J F,Roshier D A,Ribot R F H,et al.Proximate cues to phases of movement in a highly dispersive waterfowl Anas superciliosa[J].Movement Ecology,2015,33:21.
[69]Reese G C,Skagen S K.Modeling nonbreeding distributions of shorebirds and waterfowl in response to climate change[J].Ecology&Evolution,2017,77(5):1497-1513.
[2]贾大成,毛永新,姜奇刚,等.吉林省西部湿地形成的地质条件[J].湿地科学,2012,1010(3):327-331.
[3]贾维馨,姜琦刚,李远华,等.图们江下游湿地形成的地质条件及成因[J].湿地科学,2017,1515(3):337-342.
[4]崔桢,沈红,章光新.3个时期莫莫格国家级自然保护区景观格局和湿地水文连通性变化及其驱动因素分析[J].湿地科学,2016,1414(6):866-873.
[5]Liu H,Bu R,Liu J,et al.Predicting the wetland distributions under climate warming in the Great Xing’an Mountains,northeastern China[J].Ecological Research,2011,2626(3):605-613.
[6]Breiman L,Friedman J H,Olshen R A,et al.Classification and Regression Trees(CART)[J].Encyclopedia of Ecology,1984,40(3):582-588.
[7]Ho T K.The random subspace method for constructing decision forests[J].IEEE Transactions on Pattern Analysis&Machine Intelligence,1998,2020(8):832-844.
[8]Ho T K.Random Decision Forest[M].Boston,MA:Springer US,2010.
[9]Breiman L.Random forests[J].Machine Learning,2001,4545(1):5-32.
[10]Cutler A,Cutler D R,Stevens J R.Random forests[J].Machine Learning,2004,4545(1):157-176.
[11]Cutler R D,Edwards T C,Beard K H,et al.Random Forests for Classification in Ecology[J].Ecology,2007,8888(11):2783-2792.
[12]Mi C,Huettmann F,Guo Y,et al.Why choose random forest to predict rare species distribution with few samples in large undersampled areas?Three Asian crane species models provide supporting evidence[J].The Journal of Life and environmental Sciences,2017,55:e2849.
[13]Chen C,Liaw A,Breiman L.Using random forest to learn imbalanced data[J].Journalof Machine Learning Research,2004,1616:1-12.
[14]Robinson O J,Ruiz-Gutierrez V,Fink D.Correcting for bias in distribution modelling for rare species using citizen science data[J].Diversity&Distributions,2018,2424(4):460-472.
[15]Shotton J,Johnson M,Cipolla R.Semantic texton forests for image categorization and segmentation[C]//IEEE,2008 IEEE Conference on Computer Vision and Pattern Recognition,Anchorage,AK,USA:IEEE,2008:255-262.
[16]雷震.随机森林及其在遥感影像处理中的应用[D].上海:上海交通大学,2012.
[17]Lei Z,Fang T,Li D.Land cover classification for remote sensing imagery using conditional textonforest with historical land cover map[J].IEEE Geoscience and Remote Sensing Letters,2011,88(4):720-724.
[18]Liaw A,Wiener M.Classification and regression by random forest[J].R news,2002,22(3):18-22.
[19]付柏霖.基于多源遥感的沼泽湿地水文边界界定方法研究[D].北京:中国科学院大学,2017.
[20]刘蕾,臧淑英,那晓东,等.兼容光学雷达影像及地形辅助数据的扎龙湿地遥感分类[J].地理与地理信息科学,2013,2929(1):36-40.
[21]Arnesen A S,Silva T S F,Hess L L,et al.Monitoring flood extent in the lower Amazon River floodplain using ALOS/PAL-SAR/ScanSAR images[J].Remote Sensing of Environment,2013,13030(4):51-61.
[22]Wehr A,Lohr U.Airborne laser scanning:An introduction and overview[J].Isprs Journal of Photogrammetry&Remote Sensing,1999,544(2-3):68-82.
[23]Bai J H,Ou Y H,Cui B S,et al.Changes in landscape pattern of alpine wetlands on the ZoigêPlateau in the past four decades[J].Acta Ecologica Sinica,2008,2828(5):2245-2252.
[24]肖锦成,欧维新,符海月.基于BP神经网络与ETM+遥感数据的盐城滨海自然湿地覆盖分类[J].生态学报,2013,3333(23):7496-7504.
[25]Chan J C W,Paelinckx D.Evaluation of Random Forest and Adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery[J].Remote Sensing of Environment,2008,11212(6):2999-3011.
[26]Gislason P O,Benediktsson J A,Sveinsson J R.Random Forests for land cover classification[J].Pattern Recognition Letters,2006,2727(4):294-300.
[27]Maxwell A E,Warner T A,Strager M P.Predicting palustrine wetland probability using random forest machine learning and digital elevation data-derived terrain variables[J].Photogrammetric Engineering&Remote Sensing,2016,8282(6):437-447.
[28]Larocque A,Leblon B,Woodward R,et al.Use of Radarsat-2and ALOS-PALSAR SAR Images for Wetland Mapping in New Brunswick[C]//IEEE,IGARSS 2014-2014 IEEE International Geoscience and Remote Sensing Symposium,Quebec City,CANADA:IEEE,2014:1226-1229.
[29]Kloiber S M,Macleod R D,Smith A J.A semi-automated,multisource data fusion update of a wetland inventory for east-central Minnesota,USA[J].Wetlands,2015,3535(2):335-348.
[30]王书玉,张羽威,于振华.基于随机森林的洪河湿地遥感影像分类研究[J].测绘与空间地理信息,2014,3737(4):83-85.
[31]刘蕾,臧淑英,那晓东,等.兼容光学雷达影像及地形辅助数据的扎龙湿地遥感分类[J].地理与地理信息科学,2013,2929(1):36-40.
[32]Tian S H.Random forest classification of wetland landcovers from multi-sensor data in the arid region of Xinjiang,China[J].Remote Sensing,2016,88(11):UNSP 954.
[33]Na X D,Zang S Y,Wu C S,et al.Mapping forested wetlands in the Great Zhan River Basin through integrating optical,radar,and topographical data classification techniques[J].Environmental Monitoring&Assessment,2015,187187(11):696.
[34]Berhane T M,Lane C R,Wu Q,et al.Comparing pixel-and object-based approaches in effectively classifying wetland-dominated landscapes[J].Remote Sensing,2017,1010(1):46.
[35]Song R,Lin H,Wang G,et al.Improving selection of spectral variables for vegetation classification of east Dongting Lake,China,using a gaofen-1 image[J].Remote Sensing,2018,1010(50):50.
[36]Van Beijma S,Comber A,Lamb A.Random forest classification of salt marsh vegetation habitats using quad-polar metric airborne SAR,elevation and optical RS data[J].Remote Sensing of Environment,2014,149149:118-129.
[37]Corcoran J M,Knight J F,Gallant A L.Influence of multi-source and multi-temporal remotely sensed and ancillary data on the accuracy of random forest classification ofwetlands in northern Minnesota[J].Remote Sensing,2013,55(7):3212-3238.
[38]Dubeau P,King D,Unbushe D.Mapping the Dabus wetlands,Ethiopia,using random forest classification of landsat,palsar and topographic data[J].Remote Sensing,2017,99(10):1056.
[39]Millard K,Richardson M.Wetland mapping with Li DAR derivatives,SAR polarimetric decompositions,and Li DAR-SAR fusion using a random forest classifier[J].Canadian Journal of Remote Sensing,2013,3939(4):290-307.
[40]Blaschke H,Hay G J.Object-oriented image analysis and scalespace:theory and methods for modeling and evaluating multiscale landscape structure[J].International Archives of Photogrammetry and Remote Sensing,2001,344(4):22-29.
[41]Brisco B,Kapfer M,Hirose T T B,et al.Evaluation of C-band polarization diversity and polarimetry for wetland mapping[J].Canadian Journal of Remote Sensing,2011,3737(1):82-92.
[42]Bolin Fu.Comparison of object-based and pixel-based Random Forest algorithm for wetland vegetation mapping using high spatial resolution GF-1 and SAR data[J].Ecological Indicators,2017,733:105-117.
[43]Mahdavi S.Object-based classification of wetlands in newfoundland and labrador using multi-temporal Polsar data[J].Canadian Journal of Remote Sensing,2017,433(5):432-450.
[44]Lei Z,Fang T,Li D.Land cover classification for remote sensing imagery using Conditional Texton Forest with historical land cover map[J].IEEE Geoscience and Remote Sensing Letters,2011,88(4):720-724.
[45]Liu J,Gong J,Gong J,et al.Land-cover classification of the Yellow River Delta wetland based on multiple end-member spectral mixture analysis and a Random Forest classifier[J].International Journal of Remote Sensing,2016,377(8):1845-1867.
[46]Masoud Mahdianpari,Bahram Salehi,Fariba Mohammadimanesh,et al.Random forest wetland classification using ALOS-2 L-band,RADARSAT-2 C-band,and TerraSAR-X imagery[J].Isprs Journal of Photogrammetry and Remote Sensing,2017,130130:13-31.
[47]赵天舸,于瑞宏,张志磊.湿地植被地上生物量遥感估算方法研究进展[J].生态学杂志,2016,3535(7):1936-1946.
[48]Rushton S P,Ormerod S J,Kerby G.New paradigms for modeling species distributions?[J].Journal of Applied Ecology,2004,4141(2):193-200.
[49]Peters J,De Baets B,Samson R,et al.Verhoest NEC.Modelling groundwater-dependent vegetation patterns using ensemble learning[J].Hydrology&Earth System Sciences,2008,12(2):603-613.
[50]Hudak A T,Crookston N L,Evans J S,et al.Nearest neighbor imputation of species-level,plot-scale forest structure attributes from Li DAR data[J].Remote Sensing of Environment,2008,11212(5):2232-2245.
[51]Peters J,Verhoest N E C,Samson R,et al.Samson Wetland vegetation distribution modelling for the identification of constraining environmental variables[J].Landscape Ecology,2008,2323(9):1049-1065.
[52]Long A L,Kettenring K M,Hawkins C P,et al.Distribution and drivers of a widespread,invasive wetland grass,Phragmites australis,in wetlands of the Great Salt Lake,Utah,USA[J].Wetlands,2017,3737(1):45-57.
[53]Mutanga O,Adam E,Cho M A.High density biomass estimation for wetland vegetation using WorldView-2 imagery and random forest regression algorithm[J].International Journal of Applied Earth Observation and Geoinformation,2012,1818(1):399-406.
[54]Pham L T H,Brabyn L.Monitoring mangrove biomass change in Vietnam using SPOT images and an object-based approach combined with machine learning algorithms[J].Isprs Journal of Photogrammetry and Remote Sensing,2017,128128:86-97.
[55]Cabezas J,Galleguillos M,Perez-Quezada J F.Predicting vascular plant richness in a heterogeneous wetland using spectral and textural features and a random forest algorithm[J].IEEE Geoscience&Remote Sensing Letters,2016,1313(5):646-650.
[56]Zhu Y H,Liu K,Liu L,et al.Exploring the potential of Worldview-2 red-edge band-based vegetation indices for estimation of mangrove leaf area index with machine learning algorithms[J].Remote Sensing,2017,99(10):1060.
[57]Jagodziński A M,Horodecki P,Rawlik K,et al.Do understorey or overstorey traits drive tree encroachment on a drained raised bog?[J].Plant Biology,2017,1919(4):571-583.
[58]Castillo-Riffart I,Galleguillos M,Lopatin J,et al.Predicting vascular plant diversity in anthropogenic peatlands:comparison of modeling methods with free satellite data[J].Remote Sensing,2017,99(7):UNSP 681.
[59]Prasad A M,Iverson L R,Liaw A.Newer classification and regression tree techniques:bagging and random forests for ecological prediction[J].Ecosystems,2006,99(2):181-199.
[60]MilsomT P,Langton S D,Parkin W K,et al.Habitat models of bird species'distribution:an aid to the management of coastal grazing marshes[J].Journal of Applied Ecology,2000,3737(5):706-727.
[61]邹丽丽,陈晓翔,陈洪全,等.BP神经网络改进湿地水鸟生态位模型分布模拟研究[J].海洋环境科学,2017,3636(3):422-426.
[62]翟天庆,李欣海.用组合模型综合比较的方法分析气候变化对朱鹮潜在生境的影响[J].生态学报,2012,3232(8):2361-2370.
[63]Barbet-Massin M,Jiguet F,Albert C H,et al.Selecting pseudoabsences for species distribution models:how,where and how many?[J].Methods in Ecology&Evolution,2012,33(2):327-338.
[64]Saalfeld S T,Fischer J B,et al.Predicting waterbird nest distributions on the Yukon-Kuskokwim delta of Alaska[J].Journal of Wildlife Management,2017,8181(8):1468-1481.
[65]Kreakie BJ,Fan Y,Keitt T H.Enhanced migratory waterfowl distribution modeling by inclusion of depth to water table data[J].Plos One,2012,77(1):e30142.
[66]Nam H K,Choi S H,Yoo J C.Patterning waterbird assemblages on rice fields using self-organizing map and random forest[J].Korean Journal of Environmental Agriculture,2015,3434(3):168-177.
[67]Lieske D J,Macintosh M,Millet L,et al.Modelling the impacts of agriculture in mixed-use landscapes:a review and case study involving two species of dabbling ducks[J].Landscape Ecology,2017,333(1):35-57.
[68]Mcevoy J F,Roshier D A,Ribot R F H,et al.Proximate cues to phases of movement in a highly dispersive waterfowl Anas superciliosa[J].Movement Ecology,2015,33:21.
[69]Reese G C,Skagen S K.Modeling nonbreeding distributions of shorebirds and waterfowl in response to climate change[J].Ecology&Evolution,2017,77(5):1497-1513.
© 2004-2018 中国地质图书馆版权所有 京ICP备05064691号 京公网安备11010802017129号 地址：北京市海淀区学院路29号 邮编：100083 电话：办公室：(+86 10)66554848；文献借阅、咨询服务、科技查新：66554700 |