An accurate estimation of soil electrical conductivity (EC) using hyperspectral techniques is of great significance for understanding the spatial distribution of solutes and soil salinization. Although spectral transformation has been widely used in data pre-processing, the performance of different pre-processing techniques (or combination methods) on different models of the same data set is still ambiguous. Moreover, extremely randomized trees (ERT) and light gradient boosting machine (LightGBM) models are new learning algorithms with good generalization performance (soil moisture and above-ground biomass), but are less studied in estimating soil salinity in the visible and near-infrared spectra. In this study, 130 soil EC data, soil measured hyperspectral data, topographic factors, conventional salinity indices such as Salinity Index 1, and two-band (2D) salinity indices such as ratio indices, were introduced. The five spectral pre-processing methods of standard normal variate (SNV), standard normal variate and detrend (SNV-DT), inverse (1/OR) (OR is original spectrum), inverse-log (Log(1/OR) and fractional order derivative (FOD) (range 0–2, with intervals of 0.25) were performed. A gradient boosting machine (GBM) was used to select sensitive spectral parameters. Models (extreme gradient boosting (XGBoost), LightGBM, random forest (RF), ERT, classification and regression tree (CART), and ridge regression (RR)) were used for inversion soil EC and model validation. The results reveal that the two-dimensional correlation coefficient highlighted EC more effectively than the one-dimensional. Under SNV and the second order derivative, the two-dimensional correlation coefficient increased by 0.286 and 0.258 compared to the one-dimension, respectively. The 13 characteristic factors of slope, NDI, SI-T, RI, profile curvature, DOA, plane curvature, SI (conventional), elevation, Int2, aspect, S1 and TWI provided 90% of the cumulative importance for EC using GBM. Among the six machine models, the ERT model performed the best for simulation (R² = 0.98) and validation (R² = 0.96). The ERT model showed the best performance among the EC estimation models from the reference data. The kriging map based on the ERT simulation showed a close relationship with the measured data. Our study selected the effective pre-processing methods (SNV and the 2 order derivative) using one- and two-dimensional correlation, 13 important factors and the ERT model for EC hyperspectral inversion. This provides a theoretical support for the quantitative monitoring of soil salinization on a larger scale using remote sensing techniques.

Diisocyanates are highly reactive compounds with two functional isocyanate groups. The exposure of diisocyanates is associated with severely adverse health effects, such as asthma, inflammation in the respiratory tract, and cancer. The hydrolysis product from diisocyanates to related diamines is also a potential carcinogen. Here, we developed an effective, accurate, and precise method for simultaneous determination of residual diisocyanates and related diamines in biodegradable mulch films, based on N-ethoxycarbonylation derivatization and gas chromatography-mass spectrometry. The method development included the optimization of ultrasonic hydrolysis and extraction, screening of N-ethoxycarbonylation conditions with ethyl chloroformate, evaluation of the diamines degradation, and analysis of the fragmentation mechanisms. Under the optimum experimental conditions, good linearity was observed with R² > 0.999. The extraction recoveries were found in the range of 93.9–101.2% with repeatabilities and reproducibilities in 0.89–8.12% and 2.12–10.56%, respectively. The limits of detection ranged from 0.0025 to 0.057 µg/mL. The developed method was applied to commercial polybutylene adipate co-terephthalate (PBAT) biodegradable mulch film samples for analysis of the diverse residual diisocyanates and related diamine additives. The components varied greatly among the sample from different origin. Overall, this study provides a reliable method for assessing safety in biodegradable mulch films.

Fertilization decisions depend on the measurement of a large set of soil fertility indicators, usually through laboratory determination, which is costly and time-consuming. Visible and near-infrared (vis-NIR) spectroscopy combined with machine learning can simultaneously predict various soil fertility indicators. Spectroscopy is inherently less accurate than direct laboratory determination. However, in many fertilization recommendation contexts, farmers mainly fertilize according to classified fertility indicators, rather than by continuous soil property values. These classes have defined limits of property values. We hypothesized that the additional inaccuracy from spectroscopy may not be important for properties grouped into classes. This study compared the indirect and direct prediction of soil fertility classes. Indirectly, by (1) using vis-NIR spectra with machine learning to predict 20 soil fertility indicators (pH, soil organic matter (SOM), cation exchange capacity (CEC), total nitrogen (TN), total phosphorus (TP), total potassium (TK), alkali-hydrolyzable nitrogen (AN), available phosphorus (AP), available potassium (AK), calcium (Ca), magnesium (Mg), silicon (Si), sulfur (S), boron (B), iron (Fe), manganese (Mn), copper (Cu), Zinc (Zn), molybdenum (Mo) and chlorine (Cl)) and (2) allocating the indicators to soil fertility classes. Directly, by predicting soil fertility classes directly from vis-NIR spectra using machine learning. The prediction accuracy of these two methods were compared and the accuracies needed for the acceptable class allocation of the fertility indicators were determined. The example dataset is a soil spectral library from the Guizhou Province, southwest China. The model performance was evaluated by the overall allocation accuracy and tau index, which accounts for class imbalance. For direct allocation based on three fertility classes (low, medium and high), the overall allocation accuracy of eight properties (CEC, Cu, Si, Zn, S, Mn, Ca and Mg), nine properties (B, AN, TK, AK, SOM, TN, TP, Fe and Mo) and three properties (Cl, AP and pH) were within the range of 0.80–1.0, 0.60–0.80 and 0.40–0.60, respectively. For indirect allocation based on the same classes, the allocation accuracy of nine properties (TN, CEC, Cu, S, Zn, Si, Mn, Ca and Mg), nine properties (B, TK, pH, TP, AK, AN, Fe, Mo and SOM) and two properties (Cl and AP) were within the range of 0.80–1.0, 0.60–0.80 and 0.40–0.60, respectively. We conclude that vis-NIR spectroscopy was fairly successful for soil fertility class allocation for most of the soil properties, using either direct or indirect models. The advantage of indirect models is that both specific property values and soil fertility classes can be obtained at no increase in cost, while direct models are suggested when only soil fertility class information are available.

This study aimed to investigate the feasibility of using imaging spectroscopy (IS) to predict soil organic carbon density (SOCD) either directly or indirectly through soil organic carbon (SOC). Three methods, partial least square regression (PLSR), support vector machine (SVM), and random forest (RF), were utilized to calibrate the models and map the SOCD. The results showed that direct prediction was better than indirect prediction and the best model SVM had high R ² of 0.94 and 0.93 for calibration and validation, respectively. The measured SOCD was mainly concentrated in the surface soil layer from 0 to 40 cm, and the deeper layer tended to be gentle. The continuous depth variation trend of SOCD in the topsoil (0-40 cm) was relatively close to the measured values, while in the deeper layers (below 40 cm), it was much higher than the measured values. The study also found that the best fitting function of measured SOC stocks over time varied from linear to power and then to logarithmic with increasing depth, indicating less efficient accumulation of SOC in deep soil compared to topsoil, resulting in an overall decrease in SOC accumulation rate across soil depth. The best temporal functions for the predicted values differed from the measured values at each depth, but the changing trends of the three functions were basically consistent. It suggests that IS technology has the potential to quantitatively reveal the process of coastal soil evolution and offers a new insight for the rapid monitoring of soil property changes.