Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network

Jiang, Hong; Rusuli, Yusufujiang; Amuti, Tureniguli; He, Qinming

doi:10.1080/01431161.2018.1513180

Cited by 64 publications

(38 citation statements)

References 72 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…(c) Support Vector Regression Support Vector Machine, proposed by Cortes and Vapnik in 1995, has been widely used because of its strength in dealing with linearly high-dimensional and nonseparable datasets. Hyperplanes in SVM are decision boundaries that help to classify the data points, and support vectors are data points that are closer to the hyperplane and influence the position and orientation of the hyperplane [51]. The objective of the SVM is to find an optimal hyperplane (has the maximum margin between support vectors) in feature space for classification problems.…”

Section: Brief Introduction Of Machine Learning Algorithmsmentioning

confidence: 99%

Benchmarking Machine Learning Algorithms for Instantaneous Net Surface Shortwave Radiation Retrieval Using Remote Sensing Data

Ying

2019

Remote Sensing

View full text Add to dashboard Cite

Net surface shortwave radiation (NSSR) is one of the most important fundamental parameters in various land processes. Benefiting from its efficient nonlinear fitting ability, machine learning algorithms have a great potential in the retrieval of NSSR. However, few studies have explored the level of accuracy that machine learning algorithms can reach for different land covers on the worldwide scale and what the optimal independent variables are in the machine learning-based NSSR model. To guide the use of machine learning algorithms correctly in the retrieval of NSSR, it is necessary to give a comprehensive analysis from algorithm complexity, accuracy, and other aspects. In this study, three classic machine learning algorithms, including Random Forest (RF), Artificial Neural Network (ANN), and Support Vector Regression (SVR), were built well to estimate instantaneous NSSR with optimal hyperparameters by elaborately selecting different independent variables, including top of atmosphere (TOA) channel spectral reflectance, geographic parameters, surface information, and atmosphere conditions. Global FLUXNET in situ measurements throughout 2014 were used to validate the accuracies of retrieved NSSR over various land cover types. The root mean square error (RMSE) is below 55 W/m2, and the distributions of error histogram are also similar. Approximately 50% of absolute error were within 25 W/m2. There was a performance difference of NSSR estimations in various surface types, and the performance of three machine learning methods in a specific surface type was also different. However, the RF method may be considered as the optimal methodology to retrieve NSSR from MODIS data, owing to its relatively better precision and concise hyperparameter-tuned process. The importance analysis of the proposed independent variables of NSSR retrieval shows that the introduction of geographic information can effectively reduce the error of NSSR retrieval, and surface information and atmosphere information are not necessary. It was also found that a combination of geographic information and blue band TOA reflectance already have a pretty good accuracy in NSSR retrieval, which implies there is a possibility to transfer our NSSR model to other satellite sensors, especially with insufficient channels. In a word, the NSSR model with machine learning algorithms would be an efficient, concise, and general method in the future.

show abstract

Section: Brief Introduction Of Machine Learning Algorithmsmentioning

confidence: 99%

Benchmarking Machine Learning Algorithms for Instantaneous Net Surface Shortwave Radiation Retrieval Using Remote Sensing Data

Ying

2019

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…However, there are still three aspects that need to be further studied. First, the precision needs to be further improved, and the contributions of different data sources and nonlinear modeling methods to the precision will continue to be explored [59,60]. Additionally, the driving factors and formation mechanism of soil salinization must be elucidated to prevent this problem [61,62].…”

mentioning

confidence: 99%

A Harmonious Satellite-Unmanned Aerial Vehicle-Ground Measurement Inversion Method for Monitoring Salinity in Coastal Saline Soil

Zhang¹,

Zhao²

2019

Remote Sensing

View full text Add to dashboard Cite

Soil salinization adversely impacts crop growth and production, especially in coastal areas which experience serious soil salinization. Therefore, rapid and accurate monitoring of the salinity and distribution of coastal saline soil is crucial. Representative areas of the Yellow River Delta (YRD)—the Hekou District (the core test area with 140 sampling points) and the Kenli District (the verification area with 69 sampling points)—were investigated. Ground measurement data, unmanned aerial vehicle (UAV) multispectral imagery and Sentinel-2A multispectral imagery were used as the data sources and a satellite-UAV-ground integrated inversion of the coastal soil salinity was performed. Correlation analyses and multiple regression methods were used to construct an accurate model. Then, a UAV-based inversion model was applied to the satellite imagery with reflectance normalization. Finally, the spatial and temporal universality of the UAV-based inversion model was verified and the soil salinity inversion results were obtained. The results showed that the green, red, red-edge and near-infrared bands were significantly correlated with soil salinity and the spectral parameters significantly improved this correlation; hence, the model is more effective upon combining spectral parameters with sensitive bands, with modeling precision and verification precision of the best model being 0.743 and 0.809, respectively. The reflectance normalization yielded good results. These findings proved that applying the UAV-based model to reflectance normalized Sentinel-2A images produces results that are consistent with the actual situation. Moreover, the inversion results effectively reflect the distributions characteristic of the soil salinity in the core test area and the study area. This study integrated the advantages of satellite, UAV and ground methods and then proposed a method for the inversion of the salinity of coastal saline soils at different scales, which is of great value for real-time, rapid and accurate soil salinity monitoring applications.

show abstract

“…Jiang et al monitored soil salinity by integrating multiple biophysical indicators with support vector machine (SVM) and artificial neural network (ANN) regression algorithms. The results demonstrate that the SVM regression algorithm outperforms the ANN algorithm in monitoring soil salinity [4]. Farifteh used the ANN algorithm and the PLSR algorithm to estimate the soil salinity.…”

Section: Introductionmentioning

confidence: 94%

“…Typically, salt soil and alkaline soil are mixed; hence, they are collectively referred to as salt-affected soil. Salt-affected soil is a prominent ecological and environmental problem in the world's dry farming areas [2][3][4]. The total area of the salt-affected soil resources in China is approximately 9.9 million km 2 , which are mainly distributed in the northeast plain, the arid and semi-arid areas in the northwest, the Huang-Huai-Hai plain, and the eastern coastal areas.…”

Section: Introductionmentioning

confidence: 99%

“…The regularization can reduce the influence of collinearity by adding offset to the optimization function [30]. With the deep research of machine learning methods, the results are uneven and many studies in which machine learning methods are used to estimate soil salinity have been reported [4,21,24,[32][33][34]. Jiang et al monitored soil salinity by integrating multiple biophysical indicators with support vector machine (SVM) and artificial neural network (ANN) regression algorithms.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Performance Comparison of Machine Learning Algorithms for Estimating the Soil Salinity of Salt-Affected Soil Using Field Spectral Data

et al. 2019

View full text Add to dashboard Cite

Salt-affected soil is a prominent ecological and environmental problem in dry farming areas throughout the world. China has nearly 9.9 million km2 of salt-affected land. The identification, monitoring, and utilization of soil salinization have become important research topics for promoting sustainable progress. In this paper, using field-measured spectral data and soil salinity parameter data, through analysis and transformation of spectral data, five machine learning models, namely, random forest regression (RFR), support vector regression (SVR), gradient-boosted regression tree (GBRT), multilayer perceptron regression (MLPR), and least angle regression (Lars) are compared. The following performance measures of each model were evaluated: the collinear problems, handling data noise, stability, and the accuracy. In terms of these four aspects, the performance of each model on estimating soil salinity is evaluated. The results demonstrate that among the five models, RFR has the best performance in dealing with collinearity, RFR and MLPR have the best performance in dealing with data noise, and the SVR model is the most stable. The Lars model has the highest accuracy, with a determination coefficient (R2) of 0.87, ratio of performance to deviation (RPD) of 2.67, root mean square error (RMSE) of 0.18, and mean absolute percentage error (MAPE) of 0.11. Then, the comprehensive comparison and analysis of the five models are carried out, and it is found that the comprehensive performance of RFR model is the best; hence, this method is most suitable for estimating soil salinity using hyperspectral data. This study can provide a reference for the selection of regression methods in subsequent studies on estimating soil salinity using hyperspectral data.

show abstract

Quantitative assessment of soil salinity using multi-source remote sensing data based on the support vector machine and artificial neural network

Cited by 64 publications

References 72 publications

Benchmarking Machine Learning Algorithms for Instantaneous Net Surface Shortwave Radiation Retrieval Using Remote Sensing Data

Benchmarking Machine Learning Algorithms for Instantaneous Net Surface Shortwave Radiation Retrieval Using Remote Sensing Data

A Harmonious Satellite-Unmanned Aerial Vehicle-Ground Measurement Inversion Method for Monitoring Salinity in Coastal Saline Soil

Performance Comparison of Machine Learning Algorithms for Estimating the Soil Salinity of Salt-Affected Soil Using Field Spectral Data

Contact Info

Product

Resources

About