Texture Index Research Articles

Effect of rapid cooling on the properties of friction stir processed AA7075

Friction stir processing applied to AA7075 using a pentagonal pin produced a defect free cross-section with a superior material consolidation. The processed specimens were allowed to cool under in air and water separately. Compared to the air-cooled specimen, the water-cooled specimen exhibited better grain refinement. Rapid cooling using water suppressed the growth of grains and reduced the average grain size to 3.07 μm with increased dislocation density in the microstructure. Water cooled specimen exhibited a better texture index of 1.2600 in the stir zone with S {123}<634>, Copper{112}<111>, and brass {011}<211> as the major types. Average hardness in case of the air-cooled sample was 82.77 HV, while the water-cooled sample exhibited an improved hardness of 103.86 HV due to enhanced dislocation density, grain refinement, and uniformly dispersed strengthening precipitates.

In situ interlayer hot forging arc plasma directed energy deposition of Inconel® 625: microstructure evolution during heat treatments

The study reports that the combined use of in situ interlayer hot forging and post-deposition heat treatment (PDHT) could alter the typical coarse and oriented microstructure of the Ni-based superalloy 625 obtained by arc plasma directed energy deposition (DED) to a fine and non-oriented condition. In situ synchrotron X-ray diffraction and electron backscatter diffraction showed that the high-temperature (1100 °C/ 1 h) PDHT induced significant recrystallization, leading to grain refinement and low texture index, while partially dissolving deleterious Laves and δ phases. Low-temperature (980 °C/ 1 h) PDHT had a limited effect on the grain size refinement and induced the formation of secondary phases. It is shown that conventional heat treatments applied to Ni-based superalloy 625 obtained by arc plasma DED are not conducive to optimized microstructure features. In situ hot forging induced enough crystal defects to promote static recrystallization during PDHT. Besides, high-temperature PDHT met the AMS 5662 grain size requirements.

Prognostic value of initial [ 18 F]FDG PET/computed tomography volumetric and texture analysis-based parameters in patients with head and neck squamous cell carcinoma.

To determine the predictive value of initial [ 18 F]FDG PET/computed tomography (CT) volumetric and radiomics-derived analyses in patients with head and neck squamous cell carcinoma (HNSCC). Forty-six adult patients had pathologically proven HNSCC and underwent pretherapy [ 18 F]FDG PET/CT were enrolled. Semi-quantitative PET-derived volumetric [(maximum standardized uptake value (SUVmax) and mean SUV (SUVmean), total lesion glycolysis (TLG) and metabolic tumor volume (MTV)] and radiomics analyses using LIFEx 6.73.3 software were performed. In the current study group, the receiver operating characteristic curve marked a cutoff point of 21.105 for primary MTV with area under the curve (AUC) of 0.727, sensitivity of 62.5%, and specificity of 86.8% ( P value 0.041) to distinguish responders from non-responders, while no statistically significant primary SUVmean or max or primary TLG cut off points could be determined. It also marked the cutoff point for survival prediction of 10.845 for primary MTV with AUC 0.728, sensitivity of 80%, and specificity of 77.8% ( P value 0.026). A test of the synergistic performance of PET-derived volumetric and textural features significant parameters was conducted in an attempt to develop the most accurate and stable prediction model. Therefore, multivariate logistic regression analysis was performed to detect independent predictors of mortality. With a high specificity of 97.1% and an overall accuracy of 89.1%, the combination of primary tumor MTV and the textural feature gray-level co-occurrence matrix correlation provided the most accurate prediction of mortality ( P value < 0.001). Textural feature indices are a noninvasive method for capturing intra-tumoral heterogeneity. In our study, a PET-derived prediction model was successfully generated with high specificity and accuracy.

The texture of non-fat yogurt with proteins isolates and concentrates

Yogurt is one of the most common fermented milk products. It is consumed directly as food or used for the production of fermented milk desserts and ice cream. The urgent task for yogurt producers is improving product quality due to additionally introduced protein components. In this study, an effect of protein isolates and concentrates on the rheological parameters of yogurt was evaluated. The methods included the determination of dynamic viscosity and texture indices, such as hardness, gumminess, chewiness, springiness, cohesiveness and adhesiveness. The prepared yogurt samples were investigated immediately and after 30 days of storage at a temperature of 4±2°C. The water-holding capacity was evaluated. It has been established that introduction of whey proteins makes it possible to increase the water-holding capacity to 77% and 80%, respectively. The highest value of dynamic viscosity (19.3 and 26.1 Pa·s) was found in the samples with isolate and concentrate of native whey proteins after 5 hours of fermentation. A decrease in dynamic viscosity with the introduction of milk protein isolate, soy protein concentrate and native whey protein isolate was observed after 5 hours of fermentation. Addition of the protein components led to a significant increase in texture indices, except for cohesiveness. The highest cohesiveness value of 0.4 N·s was found in the sample without protein components and in the sample with whey protein concentrate. The indicators of hardness, gumminess, chewiness, springiness and adhesiveness were the highest in the sample with native whey protein isolate.

Investigation into microstructural evolution, mechanical and tribological properties of an aluminum surface composite developed using a severe plastic deformation technique

Aluminum based surface metal matrix composite was developed with 15% and 20% of TiCp reinforcement using multi-pass friction stirring process. The effect of TiC reinforcement and multiple FSP passes on microstructural evolution was characterized using optical, X-ray diffraction, electron microscopy, and electron backscattered diffraction techniques, while texture formation was analyzed using the neutron diffraction method. Hardness and tribological investigations were carried out to examine the mechanical behavior of the reinforced surface. A defect-free, uniformly reinforced composite surface with increased matrix-reinforcement interface was attained with 15% TiC after six passes. Hardness improved substantially to 215 HV due to the combined effect of zener pinning, grain refinement, uniformly dispersed reinforcement and increased dislocation density in the matrix. Better texture index was observed on the composite surface with Copper and S as dominating texture components. Significant wear resistance was exhibited by the composite at lower load due to strong adherence of TiC to the matrix, which however decreased with increase in loading conditions. Wear surface examination revealed that the mode of wear was predominantly abrasive.

Prevalence, Predictors and Morphological Patterns of Acanthosis Nigricans Between Obese Non-diabetic Patients on Second Generation Antipsychotics Versus Non-obese Insulin Dependent Diabetes mellitus: A Nested Case-Control Study

INTRODUCTION: There is no study in literature for analyzing acanthosis nigricans (AN) in psychotropic induced obesity or hypercholesterolemia.&#x0D; AIM: To assess the prevalence and explore the predictors and morphological patterns in AN in patients on antipsychotics induced hypercholesterolemia versus those with diabetes mellitus.&#x0D; MATERIALS AND METHODS: 491 schizophrenia patients on second generation antipsychotics were screened. 26 out of 491 patients have AN and cholesterol 200 mg/dl but non-diabetic. We used MannWhitney U-test, Pearsons 2 test, Fischer Exact and Spearmans correlation coefficient.&#x0D; RESULTS: In the group of antipsychotics induced hypercholesterolemia having developed AN in 5.29% (26 out of 491) of individuals, we observed significance of Burkes knuckle (p 0.001), knee (p = 0.002), elbow (p = 0.042) compared to patients without hypercholesterolemia. Interestingly Burkes neck severity (p 0.001), neck texture (p = 0.001) and axilla (p = 0.007) index also showed marked differences on MannWhitney U-test and Wilcoxson W-test. On Spearmans correlation coefficient antipsychotics induced hypercholesterolemia was found to affect most positively and significantly as the emergence of AN specifically for neck texture ( = 0.413, p = 0.003) compared to other bodily regions.&#x0D; CONCLUSION: About 5.29% prevalence of AN in the group having obesity secondary to psychotropic drugs which was significantly less than what even non-obese, insulin dependent diabetic patients who almost had 13.55% prevalence, close to three times. This suggests that diabetes is strongly linked with occurrence of AN lesions and might reflect the continuity in the paradigm of metabolic syndrome as its definitive predictor of severity while obesity is the initiation of phase shift in the process.

Non-destructive monitoring of maize LAI by fusing UAV spectral and textural features.

Leaf area index (LAI) is an essential indicator for crop growth monitoring and yield prediction. Real-time, non-destructive, and accurate monitoring of crop LAI is of great significance for intelligent decision-making on crop fertilization, irrigation, as well as for predicting and warning grain productivity. This study aims to investigate the feasibility of using spectral and texture features from unmanned aerial vehicle (UAV) multispectral imagery combined with machine learning modeling methods to achieve maize LAI estimation. In this study, remote sensing monitoring of maize LAI was carried out based on a UAV high-throughput phenotyping platform using different varieties of maize as the research target. Firstly, the spectral parameters and texture features were extracted from the UAV multispectral images, and the Normalized Difference Texture Index (NDTI), Difference Texture Index (DTI) and Ratio Texture Index (RTI) were constructed by linear calculation of texture features. Then, the correlation between LAI and spectral parameters, texture features and texture indices were analyzed, and the image features with strong correlation were screened out. Finally, combined with machine learning method, LAI estimation models of different types of input variables were constructed, and the effect of image features combination on LAI estimation was evaluated. The results revealed that the vegetation indices based on the red (650 nm), red-edge (705 nm) and NIR (842 nm) bands had high correlation coefficients with LAI. The correlation between the linearly transformed texture features and LAI was significantly improved. Besides, machine learning models combining spectral and texture features have the best performance. Support Vector Machine (SVM) models of vegetation and texture indices are the best in terms of fit, stability and estimation accuracy (R2 = 0.813, RMSE = 0.297, RPD = 2.084). The results of this study were conducive to improving the efficiency of maize variety selection and provide some reference for UAV high-throughput phenotyping technology for fine crop management at the field plot scale. The results give evidence of the breeding efficiency of maize varieties and provide a certain reference for UAV high-throughput phenotypic technology in crop management at the field scale.

A Comparison of Machine Learning Models for Mapping Tree Species Using WorldView-2 Imagery in the Agroforestry Landscape of West Africa

Farmland trees are a vital part of the local economy as trees are used by farmers for fuelwood as well as food, fodder, medicines, fibre, and building materials. As a result, mapping tree species is important for ecological, socio-economic, and natural resource management. The study evaluates very high-resolution remotely sensed WorldView-2 (WV-2) imagery for tree species classification in the agroforestry landscape of the Kano Close-Settled Zone (KCSZ), Northern Nigeria. Individual tree crowns extracted by geographic object-based image analysis (GEOBIA) were used to remotely identify nine dominant tree species (Faidherbia albida, Anogeissus leiocarpus, Azadirachta indica, Diospyros mespiliformis, Mangifera indica, Parkia biglobosa, Piliostigma reticulatum, Tamarindus indica, and Vitellaria paradoxa) at the object level. For every tree object in the reference datasets, eight original spectral bands of the WV-2 image, their spectral statistics (minimum, maximum, mean, standard deviation, etc.), spatial, textural, and color-space (hue, saturation), and different spectral vegetation indices (VI) were used as predictor variables for the classification of tree species. Nine different machine learning methods were used for object-level tree species classification. These were Extra Gradient Boost (XGB), Gaussian Naïve Bayes (GNB), Gradient Boosting (GB), K-nearest neighbours (KNN), Light Gradient Boosting Machine (LGBM), Logistic Regression (LR), Multi-layered Perceptron (MLP), Random Forest (RF), and Support Vector Machines (SVM). The two top-performing models in terms of highest accuracies for individual tree species classification were found to be SVM (overall accuracy = 82.1% and Cohen’s kappa = 0.79) and MLP (overall accuracy = 81.7% and Cohen’s kappa = 0.79) with the lowest numbers of misclassified trees compared to other machine learning methods.

Upstream River Erosion vis-a-vis Sediments Variability in Hugli Estuary, India: A Geospatial Approach

Satellite data shows that the Bhagirathi-Hugli River’s riverbank has faced severe erosion during the last decades (1990 to 2020), with the middle stretch of the river being more prone to erosion. This huge sediment load derived from upstream erosion is coming to the estuary. The suspended sediment concentration dynamics of the Hugli estuary were calculated using in-situ data and remote sensing reflectance by establishing a linear regression. A continuous huge sediment load is found in the estuarine water. The sediment concentration was higher pre-monsoon than post-monsoon as the region is highly influenced by monsoonal rainfall and runoff. The sediment concentration was also higher in the estuary’s southwestern section than in the northern part. The impact of this high sediment load contributes to the deposition. This depositional area assessment was performed using an object-based classification approach called Support Vector Machine utilizing Grey Level Co-occurrence Matrix to create cluster textural indices. Despite the impact of continuous sea level rise in the estuary, the result shows that effective island and Chars areas have increased in the past decade due to the upstream erosion-driven sediments.

Estimation of Aboveground Biomass for Winter Wheat at the Later Growth Stage by Combining Digital Texture and Spectral Analysis

Aboveground biomass (AGB) is an important indicator used to predict crop yield. Traditional spectral features or image textures have been proposed to estimate the AGB of crops, but they perform poorly at high biomass levels. This study thus evaluated the ability of spectral features, image textures, and their combinations to estimate winter wheat AGB. Spectral features were obtained from the wheat canopy reflectance spectra at 400–1000 nm, including original wavelengths and seven vegetation indices. Effective wavelengths (EWs) were screened through use of the successive projection algorithm, and the optimal vegetation index was selected by correlation analysis. Image texture features, including texture features and the normalized difference texture index, were extracted using gray level co-occurrence matrices. Effective variables, including the optimal texture subset (OTEXS) and optimal normalized difference texture index subset (ONDTIS), were selected by the ranking of feature importance using the random forest (RF) algorithm. Linear regression (LR), partial least squares regression (PLS), and RF were established to evaluate the relationship between each calculated feature and AGB. Results demonstrate that the ONDTIS with PLS based on the validation datasets exhibited better performance in estimating AGB for the post-seedling stage (R2 = 0.75, RMSE = 0.04). Moreover, the combinations of the OTEXS and EWs exhibited the highest prediction accuracy for the seeding stage when based on the PLS model (R2 = 0.94, RMSE = 0.01), the post-seedling stage when based on the LR model (R2 = 0.78, RMSE = 0.05), and for all stages when based on the RF model (R2 = 0.87, RMSE = 0.05). Hence, the combined use of spectral and image textures can effectively improve the accuracy of AGB estimation, especially at the post-seedling stage.

Effect of tool pin geometry and multi-pass intermittent friction stir processing on the surface properties of aerospace grade aluminium 7075 alloy

Multiple pass intermittent friction stir processing was conducted on the surface of an aerospace grade AA7075 alloy using pentagonal and hexagonal profiled pins and its microstructural evolution and mechanical properties were investigated. Results showed a defect-free cross-section with better material mixing for the specimens processed using pentagonal pin. Application of 6 intermittent friction stir processing passes reduced average grain size to 2.32 μm as a result of dynamic recrystallization. Texture index improved after 6 intermittent friction stir processing passes with a higher volume of deformation textures. Microhardness and tensile strength of the alloy increased to 125.5 HV, and 476 ± 10 MPa after 6 intermittent friction stir processing passes due to precipitation strengthening, grain refinement, and dislocation density. Fracture surface investigation revealed an intergranular mode of failure.

Leaf area index estimation of pergola-trained vineyards in arid regions using classical and deep learning methods based on UAV-based RGB images

Timely and accurate mapping of leaf area index (LAI) in vineyards plays an important role for management choices in precision agricultural practices. However, only a little work has been done to extract the LAI of pergola-trained vineyards using higher spatial resolution remote sensing data. The main objective of this study was to evaluate the ability of unmanned aerial vehicle (UAV) imageries to estimate the LAI of pergola-trained vineyards using shallow and deep machine learning (ML) methods. Field trials were conducted in different growth seasons in 2021 by collecting 465 LAI samples. Firstly, this study trained five classical shallow ML models and an ensemble learning model by using different spectral and textural indices calculated from UAV imageries, and the most correlated or useful features for LAI estimations in different growth stages were differentiated. Then, due to the classical ML approaches need the arduous computation of multiple indices and feature selection procedures, another ResNet-based convolutional neural network (CNN) model was constructed which can be directly fed by cropped images. Furthermore, this study introduced a new image data augmentation method which is applicable to regression problems. Results indicated that the textural indices performed better than spectral indices, while the combination of them can improve estimation results, and the ensemble learning method showed the best among classical ML models. By choosing the optimal input image size, the CNN model we constructed estimated the LAI most effectively without extracting and selecting the features manually. The proposed image data augmentation method can generate new training images with new labels by mosaicking the original ones, and the CNN model showed improved performance after using this method compared to those using only the original images, or augmented by rotation and flipping methods. This data augmentation method can be applied to other regression models to extract growth parameters of crops using remote sensing data, and we conclude that the UAV imagery and deep learning methods are promising in LAI estimations of pergola-trained vineyards.

Study of Freeze-thaw Induced Damage Characteristic for Himalayan Schist

Abstract The freeze-thaw (F-T) induced deterioration in rocks affects their durability, leading to various landslides, rockslides, and avalanches. The study focuses on estimating loss in rock strength using mineralogical properties under the influence of multiple F-T cycles. The rock samples were collected from F-T affected north Indian Himalayan region. The rock specimens were subjected to multiple F-T conditioning (0th, 10th, 20th and 30th F-T cycles). The mineralogical properties (such as mineralogical indices and textural indices) and mechanical properties (such as uniaxial compressive strength; UCS and Brazilian tensile strength; BTS) were calculated before and after F-T conditioning. A correlation was developed among the various strength properties and mineralogical properties. The result shows a strong relationship between the UCS and BTS with mean grain size. Further, results were used to develop a mathematical model, based on mineralogical parameter and decay function, to predict the rock strength under the influence of multiple F-T cycles.

Manufacture of SiC: Effect of Carbon Precursor

SiC is one of the most important ceramics at present due to its excellent properties and wide range of applications. The industrial production method, known as the Acheson method, has not changed in 125 years. Because the synthesis method in the laboratory is completely different, laboratory optimisation may not be extrapolated to the industrial level. In the present study, the results at the industrial level and at the laboratory level of the synthesis of SiC are compared. These results show that it is necessary to make a more detailed analysis of the coke than the traditional one; therefore, the Optical Texture Index (OTI) should be included, as well as the analysis of the metals that form the ashes. It has been found that the main influencing factors are OTI and the presence of Fe and Ni in the ashes. It has been determined that the higher the OTI, as well as the Fe and Ni content, the better the results obtained. Therefore, the use of regular coke is recommended in the industrial synthesis of SiC.

Using electric field to modify wet gluten as meat analogue material: A comparative study between pulsed and direct current electric fields

To assess the efficacy of electric field (EF) on vegetable protein juice-holding and texturisation as a low denaturation processing means, the impacts of pulsed (PEF) and low direct current (DCEF) electric field on the water- (WHC) and oil-holding capacity (OHC), microstructure, texture and physical structure of wheat gluten were investigated using wet gluten dough. The results showed that the PEF and DCEF affected the WHC and OHC significantly. The PEF seemed not to affect the textural properties so severely although significant differences appeared in hardness, chewiness, gumminess, and cohesiveness; there were no significant differences either in springiness or in resilience. The DCEF had a stronger impact on all the textural indices. Scanning electronic microscopy suggested that the PEF caused smaller and uniform micropores and the DCEF derivated more continuous and compact microstructure. Fourier transform infrared spectrometry demonstrated that EF significantly altered the composition proportion of the secondary structure. A slight blue shifts of UV spectra, a red shift of fluorescence spectra, and an increased surface hydrophobicity of gluten could be observed after EF treatment. X-ray diffractometry demonstrated that the EF significantly made the physical structure of wet gluten compacter. The results suggested that EF is promising in vegetable protein texturisation.

The Effects of Malonaldehyde on Quality Characteristics and Protein Oxidation of Coregonus peled (Coregonuspeled) during Storage.

The effects of changes in the malondialdehyde (MDA) content on the quality of fish during the low-temperature storage period are unclear. Therefore, the effects of the MDA content on Coregonus peled quality and protein changes were investigated following storage under refrigeration (4 °C) and super chilling (-3 °C) for 15 days (d). The results showed that the MDA content continued to increase during storage and that the highest content was produced at 1.42 mg/kg during refrigeration. The fillet pH, drip loss, texture (hardness and elasticity), and myofibril fragmentation index deteriorated significantly during the storage period. Increased oxidation of the myofibrillar protein (MP) was observed in the 15 d storage period, and the MP carbonyl content was 1.19 times higher under refrigeration than in super chilling, while the protein α-helix structure decreased by 12.48% and 12.20% under refrigeration and super chilling, respectively. Electropherograms also showed that myosin degradation was particularly severe in the refrigeration storage period of 15 d. Overall, the MDA formed at the refrigeration and super chilling storage temperatures could promote structural changes in, and the oxidative degradation of, proteins to different degrees, leading to the deterioration of the fillet quality. This study provides a scientific basis for investigating the relationship between fish quality and changes in the MDA content during low-temperature storage.

Densification, Microstructure and Anisotropic Corrosion Behavior of Al-Mg-Mn-Sc-Er-Zr Alloy Processed by Selective Laser Melting

High-performance additives manufactured by Al alloys provide significant potential for lightweight applications and have attracted much attention nowadays. However, there is no research on Sc, Er and Zr microalloyed Al alloys, especially concerning corrosion behavior. Herein, crack-free and dense Al-Mg-Mn-Sc-Er-Zr alloys were processed by selective laser melting (SLM). After optimizing the process parameters of SLM, the anisotropic corrosion behavior of the sample (volume energy density of 127.95 J·mm−3) was investigated by intergranular corrosion (IGC) and electrochemical measurements. The results showed that the XY plane of the as-built sample is less prone to IGC, and it also has a higher open circuit potential value of −901.54 mV, a higher polarization resistance of 2.999 × 104 Ω·cm2, a lower corrosion current of 2.512 μA·cm−2 as well as passive film with superior corrosion resistance compared to the XZ plane. According to our findings, the XY plane has superior corrosion resistance compared to the XZ plane because it has fewer primary phases of Al3(Sc, Er, Zr) and Al2MgO4, which can induce localized corrosion. Additionally, a higher fraction of low-angle grain boundaries (LAGBs) and a stronger (001) texture index along the building direction are also associated with better corrosion resistance of the XY plane.

Monitoring of Wheat Fusarium Head Blight on Spectral and Textural Analysis of UAV Multispectral Imagery

Crop disease identification and monitoring is an important research topic in smart agriculture. In particular, it is a prerequisite for disease detection and the mapping of infected areas. Wheat fusarium head blight (FHB) is a serious threat to the quality and yield of wheat, so the rapid monitoring of wheat FHB is important. This study proposed a method based on unmanned aerial vehicle (UAV) low-altitude remote sensing and multispectral imaging technology combined with spectral and textural analysis to monitor FHB. First, the multispectral imagery of the wheat population was collected by UAV. Second, 10 vegetation indices (VIs)were extracted from multispectral imagery. In addition, three types of textural indices (TIs), including the normalized difference texture index (NDTI), difference texture index (DTI), and ratio texture index (RTI) were extracted for subsequent analysis and modeling. Finally, VIs, TIs, and VIs and TIs integrated as the input features, combined with k-nearest neighbor (KNN), the particle swarm optimization support vector machine (PSO-SVM), and XGBoost were used to construct wheat FHB monitoring models. The results showed that the XGBoost algorithm with the fusion of VIs and TIs as the input features has the highest performance with the accuracy and F1 score of the test set being 93.63% and 92.93%, respectively. This study provides a new approach and technology for the rapid and nondestructive monitoring of wheat FHB.

Retrieving rice (Oryza sativa L.) net photosynthetic rate from UAV multispectral images based on machine learning methods.

Photosynthesis is the key physiological activity in the process of crop growth and plays an irreplaceable role in carbon assimilation and yield formation. This study extracted rice (Oryza sativa L.) canopy reflectance based on the UAV multispectral images and analyzed the correlation between 25 vegetation indices (VIs), three textural indices (TIs), and net photosynthetic rate (Pn) at different growth stages. Linear regression (LR), support vector regression (SVR), gradient boosting decision tree (GBDT), random forest (RF), and multilayer perceptron neural network (MLP) models were employed for Pn estimation, and the modeling accuracy was compared under the input condition of VIs, VIs combined with TIs, and fusion of VIs and TIs with plant height (PH) and SPAD. The results showed that VIs and TIs generally had the relatively best correlation with Pn at the jointing-booting stage and the number of VIs with significant correlation (p< 0.05) was the largest. Therefore, the employed models could achieve the highest overall accuracy [coefficient of determination (R 2) of 0.383-0.938]. However, as the growth stage progressed, the correlation gradually weakened and resulted in accuracy decrease (R 2 of 0.258-0.928 and 0.125-0.863 at the heading-flowering and ripening stages, respectively). Among the tested models, GBDT and RF models could attain the best performance based on only VIs input (with R 2 ranging from 0.863 to 0.938 and from 0.815 to 0.872, respectively). Furthermore, the fusion input of VIs, TIs with PH, and SPAD could more effectively improve the model accuracy (R 2 increased by 0.049-0.249, 0.063-0.470, and 0.113-0.471, respectively, for three growth stages) compared with the input combination of VIs and TIs (R 2 increased by 0.015-0.090, 0.001-0.139, and 0.023-0.114). Therefore, the GBDT and RF model with fused input could be highly recommended for rice Pn estimation and the methods could also provide reference for Pn monitoring and further yield prediction at field scale.

Synergistic estimation of soil salinity based on Sentinel-1 image texture and Sentinel-2 salinity spectral indices

Soil salinization, one of the important factors leading to global land degradation, seriously affects sustainable agricultural development. Accurate and frequent monitoring of soil salt content (SSC) contributes to the management and restoration of salinized soil. Our study aimed to evaluate the potential to synthetically estimate the salinity in bare soil with different remote sensing sensors (medium-resolution Sentinel-1 and Sentinel-2). The salinity data of 134 surface soil samples were collected in the Shahaoqu irrigation area (SIA) in the Hetao Irrigation District of Inner Mongolia. Simultaneously, the remote sensing images of Sentinel-1 and Sentinel-2 of SIA were obtained. A total of 46 predictors, including 12 remote sensing data (10 multispectral bands, 1 VV, and 1 VH), 8 polarization combination indices, 16 salinity spectral indices, and 10 texture features, were obtained and calculated from the remote sensing image data. Three machine learning algorithms, random forest (RF), support vector machine (SVM), and extreme learning machine (ELM), were used for the construction of soil salinity prediction models based on different combinations of the 46 predictors. The results showed that the remote sensing image data from multiple sensors could be used to estimate soil salinity more accurately than that of a single sensor. Among the three regression models (RF, SVM, and ELM) in our study, RF was the best prediction model (Rv2=0.71, RMSEv = 0.140 % , and MAE = 0.094 % ). The RF model combining Sentinel-1 SAR and Sentinel-2 multispectral imagery was the most effective in revealing the spatial distribution of soil salinity. The importance analysis of the predictor variables showed that texture features were the main explanatory variables for SSC prediction, with contrast being the most important predictor. The results of our study verified the potential to predict SSC by combining multisource remote sensing data and machine learning models in arid and semiarid regions, which could provide some reference for soil salinization monitoring and control in the bare soil.