Search Results (48)

Detecting trace metals in soil across geologically diverse terrains remains challenging due to complex mineral–metal interactions and the limited spatial coverage of traditional geochemical tests. This study develops a scalable VIS–NIR–SWIR spectroscopy and machine learning (ML) framework to predict and map soil concentrations of Cr, As, Cu, and Cd in the Aligudarz District, located within the geotectonically complex Sanandaj–Sirjan Zone of western Iran. Laboratory reflectance spectra (~350–2500 nm) obtained from 110 soil samples were pre-processed using derivative filtering, scatter-correction techniques, and genetic algorithm (GA)-based wavelength optimisation to enhance diagnostic absorption features linked to Fe-oxides, clay minerals, and carbonates. Multiple ML-based approaches, including artificial neural networks (ANNs), support vector regression (SVR), and partial least squares regression (PLSR), as well as stepwise multiple linear regression (SMLR), were compared using nested, spatial, and external validation. Nonlinear models, particularly ANNs, exhibited the highest predictive accuracy, with strong generalisation confirmed via an independent test set. GA-selected wavelengths and derivative-enhanced spectra revealed mineralogical controls on metal retention, confirming that spectral predictions reflect underlying geological processes. Ordinary kriging of spectral-ML residuals generated spatially consistent metal-distribution maps that aligned well with local and regional geological features. The integrated framework demonstrates high predictive accuracy and operational scalability, providing a reproducible, field-ready method for rapid geochemical assessment. The findings highlight the potential of VIS–NIR–SWIR spectroscopy, combined with advanced modelling and geostatistics, to support environmental monitoring, mineral exploration, and risk assessment in geologically complex terrains. Full article

The estimation of Above-Ground Biomass (AGB) in Amorphophallus konjac (Konjac) is essential for field management and yield prediction. While previous research has demonstrated the efficacy of Unmanned Aerial Vehicle (UAV) RGB imagery in estimating AGB for monoculture crops, the applicability of these methods to AGB estimation in Konjac remains uncertain due to its distinct morphological traits and prevalent intercropping practices with maize. Additionally, the Vegetation Indices (VIs) and Texture Features (TFs) obtained from UAV-based RGB imagery exhibit significant redundancy, raising concerns about whether the selected optimal variables can maintain estimation accuracy. Therefore, this study assessed the effectiveness of Variable Selection Using Random Forests (VSURF) and Principal Component Analysis (PCA) in variable selection and compared the performance of Stepwise Multiple Linear Regression (SMLR) with four Machine Learning (ML) regression techniques: Random Forest Regression (RFR), Extreme Gradient Boosting Regression (XGBR), Partial Least Squares Regression (PLSR), and Support Vector Regression (SVR), as well as Deep Learning (DL), in estimating the AGB of Konjac based on the selected features. The results indicate that the integration (PCA_(PCA_VIs+PCA_TFs)) of PCA-based VIs and PCA-based TFs using PCA achieved the best prediction accuracy (R² = 0.96, RMSE = 0.08 t/hm², MAE = 0.06 t/hm²) with SVR. In contrast, the DL model derived from AlexNet, combined with RGB imagery, yielded moderate predictive accuracy (R² = 0.72, RMSE = 0.21 t/hm², MAE = 0.17 t/hm²) compared with the optimal ML model. Our findings suggest that ML regression techniques, combined with appropriate variable-selected approaches, outperformed DL techniques in estimating the AGB of Konjac. This study not only provides new insights into AGB estimation in Konjac but also offers valuable guidance for estimating AGB in other crops, thereby advancing the application of UAV technology in crop biomass estimation. Full article

Identification of nutritious rice varieties through non-destructive detection technology is important for high-quality seed production. With the development of technology, rapid and non-destructive identification methods based on unmanned aerial vehicle (UAV) remote sensing technology are increasingly gaining attention in the scientific community. This study utilized hyperspectral imaging technology to acquire spectral reflectance data from the rice canopy during the grain filling stage. Different models (stepwise multiple linear regression (SMLR) and the Back Propagation Neural Network (BPNN)) for estimating rice protein content based on canopy spectral information were constructed using both multiple stepwise regression and BP neural networks. The results showed that the model based on BPNN estimation performed best for predicting grain protein content, with an R² = 0.9516 and RMSE = 0.3492, indicating high accuracy and stability in the model. Overall, hyperspectral imaging technology combined with various models could significantly help to identify rice varieties. Further, the current findings provide a technical reference for the selection of high-quality rice varieties in a non-destructive manner. Full article

Mercury (Hg) is a highly toxic contaminant posing serious ecological and human health risks. This study investigates the Hg transfer characteristics and prediction models in a soil–lettuce system, employing bioconcentration factors (BCF), path analysis (PA), and Freundlich-type functions. A pot experiment was conducted in a greenhouse, where lettuce was grown in a range of Chinese agricultural soils (n = 21) and deliberately spiked with Hg using Hg(NO₃)₂ solution. The results indicated that lettuce grown in Hg-spiked acidic soils (pH < 6.5) accumulated total Hg (THg) levels up to 14.01 µg kg⁻¹, surpassing the safe consumption limit of 10 µg kg⁻¹. The BCF for lettuce THg was less than 1.0, suggesting a low transfer of Hg from soil to lettuce. Notably, BCF values were significantly higher in acidic soils (0.02) compared to alkaline soils (0.005). Path analysis accounted for 82% of the variation in lettuce THg content, identifying soil THg, pH, and amorphous (Amo) Al and Fe oxides as primary direct factors. Additionally, soil-available Hg (AvHg), exchangeable Hg (ExHg), clay, and organic matter (OM) were significant indirect factors affecting lettuce THg content. To validate the findings of the path analysis, an extended Freundlich-type equation was developed using stepwise multiple linear regression (SMLR). This model exhibited high predictive accuracy (R² = 0.82, p ≤ 0.001), with soil pH, THg, and amorphous Al and Fe oxides being the key variables for predicting Hg transfer in the soil–lettuce system. The insights from this study can guide the management of safe lettuce production in Hg-contaminated soils, ensuring the mitigation of Hg exposure through agricultural produce. Full article

The rapid and accurate diagnosis of nitrogen content in apple orchard soil is of great significance for the rational application of nitrogen fertilizer in orchards to improve apple yield and quality. An apple orchard in Shuangquan Town, Changqing District, Jinan City, Shandong Province, was taken as the experimental area. The optimal method for extracting spectral characteristic bands and screening spectral characteristic indices (SCIs) of soil total nitrogen (TN) for independent and comprehensive fertilization periods was explored. Independent and comprehensive soil TN content estimation models were constructed and optimized for each and the entire fertilization period, respectively. The results show that compared with the correlation coefficient method, stepwise multiple linear regression (SMLR) performs better in extracting hyperspectral characteristic bands of soil TN content. It helps to achieve a higher modeling accuracy, smaller root mean square error (RMSE), and is more conducive to avoiding the influence of multicollinearity of model variables. The sensitive areas of soil TN content in the SCI do not undergo significant changes due to different fertilization periods. Among them, the ratio spectral indices (RSIs) are in the range of 800–900 nm, 1900–1950 nm, and 2200–2300 nm, while the sensitive areas of the difference spectral index (DI) and Normalized difference spectral index (NDSI) are in the range of 1900–1950 nm and 2200–2300 nm. The combination of SCI and characteristic bands significantly improves the prediction accuracy of soil TN estimation models. The independent and comprehensive estimation models for each fertilization period based on the BP (back propagation) neural network optimized by the Mind Evolution Algorithm (MEA-BPNN) can achieve a more stable and accurate estimation of soil TN. Finally, using soil spectral characteristic bands selected through continuum removal (CR) transformation and SMLR, combined with SCI, the model based on the MEA-BPNN (CR-SCI-MEA-BPNN) has the best prediction performance. The modeling determination coefficients R² for each fertilization period reached 0.94, 0.95, 0.92, and 0.94, respectively, with RMSE of 0.0032, 0.0024, 0.0035, and 0.0027. The R² and RMSE of the modeling and validation set of the entire fertilization period comprehensive model are 0.899, 0.0038, and 0.89, 0.0041, respectively. The results of this article provide technical support for promoting the timely monitoring of soil TN content and guiding rational fertilization in apple orchards. Full article

The accurate assessment of nitrogen (N) status is important for N management and yield improvement. The N status in plants is affected by plant densities and N application rates, while the methods for assessing the N status in drip-irrigated cotton under reduced nitrogen treatment and different plant densities are lacking. Therefore, this study was conducted with four different N treatments (195.5, 299, 402.5, and 506 kg N ha⁻¹) and three sowing densities (6.9 × 10⁴, 13.8 × 10⁴, and 24 × 10⁴ plants ha⁻¹) by using a low-cost Unmanned Aerial Vehicle (UAV) system to acquire RGB imagery at a 10 m flight altitude at cotton main growth stages. We evaluated the performance of different ground resolutions (1.3, 2.6, 5.2, 10.4, 20.8, 41.6, 83.2, and 166.4 cm) for image textures, vegetation indices (VIs), and their combination for leaf N concentration (LNC) estimation using four regression methods (stepwise multiple linear regression, SMLR; support vector regression, SVR; extreme learning machine, ELM; random forest, RF). The results showed that combining VIs (ExGR, GRVI, GBRI, GRRI, MGRVI, RGBVI) and textures (VAR, HOM, CON, DIS) yielded higher estimation accuracy than using either alone. Specifically, the RF regression models had a higher accuracy and stability than SMLR and the other two machine learning algorithms. The best accuracy (R² = 0.87, RMSE = 3.14 g kg⁻¹, rRMSE = 7.00%) was obtained when RF was applied in combination with VIs and texture. Thus, the combination of VIs and textures from UAV images using RF could improve the estimation accuracy of drip-irrigated cotton LNC and may have a potential contribution in the rapid and non-destructive nutrition monitoring and diagnosis of other crops or other growth parameters. Full article

Excess Na⁺ and high pH result in poor structures in Saline-Sodic soils, which reduces extracellular enzyme activity (EEA) and causes nutrient limitations. The application of manure improved the Physical-Chemical properties of soil and balanced the soil nutrient supply, which was reflected in the soil EEAs and stoichiometry. Five experimental treatments were designed according to the manure application duration as follows: manure application for 11 years (11a), 16 years (16a), 22 years (22a), and 27 years (27a) and a control treatment with no manure application (CK). The results of the redundancy analysis (RDA) showed that physical properties (mean weight diameter (MWD)) and EEA (β–glucosidase (BG)) significantly increased and bulk density (ρ_b) significantly decreased when the nutrient content increased. Additionally, soil pH, electrical conductivity (EC), exchangeable sodium percentage (ESP) and sodium adsorption ratio (SAR) significantly decreased after manure application. Based on stepwise multiple linear regression models (SMLR), total nitrogen (TN) was the dominant variable that significantly increased EEA, and the Mantel test showed that soil C:N significantly influenced enzyme stoichiometry. Furthermore, RDA showed that pH, soil C:N and TN were the main factors influencing EEAs and enzyme stoichiometry. Soil EEAs significantly increased with TN and decreased with pH and soil C:N, which affected enzyme stoichiometry. The enzyme stoichiometry increased from 1:2.1:1.2 and 1:2.7:1.5 to 1:1.7:1.2, and the vector angle (vector A) increased, which showed that the N limitation was relieved after the application of manure. The vector length (vector L) showed no significant difference in the C limitation at depths of 0–20 cm and significantly increased at depths of 20–40 cm. In conclusion, soil EEAs and stoichiometry improved with changes in TN and soil C:N, and pH decreased with changes in the soil structure after the application of manure, which accelerated the soil nutrient cycle and balanced the soil nutrient supply. Full article

The leaf area index (LAI) is an important indicator for crop growth monitoring. This study aims to analyze the effects of different data fusion strategies on the performance of LAI prediction models, using multisource images from unmanned aerial vehicles (UAVs). For this purpose, maize field experiments were conducted to obtain plants with different growth status. LAI and corresponding multispectral (MS) and RGB images were collected at different maize growth stages. Based on these data, different model design scenarios, including single-source image scenarios, pixel-level multisource data fusion scenarios, and feature-level multisource data fusion scenarios, were created. Then, stepwise multiple linear regression (SMLR) was used to design LAI prediction models. The performance of models were compared and the results showed that (i) combining spectral and texture features to predict LAI performs better than using only spectral or texture information; (ii) compared with using single-source images, using a multisource data fusion strategy can improve the performance of the model to predict LAI; and (iii) among the different multisource data fusion strategies, the feature-level data fusion strategy performed better than the pixel-level fusion strategy in the LAI prediction models. Thus, a feature-level data fusion strategy is recommended for the creation of maize LAI prediction models using multisource UAV images. Full article

Tiger nuts are a non-genetically modified organism crop with high adaptability and economic value, and they are being widely promoted for cultivation in China. This study proposed a new yield-estimation method based on a lightweight convolutional neural network (CNN) named Squeeze Net to provide accurate production forecasts for tiger nut tubers. The multispectral unmanned aerial vehicle (UAV) images were used to establish phenotypic datasets of tiger nuts, comprising vegetation indices (VIs) and plant phenotypic indices. The Squeeze Net model with a lightweight CNN structure was constructed to fully explore the explanatory power of the spectral UAV-derived information and compare the differences between the parametric and nonparametric models applied in tiger nut yield predictions. Compared with stepwise multiple linear regression (SMLR), both algorithms achieved good yield prediction performances. The highest obtained accuracies reflected an R² value of 0.775 and a root-mean-square error (RMSE) value of 688.356 kg/ha with SMLR, and R² = 0.780 and RMSE = 716.625 kg/ha with Squeeze Net. This study demonstrated that Squeeze Net can efficiently process UAV multispectral images and improve the resolution and accuracy of the yield prediction results. Our study demonstrated the enormous potential of artificial intelligence (AI) algorithms in the precise crop management of tiger nuts in the arid sandy lands of northwest China by exploring the interactions between various intensive phenotypic traits and productivity. Full article

The rapid, accurate estimation of leaf nitrogen content (LNC) and plant nitrogen content (PNC) in cotton in a non-destructive way is of great significance to the nutrient management of cotton fields. The RGB images of cotton fields in Shihezi (China) were obtained by using a low-cost unmanned aerial vehicle (UAV) with a visible-light digital camera. Combined with the data of LNC and PNC in different growth stages, the correlation between N content and visible light vegetation indices (VIs) was analyzed, and then the Random Forest (RF), Support Vector Machine (SVM), Back Propagation Neural Network (BP), and stepwise multiple linear regression (SMLR) were used to develop N content estimation models at different growth stages. The accuracy of the estimation model was assessed by coefficient of determination (R²), root mean squared error (RMSE), and relative root mean square error (rRMSE), so as to determine the optimal estimated growth stage and the best model. The results showed that the correlation between VIs and LNC was stronger than that between PNC, and the estimation accuracy of different models decreased continuously with the development of growth stages, with higher estimation accuracy in the peak squaring stage. Among the four algorithms, the best accuracy (R² = 0.9001, RMSE = 1.2309, rRMSE = 2.46% for model establishment, and R² = 0.8782, RMSE = 1.3877, rRMSE = 2.82% for model validation) was obtained when applying RF at the peak squaring stage. The LNC model for whole growth stages could be used in the later growth stage due to its higher accuracy. The results of this study showed that there is a potential for using an affordable and non-destructive UAV-based digital system to produce predicted LNC content maps that are representative of the current field nitrogen status. Full article

Nitrogen is one of the most important macronutrients and plays an essential role in the growth and development of winter wheat. It is very crucial to diagnose the nitrogen status timely and accurately for applying a precision nitrogen management (PNM) strategy to the guidance of nitrogen fertilizer in the field. The main purpose of this study was to use three different prediction methods to evaluate winter wheat plant nitrogen concentration (PNC) at booting, heading, flowering, filling, and the whole growth stage in the Guanzhong area from unmanned aerial vehicle (UAV) hyperspectral imagery. These methods include (1) the parametric regression method; (2) linear nonparametric regression methods (stepwise multiple linear regression (SMLR) and partial least squares regression (PLSR)); and (3) machine learning methods (random forest regression (RFR), support vector machine regression (SVMR), and extreme learning machine regression (ELMR)). The purpose of this study was also to pay attention to the impact of different growth stages on the accuracy of the model. The results showed that compared with parametric regression and linear nonparametric regression, the machine learning regression method could evidently improve the estimation accuracy of winter wheat PNC, especially using SVMR and RFR, the training set of the model at flowering and filling stage explained 93% and 92% of the PNC variability respectively. The testing set of the model at flowering and filling stages explained 88% and 91% of the PNC variability, the root mean square error of the validation set (RMSE_testing) was 0.82 and 1.23, and the relative prediction deviation (RPD) was 2.58 and 2.40, respectively. Therefore, a conclusion was drawn that it was the best choice to estimate winter wheat PNC at the flowering and filling stage from UAV hyperspectral imagery. Using machine learning methods, SVMR and RFR, respectively, could achieve the most outstanding estimation performance, which could provide a theoretical basis for putting forward the PNM strategy. Full article

The aboveground dry biomass (AGDB) of winter wheat can reflect the growth and development of winter wheat. The rapid monitoring of AGDB by using hyperspectral technology is of great significance for obtaining the growth and development status of winter wheat in real time and promoting yield increase. This study analyzed the changes of AGDB based on a winter wheat irrigation experiment. At the same time, the AGDB and canopy hyperspectral reflectance of winter wheat were obtained. The effect of spectral preprocessing algorithms such as reciprocal logarithm (Lg), multiple scattering correction (MSC), standardized normal variate (SNV), first derivative (FD), and second derivative (SD); sample division methods such as the concentration gradient method (CG), the Kennard–Stone method (KS), and the sample subset partition based on the joint X–Y distances method (SPXY); sample division ratios such as 1:1 (Ratio1), 3:2 (Ratio2), 2:1 (Ratio3), 5:2 (Ratio4), and 3:1 (Ratio5); dimension reduction algorithms such as uninformative variable elimination (UVE); and modeling algorithms such as partial least-squares regression (PLSR), stepwise multiple linear regression (SMLR), artificial neural network (ANN), and support vector machine (SVM) on the hyperspectral monitoring model of winter wheat AGDB was studied. The results showed that irrigation can improve the AGDB and canopy spectral reflectance of winter wheat. The spectral preprocessing algorithm can change the original spectral curve and improve the correlation between the original spectrum and the AGDB of winter wheat and screen out the bands of 1400 nm, 1479 nm, 1083 nm, 741 nm, 797 nm, and 486 nm, which have a high correlation with AGDB. The calibration sets and validation sets divided by different sample division methods and sample division ratios have different data-distribution characteristics. The UVE method can obviously eliminate some bands in the full-spectrum band. SVM is the best modeling algorithm. According to the universality of data, the better sample division method, sample division ratio, and modeling algorithm are SPXY, Ratio4, and SVM, respectively. Combined with the original spectrum and by using UVE to screen bands, a model with stable performance and high accuracy can be obtained. According to the particularity of data, the best model in this study is FD-CG-Ratio4-Full-SVM, for which the R²_c, RMSE_c, R²_v, RMSE_v, and RPD are 0.9487, 0.1663 kg·m⁻², 0.7335, 0.3600 kg·m⁻², and 1.9226, respectively, which can realize hyperspectral monitoring of winter wheat AGDB. This study can provide a reference for the rational irrigation of winter wheat in the field and provide a theoretical basis for monitoring the AGDB of winter wheat by using hyperspectral remote sensing technology. Full article

Two multivariate models were compared to assess their yield predictability based on long-term (1980–2021) rice yield and weather datasets over eleven districts of Karnataka. Simple multiple linear regression (SMLR) and artificial neural network models (ANN) were calibrated (1980–2019 data) and validated (2019–2020 data), and yields were forecasted (2021). An intercomparison of the models revealed better yield predictability with ANN, as the observed deviations were smaller (−37.1 to 21.3%, 4% mean deviation) compared to SMLR (−2.5 to 35.0%, 16% mean deviation). Further, district-wise yield forecasting using ANN indicated an underestimation of yield, with higher errors in Mysuru (−0.2%), Uttara Kannada (−1.5%), Hassan (−0.1%), Ballari (−1.5%), and Belagavi (−15.3%) and overestimations in the remaining districts (0.0 to 4.2%) in 2018. Likewise, in 2019 the yields were underestimated in Kodagu (−0.6%), Shivamogga (−0.1%), Davanagere (−0.7%), Hassan (−0.2%), Ballari (−5.1%), and Belagavi (−10.8%) and overestimated for the other five districts (0.0 to 4.8%). Such model yield underestimations are related to the farmers’ yield improvement practices carried out under adverse weather conditions, which were not considered by the model while forecasting. As the deviations are in an acceptable range, they prove the better applicability of ANN for yield forecasting and crop management planning in addition to its use for regional agricultural policy making. Full article

The water quality of a basin is pronouncedly affected by the surrounding types of land use. Analyzing the impact of LULC and landscape patterns on water quality is critical for identifying potential drivers. To further study how LUCC affects the water quality in a typical plateau lake basin, this study investigated the impacts of land-use types on water quality in the Dianchi Lake Basin in Southwest China. We analyzed changes in land-use types and the landscape pattern of the Dianchi basin, calculated the CWQI (Canadian Water Quality Index) value based on the water quality indexes (PH, total phosphorus (TP), total nitrogen (TN), chemical oxygen demand (COD), dissolved oxygen (DO), permanganate index (COD_Mn), five-day biochemical ox-ygen demand (BOD₅), ammonia nitrogen (NH₃-N), turbitidy, and chlorophyll-a (Chla)), used the RDA (Redundancy Analysis) and SMLR (Stepwise multiple linear regression) methods, the coupling degree, coupling coordination degree, and the geographical detector model to explore the relationship between water quality and changes in the land-use type. The results show that (1) changes in the land-use types were obvious: the majority of the land, which was originally forest land, became built land in 2020 and farmland in 1990 (except for the Dianchi water). Landscape pattern indexes indicated that almost all land-use types were first scattered, then gathered from 1990 to 2020. (2) Changes in the water quality of Dianchi Lake lagged behind the changes in land-use types, and the variation trends were similar to the landscape pattern variation trends. The CWQI value decreased in a nearly linear fashion from 1990 to 1998, exhibited a slight change from 1999 to 2013, and quickly increased from 2013. (3) Land-use types demonstrated a tight correlation with the Dianchi water quality, and LPI was the most dominant factor in both Caohai Lake and Waihai Lake. (4) There were different indexes affecting the coupling coordination degrees of Caohai Lake and Waihai Lake. Full article

Crop yield forecasting before harvesting is critical for the creation, implementation, and optimization of policies related to food safety as well as for agro-product storage and marketing. Crop growth and development are influenced by the weather. Therefore, models using weather variables can provide reliable predictions of crop yields. It can be tough to select the best crop production forecasting model. Therefore, in this study, five alternative models, viz., stepwise multiple linear regression (SMLR), an artificial neural network (ANN), the least absolute shrinkage and selection operator (LASSO), an elastic net (ELNET), and ridge regression, were compared in order to discover the best model for rice yield prediction. The outputs from individual models were used to build ensemble models using the generalized linear model (GLM), random forest (RF), cubist and ELNET methods. For the previous 21 years, historical rice yield statistics and meteorological data were collected for three districts under three separate agro-climatic zones of Chhattisgarh, viz., Raipur in the Chhattisgarh plains, Surguja in the northern hills, and Bastar in the southern plateau. The models were calibrated using 80% of these datasets, and the remaining 20% was used for the validation of models. The present study concluded that for rice crop yield forecasting, the performance of the ANN was good for the Raipur ($R_{cal}^2$ = 1, $R_{val}^2$= 1 and $RMS{E}_{cal}$ = 0.002, $RMS{E}_{val}$ = 0.003) and Surguja ($R_{cal}^2$ = 1, $R_{val}^2$= 0.99 and $RMS{E}_{cal}$ = 0.004, $RMS{E}_{val}$ = 0.214) districts as compared to the other models, whereas for Bastar, ELNET ($R_{cal}^2$ = 90, $R_{val}^2$= 0.48) and LASSO ($R_{cal}^2$ = 93, $R_{val}^2$= 0.568) performed better. The performance of the ensemble model was better compared to the individual models. For Raipur and Surguja, the performance of all the ensemble methods was comparable, whereas for Bastar, random forest (RF) performed better, with R² = 0.85 and 0.81 for calibration and validation, respectively, as compared to the GLM, cubist, and ELNET approach. Full article