Integrating a Hybrid Back Propagation Neural Network and Particle Swarm Optimization for Estimating Soil Heavy Metal Contents Using Hyperspectral Data

Soil heavy metals affect human life and the environment, and thus, it is very necessary to monitor their contents. Substantial research has been conducted to estimate and map soil heavy metals in large areas using hyperspectral data and machine learning methods (such as neural network), however, lower estimation accuracy is often obtained. In order to improve the estimation accuracy, in this study, a back propagation neural network (BPNN) was combined with the particle swarm optimization (PSO), which led to an integrated PSO-BPNN method used to estimate the contents of soil heavy metals: Cd, Hg, and As. This study was conducted in Guangdong, China, based on the soil heavy metal contents and hyperspectral data collected from 90 soil samples. The prediction accuracies from BPNN and PSO-BPNN were compared using field observations. The results showed that, 1) the sample averages of Cd, Hg, and As were 0.174 mg/kg, 0.132 mg/kg, and 9.761 mg/kg, respectively, with the corresponding maximum values of 0.570 mg/kg, 0.310 mg/kg, and 68.600 mg/kg being higher than the environment baseline values; 2) the transformed and combined spectral variables had higher correlations with the contents of the soil heavy metals than the original spectral data; 3) PSO-BPNN significantly improved the estimation accuracy of the soil heavy metal contents, with the decrease in the mean relative error (MRE) and relative root mean square error (RRMSE) by 68% to 71%, and 64% to 67%, respectively. This indicated that the PSO-BPNN provided great potential to estimate the soil heavy metal contents; and 4) with the PSO-BPNN, the Cd content could also be mapped using HuanJing-1A Hyperspectral Imager (HSI) data with a RRMSE value of 36%, implying that the PSO-BPNN method could be utilized to map the heavy metal content in soil, using both field spectral data and hyperspectral imagery for the large area.

[1]  Lutgarde M. C. Buydens,et al.  The potential of field spectroscopy for the assessment of sediment properties in river floodplains , 2003 .

[2]  C. Cao,et al.  Estimation of chlorophyll-a concentration in coastal waters with HJ-1A HSI data using a three-band bio-optical model and validation , 2014 .

[3]  Hongxia Luo,et al.  The camparison of citrus canopy spectral characteristics obtained by the HJ-1A/ HSI and ASD field spectrometer , 2012, 2012 9th International Conference on Fuzzy Systems and Knowledge Discovery.

[4]  M. H. Sadr,et al.  Improving the neural network method for finite element model updating using homogenous distribution of design points , 2007 .

[5]  Jay Gao,et al.  Hyperspectral sensing of heavy metals in soil and vegetation: Feasibility and challenges , 2018 .

[6]  Riccardo Poli,et al.  Particle swarm optimization , 1995, Swarm Intelligence.

[7]  Lutgarde M. C. Buydens,et al.  Possibilities of visible–near-infrared spectroscopy for the assessment of soil contamination in river floodplains , 2001 .

[8]  Peijun Du,et al.  Estimation of Arsenic Contamination in Reclaimed Agricultural Soils Using Reflectance Spectroscopy and ANFIS Model , 2014, IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing.

[9]  Bo Gao,et al.  Estimate of heavy metals in soil and streams using combined geochemistry and field spectroscopy in Wan-sheng mining area, Chongqing, China , 2015, Int. J. Appl. Earth Obs. Geoinformation.

[10]  [Study on the prediction of soil heavy metal elements content based on mid-infrared diffuse reflectance spectra]. , 2010, Guang pu xue yu guang pu fen xi = Guang pu.

[11]  Hong-Yan Ren,et al.  [Analysis of visible and near-infrared spectra of As-contaminated soil in croplands beside mines]. , 2009, Guang pu xue yu guang pu fen xi = Guang pu.

[12]  Meiling Liu,et al.  Neural-network model for estimating leaf chlorophyll concentration in rice under stress from heavy metals using four spectral indices , 2010 .

[13]  Carranza Díaz,et al.  Espectroscopía de reflectancia difusa – NIR para la determinación del contenido de agua en el suelo , 2020 .

[14]  Ewald Schnug,et al.  Estimation of Some Chemical Properties of an Agricultural Soil by Spectroradiometric Measurements , 2008 .

[15]  H. Ramon,et al.  On-line measurement of some selected soil properties using a VIS–NIR sensor , 2007 .

[16]  C. García,et al.  Collinearity diagnostic applied in ridge estimation through the variance inflation factor , 2016 .

[17]  Philippe Lagacherie,et al.  Continuum removal versus PLSR method for clay and calcium carbonate content estimation from laboratory and airborne hyperspectral measurements , 2008 .

[18]  Zhang Chun-yao.  The Hyperspectral Characteristics and Retrieval of Soil Organic Matter Content , 2007 .

[19]  Xinghuo Yu,et al.  A general backpropagation algorithm for feedforward neural networks learning , 2002, IEEE Trans. Neural Networks.

[20]  Jing Wang,et al.  BP Neural Network and Multiple Linear Regression in Acute Hospitalization Costs in the Comparative Study , 2011 .

[21]  D. Qiu,et al.  Estimation of As and Cu Contamination in Agricultural Soils Around a Mining Area by Reflectance Spectroscopy: A Case Study , 2009 .

[22]  Amr H. Abd-Elrahman,et al.  odeling soil parameters using hyperspectral image reflectance in ubtropical coastal wetlands aveen , 2014 .

[23]  T. Meenambal,et al.  SPATIAL PREDICTION OF HEAVY METAL POLLUTION FOR SOILS IN COIMBATORE, INDIA BASED ON ANN AND KRIGING MODEL , 2012 .

[24]  F. D. Ardejani,et al.  Monitoring soil lead and zinc contents via combination of spectroscopy with extreme learning machine and other data mining methods , 2018 .

[25]  Thomas Kemper,et al.  Estimate of heavy metal contamination in soils after a mining accident using reflectance spectroscopy. , 2002, Environmental science & technology.

[26]  Z. Niu,et al.  Prediction of soil properties using laboratory VIS–NIR spectroscopy and Hyperion imagery , 2013 .

[27]  C. Hurburgh,et al.  Near-Infrared Reflectance Spectroscopy–Principal Components Regression Analyses of Soil Properties , 2001 .

[28]  Feridon Ghadimi,et al.  Prediction of heavy metals contamination in the groundwater of Arak region using artificial neural network and multiple linear regression , 2016 .

[29]  Tiezhu Shi,et al.  Prediction of low heavy metal concentrations in agricultural soils using visible and near-infrared reflectance spectroscopy , 2014 .

[30]  Jing Wang,et al.  [Spatiotemporal variation of soil pH in Guangdong Province of China in past 30 years]. , 2011, Ying yong sheng tai xue bao = The journal of applied ecology.

[31]  Zhihao Qin,et al.  Possibilities of reflectance spectroscopy for the assessment of contaminant elements in suburban soils , 2005 .

[32]  Lin Li,et al.  Estimation of heavy-metal contamination in soil using reflectance spectroscopy and partial least-squares regression , 2010 .