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

UAV hyperspectral analysis of secondary salinization in arid oasis cotton fields: effects of FOD feature selection and SOA-RF

Secondary salinization is a crucial constraint on agricultural progress in arid regions. The specific mulching irrigation technique not only exacerbates secondary salinization but also complicates field-scale soil salinity monitoring. UAV hyperspectral remote sensing offers a monitoring method that is high-precision, high-efficiency, and short-cycle. In this study, UAV hyperspectral images were used to derive one-dimensional, textural, and three-dimensional feature variables using Competitive adaptive reweighted sampling (CARS), Gray-Level Co-occurrence Matrix (GLCM), Boruta Feature Selection (Boruta), and Brightness-Color-Index (BCI) with Fractional-order differentiation (FOD) processing. Additionally, three modeling strategies were developed (Strategy 1 involves constructing the model solely with the 20 single-band variable inputs screened by the CARS algorithm. In Strategy 2, 25 texture features augment Strategy 1, resulting in 45 feature variables for model construction. Strategy 3, building upon Strategy 2, incorporates six triple-band indices, totaling 51 variables used in the model's construction) and integrated with the Seagull Optimization Algorithm for Random Forest (SOA-RF) models to predict soil electrical conductivity (EC) and delineate spatial distribution. The results demonstrated that fractional order differentiation highlights spectral features in noisy spectra, and different orders of differentiation reveal different hidden information. The correlation between soil EC and spectra varies with the order. 1.9th order differentiation is proved to be the best order for constructing one-dimensional indices; although the addition of texture features slightly improves the accuracy of the model, the integration of the three-waveband indices significantly improves the accuracy of the estimation, with an R2 of 0.9476. In contrast to the conventional RF model, the SOA-RF algorithm optimizes its parameters thereby significantly improving the accuracy and model stability. The optimal soil salinity prediction model proposed in this study can accurately, non-invasively and rapidly identify excessive salt accumulation in drip irrigation under membrane. It is of great significance to improve the growing conditions of cotton, increase the cotton yield, and promote the sustainable development of Xinjiang's agricultural economy, and also provides a reference for the prevention and control of regional soil salinization.

Optimization of water reuse and modelling by saline composition with nanoparticles based on machine learning architectures

Water is a necessary resource that enables the existence of all life forms, including humans. Freshwater usage has become increasingly necessary in recent years. Facilities for treating seawater are less dependable and effective. Deep learning methods have the ability to improve salt particle analysis in saltwater's accuracy and efficiency, which will enhance the performance of water treatment plants. This research proposes a novel technique in optimization of water reuse with nanoparticle analysis based on machine learning architecture. Here, the optimization of water reuse is carried out based on nanoparticle solar cell for saline water treatment and the saline composition has been analyzed using a gradient discriminant random field. Experimental analysis is carried out in terms of specificity, computational cost, kappa coefficient, training accuracy, and mean average precision for various tunnelling electron microscope (TEM) image datasets. The bright-field TEM (BF-TEM) dataset attained a specificity of 75%, kappa coefficient of 44%, training accuracy of 81%, and mean average precision of 61%, whereas the annular dark-field scanning TEM (ADF-STEM) dataset produced specificity of 79%, kappa coefficient of 49%, training accuracy of 85%, and mean average precision of 66% as compared with the existing artificial neural network (ANN) approach.

Estimation of soil copper content based on fractional-order derivative spectroscopy and spectral characteristic band selection

Hyperspectral remote sensing is a rapid and nondestructive method to estimate the soil copper content. However, before establishing the spectral estimation model, it is crucial to preprocess the hyperspectral data to eliminate noise and highlight the spectral response characteristics of copper. The two commonly used spectral preprocessing approaches, i.e., the first- and second-order derivatives, may not provide sufficient information on the copper in the soil spectra. Therefore, this study investigates the potential of using the fractional-order derivative (FOD) of the spectra (FOD spectra) for estimating the soil copper content. A total of 170 soil samples were collected, and the soil reflectance spectra were measured outdoors using an ASD FieldSpec3 portable spectrometer. The soil copper content was obtained by chemical analysis in the laboratory. A quantitative estimation model of the soil copper content was established by combining the FOD spectra with different orders and using the partial least squares (PLS) method. The results revealed that the accuracy and prediction ability of the models using different orders of the FOD spectra varied significantly. The model using the 0.8-order FOD spectra performed the best, and the coefficient of determination (R²) and the ratio of the performance to deviation (RPD) of the validation set were 0.6416 and 1.63, respectively. The performance of the model using three characteristic bands (2365.5 nm and 2375.5 nm of the 0.9-order derivatives and 864.5 nm of the 1.1-order derivatives) provided significantly better performance than utilizing all wavelength bands from 400 to 2400 nm. This model provided the optimum predictive ability (R²: 0.6552 vs. 0.6416, RPD: 1.65 vs. 1.63) and was straightforward, requiring only three bands. These results show that it is feasible and practical to establish an accurate and rapid estimation model of the soil copper content using FOD spectra.

Integration of Geostatistical and Sentinal-2AMultispectral Satellite Image Analysis for Predicting Soil Fertility Condition in Drylands

For modelling and predicting soil indicators to be fully operational and facilitate decision-making at any spatial level, there is a requirement for precise spatially referenced soil information to be available as input data. This paper focuses on showing the capacity of Sentinal-2A(S2A) multispectral imaging to predict soil properties and provide geostatistical analysis (ordinary kriging) for mapping dry land soil fertility conditions (SOCs). Conditioned Latin hypercube sampling was used to select the representative sampling sites within the study area. To achieve the objectives of this work, 48 surface soil samples were collected from the western part of Matrouh Governorate, Egypt, and pH, soil organic matter (SOM), available nitrogen (N), phosphorus (P), and potassium (K) levels were analyzed. Multilinear regression (MLR) was used to model the relationship between image reflectance and laboratory analysis (of pH, SOM, N, P, and K in the soil), followed by mapping the predicted outputs using ordinary kriging. Model fitting was achieved by removing variables according to the confidence level (95%).Around 30% of the samples were randomly selected to verify the validity of the results. The randomly selected samples helped express the variety of the soil characteristics from the investigated area. The predicted values of pH, SOM, N, P, and K performed well, with R2 values of 0.6, 0.7, 0.55, 0.6, and 0.92 achieved for pH, SOM, N, P, and K, respectively. The results from the ArcGIS model builder indicated a descending fertility order within the study area of: 70% low fertility, 22% moderate fertility, 3% very low fertility, and 5% reference terms. This work evidence that which can be predicted from S2A images and provides a reference for soil fertility monitoring in drylands. Additionally, this model can be easily applied to environmental conditions similar to those of the studied area.