A New Methodology of Soil Salinization Degree Classification by Probability Neural Network Model Based on Centroid of Fractional Lorenz Chaos Self-Synchronization Error Dynamics

Tian, Anmin; Fu, Chengbiao; Yau, Her‐Terng; Su, Xiao-Yi; Xiong, Hui

doi:10.1109/tgrs.2019.2940592

Cited by 13 publications

(11 citation statements)

References 39 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Moreover, this zone is close to the 102th Regiment of Xinjiang, and there is relatively low vegetation coverage here compared with I Zone. 3 heavy human interference zone (III Zone), this zone has been reclaimed into two plantations with 3.5 m row spacing and 1.5 m plant spacing.…”

Section: Study Zonementioning

confidence: 99%

“…However, due to the interference of various factors such as topography, environment, geology, human activity, and climate, the primary and secondary salinization of soil has become an international ecological and environmental problem [1,2], it mainly occurs in arid and semi-arid regions where precipitation is scarce and water evaporation is rapid, such as China, Pakistan, Israel, and India. Salinized soil will reduce soil fertility and hinder the growth of crops [3,4], further restricting the development of the agricultural economy, and its damage to the social economy and ecosystem has been concerned. Therefore, the rapid detection of soil salinization information has great guiding significance for salinization management and regional ecological environmental protection [5,6].…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Estimation of Salinity Content in Different Saline-Alkali Zones Based on Machine Learning Model Using FOD Pretreatment Method

Tian

Zhu

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

Soil salinization is a global ecological and environmental problem in arid and semi-arid areas that can be ameliorated via soil management, visible-near infrared-shortwave infrared (VNIR-SWIR) spectroscopy can be adapted to rapidly monitor soil salinity content. This study explored the potential of Grünwald–Letnikov fractional-order derivative (FOD), feature band selection methods, nonlinear partial least squares regression (PLSR), and four machine learning models to estimate the soil salinity content using VNIR-SWIR spectra. Ninety sample points were field scanned with VNIR-SWR and soil samples (0–20 cm) were obtained at the time of scanning. The samples points come from three zones representing different intensities of human interference (I, II, and III Zones) in Fukang, Xinjiang, China. Each zone contained thirty sample points. For modeling, we firstly adopted FOD (with intervals of 0.1 and range of 0–2) as a preprocessing method to analyze soil hyperspectral data. Then, four sets of spectral bands (R-FOD-FULL indicates full band range, R-FOD-CC5 bands that met a 0.05 significance test, R-FOD-CC1 bands that met a 0.01 significance test, and R-FOD-CC1-CARS represents CC1 combined with competitive adaptive reweighted sampling) were selected as spectral input variables to develop the estimation model. Finally, four machine learning models, namely, generalized regression neural network (GRNN), extreme learning machine (ELM), random forest (RF), and PLSR, to estimate soil salinity. Study results showed that (1) the heat map of correlation coefficient matrix between hyperspectral data and salinity indicated that FOD significantly improved the correlation. (2) The characteristic band variables extracted and used by R-FOD-CC1 were fewer in number, and redundancy between bands smaller than R-FOD-FULL and R-FOD-CC5, thus estimation accuracy of R-FOD-CC1 was higher than R-FOD-CC5 or R-FOD-FULL. A high prediction accuracy was achieved with a less complex calculation. (3) The GRNN model yielded the best salinity estimation in all three zones compared to ELM, BPNN, RF, and PLSR on the whole, whereas, the RF model had the worst estimation effect. The R-FOD-CC1-CARS-GRNN model yielded the best salinity estimation in I Zone with R2, RMSE and RPD of 0.7784, 1.8762, and 2.0568, respectively. The fractional order was 1.5 and estimation performance was great. The optimal model for predicting soil salinity in II and III Zone was, also, R-FOD-CC1-CARS-GRNN (R2 = 0.7912, RMSE = 3.4001, and RPD = 1.8985 in II Zone; R2 = 0.8192, RMSE = 6.6260, and RPD = 1.8190 in III Zone), with the fractional order of 1.7- and 1.6-, respectively, and the estimation performance were all fine. (4) The characteristic bands selected by the best model in I, II, and III Zones were 8, 9, and 11, respectively, which account for 0.45%, 0.51%, and 0.63%% of the full bands. This approach reduces the number of modeled band variables and simplifies the model structure.

show abstract

Section: Study Zonementioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Estimation of Salinity Content in Different Saline-Alkali Zones Based on Machine Learning Model Using FOD Pretreatment Method

Tian

Zhu

et al. 2021

Remote Sensing

Self Cite

View full text Add to dashboard Cite

show abstract

“…In addition, the order choice of FOD is not limited to integers, and the order of operations is expanded [33][34][35][36], which has a wider selection range and higher degree of freedom than integer-order derivatives. Meanwhile, many systems belong to the fractionalorder, and the integer-order derivative model is used to describe it, which will lead to a large deviation between the model and the actual result, and the system simulation and prediction cannot be performed well, it also ignores the authenticity of the system to a certain extent.…”

Section: Comparison Of the Fractional-order Derivative And Integer-or...mentioning

confidence: 99%

Study on the Pretreatment of Soil Hyperspectral and Na+ Ion Data under Different Degrees of Human Activity Stress by Fractional-Order Derivatives

et al. 2021

Self Cite

View full text Add to dashboard Cite

Soluble salts in saline soil often exist in the form of salt base ions, and excessive water-soluble base ions can harm plant growth. As one of the water-soluble base ions, Na+ ion, is the main indicator of the degree of soil salinization. The pretreatment of visible, near infrared and short-wave infrared (VNIR-SWIR) spectroscopy data is the key to establishing a high-precision inversion model, and a proper pretreatment method can fully extract the effective information hidden in the hyperspectral data. Meanwhile, different degrees of human activity stress will have an impact on the ecological environment of oases. However, there are few comparative analyses of the data pretreatment effects for soil water-soluble base ions on the environment under different human interference conditions. Therefore, in this study, the difference in the degree of soil disturbance caused by human activities was used as the basis for dividing the experimental area into lightly disturbed area (Area A), moderately disturbed area (Area B) and severely disturbed zone (Area C). The Grünwald-Letnikov fractional-order derivative (FOD) was used to preprocess the VNIR-SWIR spectroscopic data measured by a FieldSpec®3Hi-Res spectrometer, which could fully extract the useful information hidden in the FOD of the VNIR-SWIR spectroscopy results and avoid the loss of information caused by the traditional integer-order derivative (1.0-order, 2.0-order) pretreatment. The spectrum pretreatment was composed of five transform spectra (R,R, 1/R, lgR, 1/lgR) and 21 FOD methods (step size is 0.1, derivative range is from 0.0- to 2.0-order). In addition, this manuscript compares and analyzes the pretreatment advantages between fractional-order and integer-order. The main results were as follows: (1) Grünwald-Letnikov FOD can reveal the nonlinear characteristics and variation laws of the field hyperspectral of saline soil, namely, due to the continuous performance of the order selection, the FOD accurately depicts the details of spectral changes during the derivation process, and improves the resolution between the peaks of the hyperspectral spectrum. (2) There is a big difference in the shape of the correlation coefficient curve between the original hyperspectral and Na+ at different FOD. The correlation coefficient curve has a clear outline in rang of the 0.0- to 0.6-order, and the change trend is gentle, which presents a certain gradual form. With the continuous increase of the order of the FOD, the change range of the correlation coefficient curve is gradually increased, and the fluctuation is greater between the 1.0-order and the 2.0-order. (3) Regardless of the transformation spectrum and different interference regions, the improvement effect of the FOD on the correlation between hyperspectral and Na+ is significantly better than that of the integer-order derivative. Comparative analysis shows that he percentage of increase of the former is more than 3%, and the highest is more than 17%.

show abstract

“…The almost continuous spectral curve provides excellent conditions for accurate ground object classification. Thus, hyperspectral images (HSIs) have attracted extensive attention in many fields, such as agricultural crop growth, environmental monitoring [2,3], urban planning, military target monitoring, and other fields [4][5][6]. However, some interference factors, including equipment and transmission errors, light conditions, air components, and their jointly presented interferences, cause spectral features to be trapped in a state of high-dimensional non-linearity, increasing the difficulty of carrying out effective objects recognition.…”

Section: Introductionmentioning

confidence: 99%

Lightweight Multilevel Feature Fusion Network for Hyperspectral Image Classification

Liang

Huai

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Hyperspectral images (HSIs), acquired as a 3D data set, contain spectral and spatial information that is important for ground–object recognition. A 3D convolutional neural network (3DCNN) could therefore be more suitable than a 2D one for extracting multiscale neighborhood information in the spectral and spatial domains simultaneously, if it is not restrained by mass parameters and computation cost. In this paper, we propose a novel lightweight multilevel feature fusion network (LMFN) that can achieve satisfactory HSI classification with fewer parameters and a lower computational burden. The LMFN decouples spectral–spatial feature extraction into two modules: point-wise 3D convolution to learn correlations between adjacent bands with no spatial perception, and depth-wise convolution to obtain local texture features while the spectral receptive field remains unchanged. Then, a target-guided fusion mechanism (TFM) is introduced to achieve multilevel spectral–spatial feature fusion between the two modules. More specifically, multiscale spectral features are endowed with spatial long-range dependency, which is quantified by central target pixel-guided similarity measurement. Subsequently, the results obtained from shallow to deep layers are added, respectively, to the spatial modules, in an orderly manner. The TFM block can enhance adjacent spectral correction and focus on pixels that actively boost the target classification accuracy, while performing multiscale feature fusion. Experimental results across three benchmark HSI data sets indicate that our proposed LMFN has competitive advantages, in terms of both classification accuracy and lightweight deep network architecture engineering. More importantly, compared to state-of-the-art methods, the LMFN presents better robustness and generalization.

show abstract

A New Methodology of Soil Salinization Degree Classification by Probability Neural Network Model Based on Centroid of Fractional Lorenz Chaos Self-Synchronization Error Dynamics

Cited by 13 publications

References 39 publications

Estimation of Salinity Content in Different Saline-Alkali Zones Based on Machine Learning Model Using FOD Pretreatment Method

Estimation of Salinity Content in Different Saline-Alkali Zones Based on Machine Learning Model Using FOD Pretreatment Method

Study on the Pretreatment of Soil Hyperspectral and Na+ Ion Data under Different Degrees of Human Activity Stress by Fractional-Order Derivatives

Lightweight Multilevel Feature Fusion Network for Hyperspectral Image Classification

Contact Info

Product

Resources

About