Integrating spectral indices with environmental parameters for estimating heavy metal concentrations in rice using a dynamic fuzzy neural-network model

A generalized dynamic fuzzy neural network (GDFNN) was created to estimate heavy metal concentrations in rice by integrating spectral indices and environmental parameters. Hyperspectral data, environmental parameters, and heavy metal content were collected from field experiments with different levels of heavy metal pollution (Cu and Cd). Input variables used in the GDFNN model were derived from 10 variables acquired by gray relational analysis. The assessment models for Cd and Cu concentration employed five and six input variables, respectively. The results showed that the GDFNN for estimating Cu and Cd concentrations in rice performed well at prediction with a compact network structure using the training, validation, and testing sets (for Cu, fuzzy rules=9, R^2 greater than 0.75, and RMSE less than 2.5; for Cd, fuzzy rules=9, R^2 greater than 0.75, and RMSE less than 1.0). The final GDFNN model was then compared with a back-propagation (BP) neural network model, adaptive-network-based fuzzy interference systems (ANFIS), and a regression model. The accuracies of GDFNN model prediction were usually slightly better than those of the other three models. This demonstrates that the GDFNN model is more suitable for predicting heavy metal concentrations in rice.

[1]  H. Noh,et al.  A Neural Network Model of Maize Crop Nitrogen Stress Assessment for a Multi-spectral Imaging Sensor , 2006 .

[2]  Tony Plate,et al.  Visualizing the Function Computed by a Feedforward Neural Network , 2000, Neural Computation.

[3]  Guoping Zhang,et al.  The influence of pH and organic matter content in paddy soil on heavy metal availability and their uptake by rice plants. , 2011, Environmental pollution.

[4]  A. Malik,et al.  Artificial neural network modeling of the river water quality—A case study , 2009 .

[5]  Y. Pachepsky,et al.  Artificial Neural Networks to Estimate Soil Water Retention from Easily Measurable Data , 1996 .

[6]  Hui Chen,et al.  Feasibility of estimating heavy metal concentrations in Phragmites australis using laboratory-based hyperspectral data - A case study along Le'an River, China , 2010, Int. J. Appl. Earth Obs. Geoinformation.

[7]  Si-Ning Chen,et al.  [Study on the spectrum response of Brassica Campestris L leaf to the zinc pollution]. , 2007, Guang pu xue yu guang pu fen xi = Guang pu.

[8]  Hongrui Wang,et al.  Generalized dynamic fuzzy neural network-based tracking control of robot manipulators , 2004, Proceedings of 2004 International Conference on Machine Learning and Cybernetics (IEEE Cat. No.04EX826).

[9]  Ralf Wieland,et al.  Adaptive fuzzy modeling versus artificial neural networks , 2008, Environ. Model. Softw..

[10]  Dawei Han,et al.  Evaporation Estimation Using Artificial Neural Networks and Adaptive Neuro-Fuzzy Inference System Techniques , 2009 .

[11]  Isaac Asencio,et al.  Capability of Selected Crop Plants for Shoot Mercury Accumulation from Polluted Soils: Phytoremediation Perspectives , 2007, International journal of phytoremediation.

[12]  Yo-Ping Huang,et al.  The integration and application of fuzzy and grey modeling methods , 1996, Fuzzy Sets Syst..

[13]  J. Fernandes,et al.  Biochemical, physiological, and structural effects of excess copper in plants , 1991, The Botanical Review.

[14]  J. Buckley,et al.  Fuzzy neural networks: a survey , 1994 .

[15]  A. Huete.  A soil-adjusted vegetation index (SAVI) , 1988 .

[16]  G. Huang,et al.  Grey integer programming: An application to waste management planning under uncertainty , 1995 .

[17]  T. Martin McGinnity,et al.  An approach for on-line extraction of fuzzy rules using a self-organising fuzzy neural network , 2005, Fuzzy Sets Syst..

[18]  F. Meer,et al.  Quantitative analysis of salt-affected soil reflectance spectra: A comparison of two adaptive methods (PLSR and ANN) , 2007 .

[19]  P. Das,et al.  Studies on cadmium toxicity in plants: a review. , 1997, Environmental pollution.

[20]  C. Mao,et al.  Comparison of two hyperspectral imaging and two laser-induced fluorescence instruments for the detection of zinc stress and chlorophyll concentration in bahia grass (Paspalum notatum Flugge.) , 2003 .

[21]  Meng Joo Er,et al.  Dynamic fuzzy neural networks-a novel approach to function approximation , 2000, IEEE Trans. Syst. Man Cybern. Part B.

[22]  Ninan Sajeeth Philip,et al.  A neural network tool for analyzing trends in rainfall , 2003 .

[23]  J. Deng,et al.  Introduction to Grey system theory , 1989 .

[24]  Paul M. Feikema,et al.  Quantifying uncertainty from large‐scale model predictions of forest carbon dynamics , 2006 .

[25]  Siza D. Tumbo,et al.  HYPERSPECTRAL–BASED NEURAL NETWORK FOR PREDICTING CHLOROPHYLL STATUS IN CORN , 2002 .

[26]  I Thornton,et al.  Environmental contamination and seasonal variation of metals in soils, plants and waters in the paddy fields around a Pb-Zn mine in Korea. , 1997, The Science of the total environment.

[27]  Alessandro Sperduti,et al.  Discriminant Pattern Recognition Using Transformation-Invariant Neurons , 2000, Neural Computation.

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

[29]  Meng Joo Er,et al.  Control of a mobile robot using generalized dynamic fuzzy neural networks , 2004, Microprocess. Microsystems.

[30]  Sheng-Huei Chang,et al.  Airborne biogeophysical mapping of hidden mineral deposits , 1983 .

[31]  Jyh-Shing Roger Jang,et al.  ANFIS: adaptive-network-based fuzzy inference system , 1993, IEEE Trans. Syst. Man Cybern..

[32]  Ahmed Ouenes,et al.  Practical application of fuzzy logic and neural networks to fractured reservoir characterization , 2000 .

[33]  Meng Joo Er,et al.  A fast approach for automatic generation of fuzzy rules by generalized dynamic fuzzy neural networks , 2001, IEEE Trans. Fuzzy Syst..

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

[35]  Gwo-Ching Liao,et al.  Application of fuzzy neural networks and artificial intelligence for load forecasting , 2004 .

[36]  Mohammad Ali Ghorbani,et al.  Sea water level forecasting using genetic programming and comparing the performance with Artificial Neural Networks , 2010, Comput. Geosci..

[37]  T.Y. Pai,et al.  Using fuzzy inference system to improve neural network for predicting hospital wastewater treatment plant effluent , 2009, Comput. Chem. Eng..

[38]  Manuel A. Rodrigo,et al.  Use of neurofuzzy networks to improve wastewater flow-rate forecasting , 2009, Environ. Model. Softw..

[39]  H. Ertunç,et al.  Comparative analysis of an evaporative condenser using artificial neural network and adaptive neuro-fuzzy inference system , 2008 .

[40]  Huoyan Wang,et al.  Risk assessment of potentially toxic element pollution in soils and rice (Oryza sativa) in a typical area of the Yangtze River Delta. , 2009, Environmental pollution.

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

[42]  Chin-Teng Lin,et al.  An ART-based fuzzy adaptive learning control network , 1997, IEEE Trans. Fuzzy Syst..

[43]  Xin Chen,et al.  Spectral response of rice (Oryza sativa L.) leaves to Fe2+ stress , 2009, Science in China Series C: Life Sciences.

[44]  R. Chaney,et al.  The Physiology of Metal Toxicity in Plants , 1978 .

[45]  Zhang Guo-ping,et al.  Effect of Grain Position within a Panicle and Variety on As, Cd, Cr, Ni, Pb Concentrations in japonica Rice , 2005 .

[46]  L. Buydens,et al.  Exploring field vegetation reflectance as an indicator of soil contamination in river floodplains. , 2004, Environmental pollution.

[47]  Giles M. Foody,et al.  Using prior knowledge in artificial neural network classification with a minimal training set , 1995 .

[48]  William J. Collins,et al.  Confirmation of the airborne biogeophysical mineral exploration technique using laboratory methods , 1983 .