Machine Learning for Estimating Leaf Dust Retention Based on Hyperspectral Measurements

Hyperspectral sensors provide detailed information for dust retention content (DRC) estimation. However, rich hyperspectral data are not fully utilized by traditional image analysis techniques. We integrated several recently developed machine learning algorithms to estimate DRC on plant leaves using the spectra measured by the ASD FieldSpec 3. The experiments were carried out on three common green plants of southern China. The important hyperspectral variables were first identified by applying the random forest (RF) algorithm. Three estimation models were then developed using the support vector machine (SVM), classification and regression tree (CART), and RF algorithms. The results showed that the increase in dust retention contents on plant leaves enhanced their reflectance in the visible wavelength but weakened their reflectance in the infrared wavelength. Wavelengths in the ranges of 450–500 nm, 550–600 nm, 750–1000 nm, and 1100–1300 nm were identified as important variables using the RF algorithm and were used to estimate the DRC. The comparison of the three machine learning techniques for DRC estimation confirmed that the SVM and RF models performed well because their estimations were similar to the measured DRC. Specifically, the average R2 for SVM and RF model are 0.85 and 0.88. The technical approach of this study proved to be a successful illustration of using hyperspectral measurements to estimate the DRC on plant leaves. The findings of this study can be applied to monitor the DRC on leaves of other plants and can also be integrated with other types of spectral data to measure the DRC at a regional scale.

[1]  Jie Duan,et al.  An investigation of the leaf retention capacity, efficiency and mechanism for atmospheric particulate matter of five greening tree species in Beijing, China. , 2018, The Science of the total environment.

[2]  John W. Dover,et al.  Particulate matter pollution capture by leaves of seventeen living wall species with special reference to rail-traffic at a metropolitan station , 2017 .

[3]  Vijay Sivaraman,et al.  HazeEst: Machine Learning Based Metropolitan Air Pollution Estimation From Fixed and Mobile Sensors , 2017, IEEE Sensors Journal.

[4]  Rui Yang,et al.  Analysis on Dust Retention Measurement of Common Plant Leaves in Shenyang , 2017 .

[5]  Shuai Shi,et al.  Retention of Atmospheric Particles by Local Plant Leaves in the Mount Wutai Scenic Area, China , 2016 .

[6]  John J. Nay,et al.  Application of machine learning to the prediction of vegetation health , 2016 .

[7]  Chunyan Wu,et al.  Research of foliar dust content estimation by reflectance spectroscopy of Euonymus japonicus Thunb , 2016 .

[8]  Mariana Belgiu,et al.  Random forest in remote sensing: A review of applications and future directions , 2016 .

[9]  John J. Nay,et al.  A machine-learning approach to forecasting remotely sensed vegetation health , 2016, 1602.06335.

[10]  Q. Xiong,et al.  [Retrieving Dustfall Distribution in Beijing City Based on Ground Spectral Data and Remote Sensing]. , 2016, Guang pu xue yu guang pu fen xi = Guang pu.

[11]  Stien Heremans,et al.  Machine learning methods for sub-pixel land-cover classification in the spatially heterogeneous region of Flanders (Belgium): a multi-criteria comparison , 2015 .

[12]  Xia Hui-lin.  ANALYSIS OF DUST DETENTION CAPABILITY OF LANDSCAPE PLANTS AND THE HYPERSPECTRAL REMOTE SENSING QUANTITATIVE MODELS CONSTRUCTION OF FOLIAGEDUST DETENTION , 2015 .

[13]  T. Aishan,et al.  Dust Retention Capacities of Urban Trees and the Influencing Factors in Aksu, Xinjiang, China , 2015 .

[14]  M. Molina,et al.  Elucidating severe urban haze formation in China , 2014, Proceedings of the National Academy of Sciences.

[15]  A. Piazzalunga,et al.  High secondary aerosol contribution to particulate pollution during haze events in China , 2014, Nature.

[16]  T. Emilsson,et al.  Plant performance in living wall systems in the Scandinavian climate , 2014 .

[17]  W. Shi,et al.  Estimation of Atmospheric Dust Deposition on Plant Leaves Based on Spectral Features , 2014 .

[18]  Shikha Gupta,et al.  Identifying pollution sources and predicting urban air quality using ensemble learning methods , 2013 .

[19]  Na Luo,et al.  [Impact of dust-fall on spectral features of plant leaves]. , 2013, Guang pu xue yu guang pu fen xi = Guang pu.

[20]  Bani K. Mallick,et al.  Hyperspectral remote sensing of plant biochemistry using Bayesian model averaging with variable and band selection , 2013 .

[21]  D. Guan,et al.  The dust retention capacities of urban vegetation—a case study of Guangzhou, South China , 2013, Environmental Science and Pollution Research.

[22]  George Alan Blackburn,et al.  Discrimination of plant stress caused by oil pollution and waterlogging using hyperspectral and thermal remote sensing , 2013 .

[23]  Jiangxiao Qiu,et al.  Variations of urban greenness across urban structural units in Beijing, China , 2013 .

[24]  Yue-ming Zuo,et al.  [Influence of foliar dust on crop reflectance spectrum and nitrogen monitoring]. , 2012, Guang pu xue yu guang pu fen xi = Guang pu.

[25]  Yi-Chung Wang.  Carbon sequestration and foliar dust retention by woody plants in the greenbelts along two major Taiwan highways , 2011 .

[26]  A. Kalra,et al.  Estimating soil moisture using remote sensing data: A machine learning approach , 2010 .

[27]  Freek D. van der Meer,et al.  Mapping of heavy metal pollution in stream sediments using combined geochemistry, field spectroscopy, and hyperspectral remote sensing: A case study of the Rodalquilar mining area, SE Spain , 2008 .

[28]  Jonathan Cheung-Wai Chan,et al.  Evaluation of random forest and adaboost tree-based ensemble classification and spectral band selection for ecotope mapping using airborne hyperspectral imagery , 2008 .

[29]  Janet Franklin,et al.  Mapping land-cover modifications over large areas: A comparison of machine learning algorithms , 2008 .

[30]  Lorenzo Bruzzone,et al.  Classification of hyperspectral remote-sensing data with primal SVM for small-sized training dataset problem☆ , 2008 .

[31]  Kellie J. Archer,et al.  Empirical characterization of random forest variable importance measures , 2008, Comput. Stat. Data Anal..

[32]  Yan Ning-zhen,et al.  Study on Dynamic Change and Protection of Cultivated Land in Regional Land Utilization , 2007 .

[33]  Achim Zeileis,et al.  Bias in random forest variable importance measures: Illustrations, sources and a solution , 2007, BMC Bioinformatics.

[34]  T. Fearn,et al.  Classification and Regression Trees (CART) , 2020, Statistical Learning from a Regression Perspective.

[35]  Yoram J. Kaufman,et al.  Assessing vegetation condition in the presence of biomass burning smoke by applying the Aerosol‐free Vegetation Index (AFRI) on MODIS images , 2006 .

[36]  Giles M. Foody,et al.  The use of small training sets containing mixed pixels for accurate hard image classification: Training on mixed spectral responses for classification by a SVM , 2006 .

[37]  V. Kretinin,et al.  Dust retention by tree and shrub leaves and its accumulation in light chestnut soils under forest shelterbelts , 2006 .

[38]  J. Randerson,et al.  Global estimation of burned area using MODIS active fire observations , 2005 .

[39]  Liu Su-hong.  Spectral Characteristics of Vegetation in Environment Pollution Monitoring , 2005 .

[40]  Leo Breiman,et al.  Random Forests , 2001, Machine Learning.

[41]  Corinna Cortes,et al.  Support-Vector Networks , 1995, Machine Learning.

[42]  Vladimir Vapnik,et al.  Support-vector networks , 2004, Machine Learning.

[43]  Alan H. Strahler,et al.  Global land cover mapping from MODIS: algorithms and early results , 2002 .

[44]  L. S. Davis,et al.  An assessment of support vector machines for land cover classi(cid:142) cation , 2002 .

[45]  K. Taylor.  Summarizing multiple aspects of model performance in a single diagram , 2001 .

[46]  D. Horler,et al.  The red edge of plant leaf reflectance , 1983 .

[47]  A. M. Wahbi,et al.  The use of the first-derivative curves of absorption spectra in quantitative analysis , 1974 .