Classification of Rice Heavy Metal Stress Levels Based on Phenological Characteristics Using Remote Sensing Time-Series Images and Data Mining Algorithms

Heavy metal pollution in crops leads to phenological changes, which can be monitored by remote sensing technology. The present study aims to develop a method for accurately evaluating heavy metal stress in rice based on remote sensing phenology. First, the enhanced spatial and temporal adaptive reflectance fusion model (ESTARFM) was applied to blend Moderate Resolution Imaging Spectroradiometer (MODIS) and Landsat to generate a time series of fusion images at 30 m resolution, and then the vegetation indices (VIs) related to greenness and moisture content of the rice canopy were calculated to create the time-series of VIs. Second, phenological metrics were extracted from the time-series data of VIs, and a feature selection scheme was designed to acquire an optimal phenological metric subset. Finally, an ensemble model with optimal phenological metrics as classification features was built using random forest (RF) and gradient boosting (GB) classifiers, and the classification of stress levels was implemented. The results demonstrated that the overall accuracy of discrimination for different stress levels is greater than 98%. This study suggests that fusion images can be utilized to detect heavy metal stress in rice, and the proposed method may be applicable to classify stress levels.

[1]  Changsheng Li,et al.  Mapping paddy rice agriculture in southern China using multi-temporal MODIS images , 2005 .

[2]  Limin Wang,et al.  Mapping crop phenology using NDVI time-series derived from HJ-1 A/B data , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[3]  Clement Atzberger,et al.  Estimation of inter-annual winter crop area variation and spatial distribution with low resolution NDVI data by using neural networks trained on high resolution images , 2009, Remote Sensing.

[4]  Xingmei Liu,et al.  The identification of 'hotspots' of heavy metal pollution in soil-rice systems at a regional scale in eastern China. , 2014, The Science of the total environment.

[5]  A. Skidmore,et al.  Heavy metal-induced stress in rice crops detected using multi-temporal Sentinel-2 satellite images. , 2018, The Science of the total environment.

[6]  Jürgen Bajorath,et al.  Compound Classification Using the scikit‐learn Library , 2017 .

[7]  Per Jönsson,et al.  TIMESAT - a program for analyzing time-series of satellite sensor data , 2004, Comput. Geosci..

[8]  Lingzao Zeng,et al.  A multi-medium chain modeling approach to estimate the cumulative effects of cadmium pollution on human health. , 2018, Environmental pollution.

[9]  Zhi Huang,et al.  Extraction of Rice Phenological Differences under Heavy Metal Stress Using EVI Time-Series from HJ-1A/B Data , 2017, Sensors.

[10]  Mathew R. Schwaller,et al.  On the blending of the Landsat and MODIS surface reflectance: predicting daily Landsat surface reflectance , 2006, IEEE Transactions on Geoscience and Remote Sensing.

[11]  Annemarie Schneider,et al.  Monitoring land cover change in urban and peri-urban areas using dense time stacks of Landsat satellite data and a data mining approach , 2012 .

[12]  Jinwei Dong,et al.  Mapping paddy rice planting areas through time series analysis of MODIS land surface temperature and vegetation index data. , 2015, ISPRS journal of photogrammetry and remote sensing : official publication of the International Society for Photogrammetry and Remote Sensing.

[13]  P. Eilers.  A perfect smoother. , 2003, Analytical chemistry.

[14]  T. Sakamoto,et al.  A crop phenology detection method using time-series MODIS data , 2005 .

[15]  Tomomasa Nagashima,et al.  Accurate and robust gene selection for disease classification using a simple statistic , 2008, Bioinformation.

[16]  Shulin Wang,et al.  Feature selection in machine learning: A new perspective , 2018, Neurocomputing.

[17]  Wenjiang Huang,et al.  Applying remote sensing techniques to monitoring seasonal and interannual changes of aquatic vegetation in Taihu Lake, China , 2016 .

[18]  Jennifer N. Hird,et al.  Noise reduction of NDVI time series: An empirical comparison of selected techniques , 2009 .

[19]  A. Huete,et al.  Overview of the radiometric and biophysical performance of the MODIS vegetation indices , 2002 .

[20]  Jesslyn F. Brown,et al.  Measuring phenological variability from satellite imagery , 1994 .

[21]  Lu Zhenquan.  Reconstruction of MODIS LST Time Series and Comparison with Land Surface Temperature (T) among Observation Stations in the Northeast Qinghai-Tibet Plateau , 2011 .

[22]  Ming Lei,et al.  Heavy metal pollution and potential health risk assessment of white rice around mine areas in Hunan Province, China , 2015, Food Security.

[23]  Xiaolin Zhu,et al.  An enhanced spatial and temporal adaptive reflectance fusion model for complex heterogeneous regions , 2010 .

[24]  Xuezheng Shi,et al.  Hyper-spectral remote sensing to monitor vegetation stress , 2008 .

[25]  P. C. Nagajyoti,et al.  Heavy metals, occurrence and toxicity for plants: a review , 2010 .

[26]  Bradley C. Reed,et al.  Remote Sensing Phenology , 2009 .

[27]  Masahiro Sawai,et al.  Statistical method for classifying cries of baby based on pattern recognition of power spectrum , 2010, Int. J. Biom..

[28]  WU Deng-wei,et al.  Review on Remote Sensing Monitoring on Contaminated Plant , 2012 .

[29]  K. Beurs,et al.  Evaluation of Landsat and MODIS data fusion products for analysis of dryland forest phenology , 2012 .

[30]  Jonas S. Almeida,et al.  Automated smoother for the numerical decoupling of dynamics models , 2007, BMC Bioinformatics.

[31]  Conceição Santos,et al.  Cadmium toxicity affects photosynthesis and plant growth at different levels , 2012, Acta Physiologiae Plantarum.

[32]  P. Eilers,et al.  Evaluating the effectiveness of smoothing algorithms in the absence of ground reference measurements , 2011 .

[33]  Peijun Du,et al.  Random Forest and Rotation Forest for fully polarized SAR image classification using polarimetric and spatial features , 2015 .

[34]  Shuiping Cheng,et al.  Effects of Heavy metals on plants and resistance mechanisms , 2003 .

[35]  Xiangnan Liu,et al.  Evaluating Heavy-Metal Stress Levels in Rice Using a Theoretical Model of Canopy-Air Temperature and Leaf Area Index Based on Remote Sensing , 2017, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[36]  S. Piao,et al.  Spring vegetation green-up date in China inferred from SPOT NDVI data: A multiple model analysis , 2012 .

[37]  G. Pan,et al.  Low uptake affinity cultivars with biochar to tackle Cd-tainted rice--A field study over four rice seasons in Hunan, China. , 2016, The Science of the total environment.

[38]  Meiling Liu,et al.  Evaluating Heavy Metal Stress Levels in Rice Based on Remote Sensing Phenology , 2018, Sensors.

[39]  Xiangnan Liu,et al.  Extraction of Rice Heavy Metal Stress Signal Features Based on Long Time Series Leaf Area Index Data Using Ensemble Empirical Mode Decomposition , 2017, International journal of environmental research and public health.

[40]  Joanne C. White,et al.  A new data fusion model for high spatial- and temporal-resolution mapping of forest disturbance based on Landsat and MODIS , 2009 .

[41]  P. Atkinson,et al.  Inter-comparison of four models for smoothing satellite sensor time-series data to estimate vegetation phenology , 2012 .

[42]  Esra Erten,et al.  Paddy-Rice Phenology Classification Based on Machine-Learning Methods Using Multitemporal Co-Polar X-Band SAR Images , 2016, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[43]  Jin Chen,et al.  An improved logistic method for detecting spring vegetation phenology in grasslands from MODIS EVI time-series data , 2015 .

[44]  Andreas W. Kempa-Liehr,et al.  Distributed and parallel time series feature extraction for industrial big data applications , 2016, ArXiv.

[45]  M. Friedl,et al.  Detecting interannual variation in deciduous broadleaf forest phenology using Landsat TM/ETM+ data , 2013 .

[46]  F. Gao,et al.  Generating daily land surface temperature at Landsat resolution by fusing Landsat and MODIS data , 2014 .

[47]  Jin Chen,et al.  Global land cover mapping at 30 m resolution: A POK-based operational approach , 2015 .

[48]  Ling Yan.  Study on Phenology Extraction of Paddy Rice Based on Different Filtering Methods , 2014 .

[49]  B. Gao.  NDWI—A normalized difference water index for remote sensing of vegetation liquid water from space , 1996 .

[50]  Andreas W. Kempa-Liehr,et al.  Time Series FeatuRe Extraction on basis of Scalable Hypothesis tests (tsfresh - A Python package) , 2018, Neurocomputing.

[51]  C. Poschenrieder,et al.  Plant water relations as affected by heavy metal stress: A review , 1990 .

[52]  Hugh G. Lewis,et al.  A generalized confusion matrix for assessing area estimates from remotely sensed data , 2001 .

[53]  Jonathan Cheung-Wai Chan,et al.  Multiple Criteria for Evaluating Machine Learning Algorithms for Land Cover Classification from Satellite Data , 2000 .

[54]  Jinwei Dong,et al.  Mapping paddy rice planting area in northeastern Asia with Landsat 8 images, phenology-based algorithm and Google Earth Engine. , 2016, Remote sensing of environment.

[55]  Lei Liu,et al.  Impact of Soil Heavy Metal Pollution on Food Safety in China , 2015, PloS one.

[56]  Lars Järup,et al.  Hazards of heavy metal contamination. , 2003, British medical bulletin.

[57]  Yu Mo,et al.  Quantifying moderate resolution remote sensing phenology of Louisiana coastal marshes , 2015 .

[58]  Mark Goadrich,et al.  The relationship between Precision-Recall and ROC curves , 2006, ICML.

[59]  Songfeng Zheng,et al.  Applying tree-based ensemble algorithms to the classification of ecological zones using multi-temporal multi-source remote-sensing data , 2012 .

[60]  Jie Wang,et al.  Mapping paddy rice planting area in rice-wetland coexistent areas through analysis of Landsat 8 OLI and MODIS images , 2016, Int. J. Appl. Earth Obs. Geoinformation.

[61]  Clement Atzberger,et al.  A time series for monitoring vegetation activity and phenology at 10-daily time steps covering large parts of South America , 2011, Int. J. Digit. Earth.