Would it be better for partition prediction of heavy metal concentration in soils based on the fusion of XRF and Vis-NIR data?

Heavy metal (HM) contamination in soil necessitates effective methods to diagnose suspected contaminated areas and control rehabilitation processes. The synergistic use of proximal sensors demonstrates significant potential for rapid detection via accurate surveys of soil HM pollution at large scales and high sampling densities, and necessitates the selection of appropriate data mining and modeling methods for early diagnosis of soil pollution. The aim of this study is to evaluate the performance of a subarea model based on geographically partitioned and global models based on high-precision energy dispersive X-ray fluorescence (HD-XRF) and visible near-infrared (vis-NIR) spectra using a random forest model for predicting soil Cu and Pb concentrations. A total of 166 soil samples are acquired from a contaminated plot in Baiyin, Gansu Province, China. The soil samples are subjected to HM analysis and proximal sensor scanning in a laboratory. Vis-NIR spectral data are preprocessed using the Savitzky Golay (SG) and first-order derivative with Savitzky Golay (SGFD) methods. The results show that for predicting Cu and Pb concentrations in soil, the subarea models performs better than the global models in terms of quantitative prediction, based solely on individual HD-XRF data. For the subarea and global models, the R2 values are 0.961 and 0.981, respectively; the RMSE values are 27.8 and 79.6, respectively; and the RPD values are 4.96 and 7.38, respectively. However, making use of the random forest algorithm trained with data fusion obtained from the HD-XRF and vis-NIR sensors, the global model achieves the best predictions for Cu and Pb concentrations via HD-XRF + vis-NIR (SGFD) and HD-XRF + vis-NIR (SG), respectively. The results will provide a new perspective for modeling approaches to rapidly invert HM concentrations based on proximal sensor data fusion within a large scope of the study area.

Wheat lodging extraction using Improved_Unet network.

The accurate extraction of wheat lodging areas can provide important technical support for post-disaster yield loss assessment and lodging-resistant wheat breeding. At present, wheat lodging assessment is facing the contradiction between timeliness and accuracy, and there is also a lack of effective lodging extraction methods. This study aims to propose a wheat lodging assessment method applicable to multiple Unmanned Aerial Vehicle (UAV) flight heights. The quadrotor UAV was used to collect high-definition images of wheat canopy at the grain filling and maturity stages, and the Unet network was evaluated and improved by introducing the Involution operator and Dense block module. The performance of the Improved_Unet was determined using the data collected from different flight heights, and the robustness of the improved network was verified with data from different years in two different geographical locations. The results of analyses show that (1) the Improved_Unet network was better than other networks (Segnet, Unet and DeeplabV3+ networks) evaluated in terms of segmentation accuracy, with the average improvement of each indicator being 3% and the maximum average improvement being 6%. The Improved_Unet network was more effective in extracting wheat lodging areas at the maturity stage. The four evaluation indicators, Precision, Dice, Recall, and Accuracy, were all the highest, which were 0.907, 0.929, 0.884, and 0.933, respectively; (2) the Improved_Unet network had the strongest robustness, and its Precision, Dice, Recall, and Accuracy reached 0.851, 0.892, 0.844, and 0.885, respectively, at the verification stage of using lodging data from other wheat production areas; and (3) the flight height had an influence on the lodging segmentation accuracy. The results of verification show that the 20-m flight height performed the best among the flight heights of 20, 40, 80 and 120 m evaluated, and the segmentation accuracy decreased with the increase of the flight height. The Precision, Dice, Recall, and Accuracy of the Improved_Unet changed from 0.907 to 0.845, from 0.929 to 0.864, from 0.884 to 0.841, and from 0.933 to 0.881, respectively. The results demonstrate the improved ability of the Improved-Unet to extract wheat lodging features. The proposed deep learning network can effectively extract the areas of wheat lodging, and the different height fusion models developed from this study can provide a more comprehensive reference for the automatic extraction of wheat lodging.

Identification of Rice Sheath Blight through Spectral Responses Using Hyperspectral Images.

Sheath blight (ShB), caused by Rhizoctonia solani AG1-I, is one of the most important diseases in rice worldwide. The symptoms of ShB primarily develop on leaf sheaths and leaf blades. Hyperspectral remote sensing technology has the potential of rapid, efficient and accurate detection and monitoring of the occurrence and development of rice ShB and other crop diseases. This study evaluated the spectral responses of leaf blade fractions with different development stages of ShB symptoms to construct the spectral feature library of rice ShB based on "three-edge" parameters and narrow-band vegetation indices to identify the disease on the leaves. The spectral curves of leaf blade lesions have significant changes in the blue edge, green peak, yellow edge, red valley, red edge and near-infrared regions. The variables of the normalized index between green peak amplitude and red valley amplitude (Rg - Ro)/(Rg + Ro), the normalized index between the yellow edge area and blue edge area (SDy - SDb)/(SDy + SDb), the ratio index of green peak amplitude and red valley amplitude (Rg/Ro) and the nitrogen reflectance index (NRI) had high relevance to the disease. At the leaf scale, the importance weights of all attributes decreased with the effect of non-infected areas in a leaf by the ReliefF algorithm, with Rg/Ro being the indicator having the highest importance weight. Estimation rate of 95.5% was achieved in the decision tree classifier with the parameter of Rg/Ro. In addition, it was found that the variety degree of absorptive valley, reflection peak and reflecting steep slope was different in the blue edge, green and red edge regions, although there were similar spectral curve shapes between leaf sheath lesions and leaf blade lesions. The significant difference characteristic was the ratio index of the red edge area and green peak area (SDr/SDg) between them. These results can provide the basis for the development of a specific sensor or sensors system for detecting the ShB disease in rice.

Development and Evaluation of a New Spectral Disease Index to Detect Wheat Fusarium Head Blight Using Hyperspectral Imaging.

Fusarium head blight (FHB) is a major disease threatening worldwide wheat production. FHB is a short cycle disease and is highly destructive under conducive environments. To provide technical support for the rapid detection of the FHB disease, we proposed to develop a new Fusarium disease index (FDI) based on the spectral data of 374-1050 nm. This study was conducted through the analysis of reflectance spectral data of healthy and diseased wheat ears at the flowering and filling stages by hyperspectral imaging technology and the random forest method. The characteristic wavelengths selected were 570 nm and 678 nm for the late flowering stage, 565 nm and 661 nm for the early filling stage, 560 nm and 663 nm for the combined stage (combining both flowering and filling stages) by random forest. FDI at each stage was derived from the wavebands of each corresponding stage. Compared with other 16 existing spectral indices, FDI demonstrated a stronger ability to determine the severity of the FHB disease. Its determination coefficients (R2) values exceeded 0.90 and the RMSEs were less than 0.08 in the models for each stage. Furthermore, the model for the combined stage performed better when used at single growth stage, but its effect was weaker than that of the models for the two individual growth stages. Therefore, using FDI can provide a new tool to detect the FHB disease at different growth stages in wheat.

Use of Unmanned Aerial Vehicle Imagery and Deep Learning UNet to Extract Rice Lodging.

Rice lodging severely affects harvest yield. Traditional evaluation methods and manual on-site measurement are found to be time-consuming, labor-intensive, and cost-intensive. In this study, a new method for rice lodging assessment based on a deep learning UNet (U-shaped Network) architecture was proposed. The UAV (unmanned aerial vehicle) equipped with a high-resolution digital camera and a three-band multispectral camera synchronously was used to collect lodged and non-lodged rice images at an altitude of 100 m. After splicing and cropping the original images, the datasets with the lodged and non-lodged rice image samples were established by augmenting for building a UNet model. The research results showed that the dice coefficients in RGB (Red, Green and Blue) image and multispectral image test set were 0.9442 and 0.9284, respectively. The rice lodging recognition effect using the RGB images without feature extraction is better than that of multispectral images. The findings of this study are useful for rice lodging investigations by different optical sensors, which can provide an important method for large-area, high-efficiency, and low-cost rice lodging monitoring research.

[Prediction of regional soil quality based on mutual information theory integrated with decision tree algorithm].

In this paper, some main factors such as soil type, land use pattern, lithology type, topography, road, and industry type that affect soil quality were used to precisely obtain the spatial distribution characteristics of regional soil quality, mutual information theory was adopted to select the main environmental factors, and decision tree algorithm See 5.0 was applied to predict the grade of regional soil quality. The main factors affecting regional soil quality were soil type, land use, lithology type, distance to town, distance to water area, altitude, distance to road, and distance to industrial land. The prediction accuracy of the decision tree model with the variables selected by mutual information was obviously higher than that of the model with all variables, and, for the former model, whether of decision tree or of decision rule, its prediction accuracy was all higher than 80%. Based on the continuous and categorical data, the method of mutual information theory integrated with decision tree could not only reduce the number of input parameters for decision tree algorithm, but also predict and assess regional soil quality effectively.

[Spatial pattern of soil fertility in Bashan tea garden: a prediction based on environmental auxiliary variables].

Taking topographic factors and NDVI as auxiliary variables, and by using regression-kriging method, the spatial variation pattern of soil fertility in Bashan tea garden in the hilly area of Fuyang City was explored. The spatial variability of the soil fertility was mainly attributed to the structural factors such as relative elevation and flat/vertical curvature. The lower the relative elevation, the worse the soil fertility was. The overall soil fertility level was relatively high, and the area with lower soil fertility only accounted for 5% of the total. By using regression-kriging method with relative elevation as auxiliary variable, the prediction accuracy of soil fertility was obviously higher than that by using ordinary kriging method, with the mean error and root mean square error being 0. 028 and 0. 108, respectively. It was suggested that the prediction method used in this paper could fully reflect the effects of environmental variables on soil fertility , improve the prediction accuracy about the spatial pattern of soil fertility, and provide scientific basis for the precise management of tea garden.

[Application of mutual information to variable selection in diagnosis of phosphorus nutrition in rice].

The present study obtained data of rice canopy spectrum, and P and chlorophyll content at typical growth stages with different rates of P supply by means of solution experiment. The effects of P treatments on leaf P and chlorophyll content were analyzed statistically using LSD's multiple comparison at a probability of 0.05; By mutual information (MI) variable selection procedure, the optimal spectral variables were identified at 536, 630, 1040, 551 and 656 nm, and their corresponding mutual information values were 1.0575, 1.1039, 1.135 3, 1.1417 and 1.1494 respectively; based on these sensitive bands, the built feed-forward artificial neural network model (ANN) had higher precision for P content estimation than the multiple linear regression model (MLR). Its RMSE of cross-validation and R were 0.038 8 and 0.9882, respectively, for the calibration data set, and the RMSE of prediction and R were 0.0505 and 0.9892, respectively, for the test data set. Therefore, it was suggested that MI was encouraged for quantitative prediction of leaf P content in rice with visible/near infrared hyperspectral information without assumption on the relationship between independent and dependent variables. But more work is needed to explain why these bands are sensitive to leaf P content in rice.

Variability of total and available copper concentrations in relation to land use and soil properties in Yangtze River Delta of China.

The effects of land use and soil properties on total and available Cu concentrations in soils were investigated in this study. A total of 276 surface (0-20 cm) soil samples were collected from seven land uses: industrial area, woodland, vegetable field, dry land, paddy field, tea garden and orchard. The total and available (DTPA extractable) Cu concentrations, pH, organic matter, and total nitrogen contents, and cation exchange capacity were measured for each sample. The correlation and ANOVA analyses showed that land use significantly affected total and available Cu concentrations, and the available ratio of soil Cu (available Cu concentration/total Cu concentration). On total Cu concentration, total nitrogen had significant influence in dry land and paddy field, and CEC in garden land; on available Cu concentration, the four measured soil properties showed significant influence only in paddy field; on the available ratio of Cu, pH had significant effect in paddy field and woodland, and CEC in industrial area. Moreover, the relationship between available Cu concentration and soil properties was constructed in different land uses. Spatial analysis of grain Cu using indicator Kriging showed that most of the study areas were in low risk for arable activities, and 7.94% of the study area and 5.10% of the arable land were in high risk probability.

Assessing soil Cu content and anthropogenic influences using decision tree analysis.

Recent enhanced urbanization and industrialization in China have greatly influenced soil Cu content. To better understand the magnitude of Cu contamination in soil, it is essential to understand its spatial distribution and estimate its values at unsampled points. However, Kriging often can not achieve satisfactory estimates when soil Cu data have weak spatial dependence. The proposed classification and regression tree method (CART) simulated Cu content using environmental variables, and it had no special data requirements. The Cu concentration classes estimated by CART had accuracy in attribution to the right classes of 80.5%, this is 29.3% better than ordinary Kriging method. Moreover, CART provides some insight into the sources of current soil Cu contents. In our study, low soil Cu accumulation was driven by terrain characteristic, agriculture land uses, and soil properties; while high Cu concentration resulted from industrial and agricultural land uses.

[Assessing soil Zn content using decision tree analysis].

Taking Fuyang county of Zhejiang Province as the study area, the present study estimated soil Zn concentration (divided by its local background value into G1, G2, G3, G4 and G5) using CART methods, based on 184 soil samples (0-20 cm). The environmental factors used to infer the Zn concentration rules included soil types, pH, organic matter, agricultural land uses, industry plant types, road and village density. The other 41 soil samples were used to test the prediction results. The Zn concentration classes estimated by CART have accuracy in attribution to the right classes of 80.49%. This is a 21.95% improvement on Zn classes estimated by ordinary Kriging method. Concretely, it improved the precision much for G1, G3 and G4, while obtained similar precision for G2 and G5. Moreover, CART provided some insights into the sources of current soil Zn contents. The categories of industrial plants play the most important role in separating the high and low level of Zn concentration (G1, G2 and G3, G4, G5), and the pH value, soil types and agricultural types play important roles in differentiation among G1 and G2, and among G3, G4 and G5.

Transfer characteristics of cadmium and lead from soil to the edible parts of six vegetable species in southeastern China.

The transfer characteristics of Cd and Pb from soils to the edible parts of six vegetable species were calculated from plant and corresponding surface soil samples collected from the fields in Fujian Province, southeastern China. The soil-to-plant transfer factors (TF) calculated from both total and DTPA-extractable Cd and Pb in the soils decreased with increasing total or DTPA-extractable Cd and Pb, indicating that the TF values of Cd and Pb depend on the soil metal content. For most plants studied, there was a significant relation between the TF values and the corresponding soil metal concentrations (total or DTPA-extractable) that was best described by an exponential equation (y=axb). We recommend that the representative TF value for a given crop-metal system should be estimated from the regression models between the transfer factors and the corresponding soil metal concentrations and at a given soil metal concentration.