A hybrid model for predicting spatial distribution of soil organic matter in a bamboo forest based on general regression neural network and interative algorithm

Abstract

A general regression neural network model, combined with an interative algorithm (GRNNI) using sparsely distributed samples and auxiliary environmental variables was proposed to predict both spatial distribution and variability of soil organic matter (SOM) in a bamboo forest. The auxiliary environmental variables were: elevation, slope, mean annual temperature, mean annual precipitation, and normalized difference vegetation index. The prediction accuracy of this model was assessed via three accuracy indices, mean error (ME), mean absolute error (MAE), and root mean squared error (RMSE) for validation in sampling sites. Both the prediction accuracy and reliability of this model were compared to those of regression kriging (RK) and ordinary kriging (OK). The results show that the prediction accuracy of the GRNNI model was higher than that of both RK and OK. The three accuracy indices (ME, MAE, and RMSE) of the GRNNI model were lower than those of RK and OK. Relative improvements of RMSE of the GRNNI model compared with RK and OK were 13.6% and 17.5%, respectively. In addition, a more realistic spatial pattern of SOM was produced by the model because the GRNNI model was more suitable than multiple linear regression to capture the nonlinear relationship between SOM and the auxiliary environmental variables. Therefore, the GRNNI model can improve both prediction accuracy and reliability for determining spatial distribution and variability of SOM.

Keywords

General regression neural network / Interative algorithm / Ordinary kriging / Regression kriging / Spatial prediction / Soil organic matter

References

[1] Alomair OA, Garrouch AA. A general regression neural network model offers reliable prediction of CO₂ minimum miscibility pressure. J Pet Explor Prod Technol, 2016, 6: 351-365.

[2] Antanasijević DZ, Ristić MD, Perić-Grujić AA, Pocajt VV. Forecasting human exposure to PM10 at the national level using an artificial neural network approach. J Chemom, 2013, 27: 170-177.

[3] Behrens T, Förster H, Scholten T, Steinrücken U, Spies ED, Goldschmitt M. Digital soil mapping using artificial neural networks. J Soil Sci Plant Nutr, 2005, 168: 21-33.

[4] Dai FQ, Zhou QG, Lv ZQ, Wang XM, Liu GC. Spatial prediction of soil organic matter content integrating artificial neural network and ordinary kriging in Tibetan Plateau. Ecol Indic, 2014, 45: 184-194.

[5] Gautam R, Panigrahi S, Franzen D, Sims A. Residual soil nitrate prediction from imagery and non-imagery information using neural network technique. Biosyst Eng, 2011, 110: 20-28.

[6] Guo PT, Wu W, Sheng QK, Li MF, Liu HB, Wang ZY. Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas. Nutr Cycl Agroeco Syst, 2013, 95: 333-344.

[7] Hengl T, Heuvelink GBM, Stein A. A generic framework for spatial prediction of soil variables based on regression-kriging. Geoderma, 2004, 120: 75-93.

[8] Hengl T, Heuvelink GBM, Rossiter DG. About regression-kriging: from equation to case studies. Comput Geosci, 2007, 33: 1301-1315.

[9] Kim SW, Singh VP, Seo YM, Kim HS. Modeling nonlinear monthly evapotranspiration using soft computing and data reconstruction techniques. Water Resour Manag, 2014, 28: 185-206.

[10] Knotters M, Brus DJ, Oude Voshaar JH. A comparison of kriging, cokriging and kriging combined with regression for spatial interpolation of horizon depth with censored observations. Geoderma, 1995, 67: 227-246.

[11] Kumar S, Lal R, Liu DS. A geographically weighted regression kriging approach for mapping soil organic carbon stock. Geoderma, 2012, 189–190: 627-634.

[12] Li CF, Bovik AC, Wu XJ. Blind image quality assessment using a general regression neural network. IEEE T Neural Netw, 2011, 22: 793-799.

[13] Li QQ, Yue TX, Wang CQ, Zhang WJ, Yu Y, Li B, Yang J, Bai GH. Spatially distributed modeling of soil organic matter across China: an application of artificial neural network approach. CATENA, 2013, 104: 210-218.

[14] Li QQ, Zhang X, Wang CQ, Li B, Gao XS, Yuan DG, Luo YL. Spatial prediction of soil nutrient in a hilly area using artificial neural network model combined with kriging. Arch Agron Soil Sci, 2016, 62: 1541-1553.

[15] Lin SM. Analysis of service satisfaction in web auction logistics service using a combination of fruit fly optimization algorithm and general regression neural network. Neural Comput Appl, 2013, 22: 783-791.

[16] McBratney AB, Mendonca Santos ML, Minasny B. On digital soil mapping. Geoderma, 2003, 117: 3-52.

[17] Mora-Vallejo A, Claessens L, Stoorvogel J, Heuvelink GBM. Small scale digital soil mapping in Southeastern Kenya. CATENA, 2008, 76: 44-53.

[18] Odeh I, McBratney AB, Chittleborough DJ. Spatial prediction of soil properties from landform attributes derived from a digital elevation model. Geoderma, 1994, 63: 197-214.

[19] Pebesma EJ. Multivariable geostatistics in S: the gstat package. Comput Geosci, 2004, 30: 683-691.

[20] Simbahan GC, Dobermann A, Goovaerts P, Ping J, Haddix ML. Fineresolution mapping of soil organic carbon based on multivariate secondary data. Geoderma, 2006, 132: 471-489.

[21] Somaratne S, Seneviratne G, Coomaraswamy U. Prediction of soil organic carbon across different land-use patterns: a neural network approach. Soil Sci Soc Am J, 2005, 69: 1580-1589.

[22] Specht DF. A general regression neural network. IEEE T Neural Networ, 1991, 2: 568-576.

[23] Wang K, Zhang CR, Li WD. Comparison of geographically weighted regression and regression kriging for estimating the spatial distribution of soil organic matter. GIsci Remote Sens, 2012, 49: 915-932.

[24] Wang K, Zhang CR, Li WD, Lin J, Zhang DX. Mapping soil organic matter with limited sample data using geographically weighted regression. J Spat Sci, 2014, 59: 91-106.

[25] Wu CF, Wu JP, Luo YM, Zhang LM, DeGloria SD. Spatial prediction of soil organic matter content using cokriging with remotely sensed data. Soil Sci Soc Am J, 2009, 73: 1202-1208.

[26] Wu JF, Peng DH, Li ZP, Zhao L, Ling HZ. Network intrusion detection based on a general regression neural network optimized by an improved artificial immune algorithm. PLoS ONE, 2015 10 3 e0120976

[27] Yap KS, Lim CP, Abidin IZ. A hybrid ART-GRNN online learning neural network with a epsilon-insensitive loss function. IEEE T Neural Netw, 2008, 19: 1641-1646.

[28] Zhang W, Wang KL, Chen HS, He XY, Zhang JG. Ancillary information improves kriging on soil organic carbon data for a typical karst peak cluster depression landscape. J Sci Food Agric, 2012, 92: 1094-1102.

[29] Zhao ZY, Chow TL, Rees HW, Yang Q, Xing ZS, Meng FR. Predict soil texture distribution using an artificial neural network model. Comput Electron Agric, 2009, 65: 36-48.

[30] Zhao ZY, Yang Q, Benoy G, Chow TL, Xing ZS, Rees HW, Meng FR. Using artificial neural network models to produce soil organic carbon content distribution maps across landscapes. Can J Soil Sci, 2010, 90: 75-87.

[31] Zhou QP, Jiang HY, Wang JZ, Zhou JL. A hybrid model for PM_2.5 forecasting based on ensemble empirical mode decomposition and a general regression neural network. Sci Total Environ, 2014, 496: 264-274.