Digital Soil Mapping of Soil Organic Matter with Deep Learning Algorithms

被引:14
作者
Zeng, Pengyuan [1 ]
Song, Xuan [1 ]
Yang, Huan [2 ]
Wei, Ning [2 ]
Du, Liping [3 ]
机构
[1] Zhengzhou Univ, Sch Cyber Sci & Engn, Zhengzhou 450001, Peoples R China
[2] Zhengzhou Univ, Sch Water Conservancy Sci & Engn, Zhengzhou 450001, Peoples R China
[3] Zhengzhou Univ, Sch Civil Engn, Zhengzhou 450001, Peoples R China
关键词
digital soil mapping (DSM); soil organic matter (SOM); deep learning (DL); resnet; remote sensing; GEOGRAPHICALLY WEIGHTED REGRESSION; ARTIFICIAL NEURAL-NETWORK; SPATIAL-DISTRIBUTION; REGIONAL-SCALE; TOTAL NITROGEN; CARBON STOCKS; BANEH REGION; RIVER-BASIN; PREDICTION; VEGETATION;
D O I
10.3390/ijgi11050299
中图分类号
TP [自动化技术、计算机技术];
学科分类号
0812 ;
摘要
Digital soil mapping has emerged as a new method to describe the spatial distribution of soils economically and efficiently. In this study, a lightweight soil organic matter (SOM) mapping method based on a deep residual network, which we call LSM-ResNet, is proposed to make accurate predictions with background covariates. ResNet not only integrates spatial background information around the observed environmental covariates, but also reduces problems such as information loss, which undermines the integrity of information and reduces prediction uncertainty. To train the model, rectified linear units, mean squared error, and adaptive momentum estimation were used as the activation function, loss/cost function, and optimizer, respectively. The method was tested with Landsat5, the meteorological data from WorldClim, and the 1602 sampling points set from Xinxiang, China. The performance of the proposed LSM-ResNet was compared to a traditional machine learning algorithm, the random forest (RF) algorithm, and a training set (80%) and a test set (20%) were created to test both models. The results showed that the LSM-ResNet (RMSE = 6.40, R-2 = 0.51) model outperformed the RF model in both the roots mean square error (RMSE) and coefficient of determination (R-2), and the training accuracy was significantly improved compared to RF (RMSE = 6.81, R-2 = 0.46). The trained LSM-ResNet model was used for SOM prediction in Xinxiang, a district of plain terrain in China. The prediction maps can be deemed an accurate reflection of the spatial variability of the SOM distribution.
引用
收藏
页数:19
相关论文
共 74 条
[21]  
Hengl T., 2004, International Journal of Applied Earth Observation and Geoinformation, V5, P97, DOI DOI 10.1016/J.JAG.2004.01.006
[22]   About regression-kriging: From equations to case studies [J].
Hengl, Tomislav ;
Heuvelink, Gerard B. M. ;
Rossiter, David G. .
COMPUTERS & GEOSCIENCES, 2007, 33 (10) :1301-1315
[23]   SoilGrids250m: Global gridded soil information based on machine learning [J].
Hengl, Tomislav ;
de Jesus, Jorge Mendes ;
Heuvelink, Gerard B. M. ;
Gonzalez, Maria Ruiperez ;
Kilibarda, Milan ;
Blagotic, Aleksandar ;
Shangguan, Wei ;
Wright, Marvin N. ;
Geng, Xiaoyuan ;
Bauer-Marschallinger, Bernhard ;
Guevara, Mario Antonio ;
Vargas, Rodrigo ;
MacMillan, Robert A. ;
Batjes, Niels H. ;
Leenaars, Johan G. B. ;
Ribeiro, Eloi ;
Wheeler, Ichsani ;
Mantel, Stephan ;
Kempen, Bas .
PLOS ONE, 2017, 12 (02)
[24]   An overview and comparison of machine-learning techniques for classification purposes in digital soil mapping [J].
Heung, Brandon ;
Ho, Hung Chak ;
Zhang, Jin ;
Knudby, Anders ;
Bulmer, Chuck E. ;
Schmidt, Margaret G. .
GEODERMA, 2016, 265 :62-77
[25]   Overview of the radiometric and biophysical performance of the MODIS vegetation indices [J].
Huete, A ;
Didan, K ;
Miura, T ;
Rodriguez, EP ;
Gao, X ;
Ferreira, LG .
REMOTE SENSING OF ENVIRONMENT, 2002, 83 (1-2) :195-213
[26]  
Jenny H., 1941, Factors of Soil Formation: a system of quantitative pedology
[27]   Soil organic matter protects US maize yields and lowers crop insurance payouts under drought [J].
Kane, Daniel A. ;
Bradford, Mark A. ;
Fuller, Emma ;
Oldfield, Emily E. ;
Wood, Stephen A. .
ENVIRONMENTAL RESEARCH LETTERS, 2021, 16 (04)
[28]  
Ketkar Nikhil, 2017, Introduction to Keras BT-Deep Learning with Python: a hands-on Introduction, P97, DOI [DOI 10.1007/978-1-4842-2766-4_7, DOI 10.1007/978-1-4842-2766-47]
[29]   ImageNet Classification with Deep Convolutional Neural Networks [J].
Krizhevsky, Alex ;
Sutskever, Ilya ;
Hinton, Geoffrey E. .
COMMUNICATIONS OF THE ACM, 2017, 60 (06) :84-90
[30]   Mapping the organic carbon stocks of surface soils using local spatial interpolator [J].
Kumar, Sandeep ;
La, Rattan .
JOURNAL OF ENVIRONMENTAL MONITORING, 2011, 13 (11) :3128-3135