Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas

Guo, Ping; Wu, Wei; Sheng, Qing-Kai; Li, Mao-Fen; Liu, Hongbin; Zheng-yin, Wang

doi:10.1007/s10705-013-9566-9

Cited by 52 publications

(18 citation statements)

References 49 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The BPNN model can also incorporates the need to adjust activation functions (i.e., the sigmoid function) (Equation (7)), number of neurons ( n ) and weights (i.e., input weights

and output weights

). The input of the hidden layer (Equation (5)) and that of the output layer (Equation (6)) are calculated as follows [ 46 ]:

where

and

are the inputs of the hidden layer and the output layer, respectively;

is the variable of the

th input node; and

and

are the bias values of the hidden layer and the output layer, respectively. The sigmoid function

is applied as follows:

…”

Section: Methodsmentioning

confidence: 99%

Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale

Song

Zhao

et al. 2018

Sensors

View full text Add to dashboard Cite

Rapid acquisition of the spatial distribution of soil nutrients holds great implications for farmland soil productivity safety, food security and agricultural management. To this end, we collected 1297 soil samples and measured the content of soil total nitrogen (TN), soil available phosphorus (AP) and soil available potassium (AK) in Zengcheng, north of the Pearl River Delta, China. Hyperspectral remote sensing images (115 bands) of the Chinese Environmental 1A satellite were used as auxiliary variables and dimensionality reduction was performed using Pearson correlation analysis and principal component analysis. The TN, AP and AK of soil were predicted in the study area based on auxiliary variables after dimensionality reduction, along with stepwise linear regression (SLR), support vector machine (SVM), random forest (RF) and back-propagation neural network (BPNN) models; 324 independent points were used to verify the predictive performance. The BPNN model, which demonstrated the best predictive accuracy among all methods, combined ordinary kriging (OK) with mapping the spatial variations of soil nutrients. Results show that the BPNN model with double hidden layers had better predictive accuracy for soil TN (root mean square error (RMSE) = 0.409 mg kg−1, R2 = 44.24%), soil AP (RMSE = 40.808 mg kg−1, R2 = 42.91%) and soil AK (RMSE = 67.464 mg kg−1, R2 = 48.53%) compared with the SLR, SVM and RF models. The back propagation neural network-ordinary kriging (BPNNOK) model showed the best predictive results of soil TN (RMSE = 0.292 mg kg−1, R2 = 68.51%), soil AP (RMSE = 29.62 mg kg−1, R2 = 69.30%) and soil AK (RMSE = 49.67 mg kg−1 and R2 = 70.55%), indicating the best fitting ability between hyperspectral remote sensing bands and soil nutrients. According to the spatial mapping results of the BPNNOK model, concentrations of soil TN (north-central), soil AP (central and southwest) and soil AK (central and southeast) were respectively higher in the study area. The most important bands (464–517 nm) for soil TN (b10, b14, b20 and b21), soil AP (b3, b19 and b22) and soil AK (b4, b11, b12 and b25) exhibited the best response and sensitivity according to the SLR, SVM, RF and BPNN models. It was concluded that the application of hyperspectral images (visible-near-infrared data) with BPNNOK model was found to be an efficient method for mapping and monitoring soil nutrients at the regional scale.

show abstract

“…The BPNN model can also incorporates the need to adjust activation functions (i.e., the sigmoid function) (Equation (7)), number of neurons ( n ) and weights (i.e., input weights

and output weights

). The input of the hidden layer (Equation (5)) and that of the output layer (Equation (6)) are calculated as follows [ 46 ]:

where

and

are the inputs of the hidden layer and the output layer, respectively;

is the variable of the

th input node; and

and

are the bias values of the hidden layer and the output layer, respectively. The sigmoid function

is applied as follows:

…”

Section: Methodsmentioning

confidence: 99%

Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale

Song

Zhao

et al. 2018

Sensors

View full text Add to dashboard Cite

show abstract

“…However, all these methods have considered topography as a necessary influential factor. In general, terrain attributes are pivotal factors that affect the SOC stock in areas with complex and varied topography, such as mountainous regions [98,99]. However, in plains or small-scaled areas, the spatial distribution of terrain is flat and has indistinctive variation.…”

Section: Effect Of Terrain Factors On Soc Predictionmentioning

confidence: 99%

Prediction of Soil Organic Carbon based on Landsat 8 Monthly NDVI Data for the Jianghan Plain in Hubei Province, China

et al. 2019

View full text Add to dashboard Cite

High-precision maps of soil organic carbon (SOC) are beneficial for managing soil fertility and understanding the global carbon cycle. Digital soil mapping plays an important role in efficiently obtaining the spatial distribution of SOC, which contributes to precision agriculture. However, traditional soil-forming factors (i.e., terrain or climatic factors) have weak variability in low-relief areas, such as plains, and cannot reflect the spatial variation of soil attributes. Meanwhile, vegetation cover hinders the acquisition of the direct information of farmland soil. Thus, useful environmental variables should be utilized for SOC prediction and the digital mapping of such areas. SOC has an important effect on crop growth status, and remote sensing data can record the apparent spectral characteristics of crops. The normalized difference vegetation index (NDVI) is an important index reflecting crop growth and biomass. This study used NDVI time series data rather than traditional soil-forming factors to map SOC. Honghu City, located in the middle of the Jianghan Plain, was selected as the study region, and the NDVI time series data extracted from Landsat 8 were used as the auxiliary variables. SOC maps were estimated through stepwise linear regression (SLR), partial least squares regression (PLSR), support vector machine (SVM), and artificial neural network (ANN). Ordinary kriging (OK) was used as the reference model, while root mean square error of prediction (RMSE P ) and coefficient of determination of prediction (R 2 P ) were used to evaluate the model performance. Results showed that SOC had a significant positive correlation in July and August (0.17, 0.29) and a significant negative correlation in January, April, and December (−0.23, −0.27, and −0.23) with NDVI time series data. The best model for SOC prediction was generated by ANN, with the lowest RMSE P of 3.718 and highest R 2 P of 0.391, followed by SVM (RMSE P = 3.753, R 2 P = 0.361) and PLSR (RMSE P = 4.087, R 2 P = 0.283). The SLR model was the worst model, with the lowest R 2 P of 0.281 and highest RMSE P of 3.930. ANN and SVM were better than OK (RMSE P = 3.727, R 2 P = 0.372), whereas PLSR and SLR were worse than OK. Moreover, the prediction results using single-data NDVI or short time series NDVI showed low accuracy. The effect of the terrain factor on SOC prediction represented unsatisfactory results. All these results indicated that the NDVI time series data can be used for SOC mapping in plain areas and that the ANN model can maximally extract additional associated information between NDVI time series data and SOC. This study presented an effective method to overcome the selection of auxiliary variables for digital soil mapping in plain areas when the soil was covered with vegetation. This finding indicated that the time series characteristics of NDVI were conducive for predicting SOC in plains.

show abstract

“…Each layer consists of a series of parallel processing elements (neurons or nodes). Each node in a layer is linked to all nodes in the next layer ( Guo et al, 2013 ).…”

Section: Methodsmentioning

confidence: 99%

PredictingPinus monophyllaforest cover in the Baja California Desert by remote sensing

Escobar-Flores

López-Sánchez

Sandoval

et al. 2018

PeerJ

View full text Add to dashboard Cite

The Californian single-leaf pinyon (Pinus monophylla var. californiarum), a subspecies of the single-leaf pinyon (the world’s only one-needled pine), inhabits semi-arid zones of the Mojave Desert (southern Nevada and southeastern California, US) and also of northern Baja California (Mexico). This tree is distributed as a relict subspecies, at elevations of between 1,010 and 1,631 m in the geographically isolated arid Sierra La Asamblea, an area characterized by mean annual precipitation levels of between 184 and 288 mm. The aim of this research was (i) to estimate the distribution of P. monophylla var. californiarum in Sierra La Asamblea by using Sentinel-2 images, and (ii) to test and describe the relationship between the distribution of P. monophylla and five topographic and 18 climate variables. We hypothesized that (i) Sentinel-2 images can be used to predict the P. monophylla distribution in the study site due to the finer resolution (×3) and greater number of bands (×2) relative to Landsat-8 data, which is publically available free of charge and has been demonstrated to be useful for estimating forest cover, and (ii) the topographical variables aspect, ruggedness and slope are particularly important because they represent important microhabitat factors that can determine the sites where conifers can become established and persist. An atmospherically corrected a 12-bit Sentinel-2A MSI image with 10 spectral bands in the visible, near infrared, and short-wave infrared light region was used in combination with the normalized differential vegetation index (NDVI). Supervised classification of this image was carried out using a backpropagation-type artificial neural network algorithm. Stepwise multiple linear binominal logistical regression and Random Forest classification including cross validation were used to model the associations between presence/absence of P. monophylla and the five topographical and 18 climate variables. Using supervised classification of Sentinel-2 satellite images, we estimated that P. monophylla covers 6,653 ± 319 ha in the isolated Sierra La Asamblea. The NDVI was one of the variables that contributed most to the prediction and clearly separated the forest cover (NDVI > 0.35) from the other vegetation cover (NDVI < 0.20). Ruggedness was the most influential environmental predictor variable, indicating that the probability of occurrence of P. monophylla was greater than 50% when the degree of ruggedness terrain ruggedness index was greater than 17.5 m. The probability of occurrence of the species decreased when the mean temperature in the warmest month increased from 23.5 to 25.2 °C. Ruggedness is known to create microclimates and provides shade that minimizes evapotranspiration from pines in desert environments. Identification of the P. monophylla stands in Sierra La Asamblea as the most southern populations represents an opportunity for research on climatic tolerance and community responses to climate variability and change.

show abstract

Prediction of soil organic matter using artificial neural network and topographic indicators in hilly areas

Cited by 52 publications

References 49 publications

Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale

Predicting Spatial Variations in Soil Nutrients with Hyperspectral Remote Sensing at Regional Scale

Prediction of Soil Organic Carbon based on Landsat 8 Monthly NDVI Data for the Jianghan Plain in Hubei Province, China

PredictingPinus monophyllaforest cover in the Baja California Desert by remote sensing

Contact Info

Product

Resources

About