Monitoring plastic-mulched farmland using Landsat-8 OLI imagery

The potential of hyperspectral imaging system was evaluated for the rapid identification of rice origin. 240 samples from four different regions of China were imaged by a hyperspectral imaging system. Hyperspectral images were studied from the three principal aspects (spectral, morphological and texture features). Support vector machine was used for developing the identification models. Seven models based on spectral, morphological, texture, combined spectral and morphological, combined spectral and texture, combined morphological and texture and combined spectral, morphological and texture features were developed for seeking the optimal feature combination. Nine important wavelengths were determined by principal component analysis. The results showed that the highest accuracy (91.67%) was obtained from combined spectral, morphological and texture features. This study demonstrated that hyperspectral imaging could provide a rapid identification of rice origin and the method of feature combination could be very helpful to improve the performance of identification models.Practical ApplicationsThe price and quality of rice mainly depends on its geographical origin in the food market. Traditional methods for identification of rice origin mainly focus on the appearance of rice and depend on the feelings of professionals, which are tedious, time‐consuming, expensive and greatly influenced by subjective factors. Therefore, the results in our paper can provide a foundational basis to develop a real‐time inspection system for the rapid, precise and non‐destructive identification of rice origin.

Optical image provides a unique spectral and textural opportunity to acquire data free of charge in cloud-free weather conditions. However, textural information from recent Sentinel-2A data has not been sufficiently recognized. Several researches have shown that texture features are essential for extracting crop information. This study presents a new scheme that integrates spectral bands and textural features for mapping maize fields and other land cover types (i.e., build-up, trees, others, and water) and evaluates the effectiveness of random forest (RF) and support vector machine (SVM) classifiers with different kernel functions based on Sentinel 2A (S-2A) data. The textural features were derived from multiple bands of S-2A image using a grey-level co-occurrence matrix (GLCM) algorithm. To normalize the analysis of these features, Random Forest feature selection was employed. The outcomes show that S-2A images are appropriate for mapping maize fields and other land covers when the image is accessible during the growing season. The SVM classifier with a radial basis function (RBF) kernel is superior to a polynomial (P), linear (L), and sigmoid (S) kernel functions, and the RF classifiers. For the SVM_RBF, the highest overall accuracy was obtained from the integration of spectral bands and textural features at scenario 2 SVM_RBF (87.40%), followed by the combination of spectral and textural features at scenario 2 SVM_P kernel (86.56%). However, scenario 5 SVM_P kernel (85.54%), scenario 4 SVM_P kernel function (85.30%), the spectral features alone, and the SVM_P kernel function, have the highest O/A (83.90%) than that of the SVM_RBF (83.66%). The inclusion of textural features contributed significantly in mapping the smallholder’s maize field in the study area. This demonstrated the value of S-2A in agricultural research.

BackgroundPepper Phytophthora blight is a devastating disease during the growth process of peppers, significantly affecting their yield and quality. Accurate, rapid, and non-destructive early detection of pepper Phytophthora blight is of great importance for pepper production management. This study investigated the possibility of using multispectral imaging combined with machine learning to detect Phytophthora blight in peppers. Peppers were divided into two groups: one group was inoculated with Phytophthora blight, and the other was left untreated as a control. Multispectral images were collected at 0-h samples before inoculation and at 48, 60, 72, and 84 h after inoculation. The supporting software of the multispectral imaging system was used to extract spectral features from 19 wavelengths, and textural features were extracted using a gray-level co-occurrence matrix (GLCM) and a local binary pattern (LBP). The principal component analysis (PCA), successive projection algorithm (SPA), and genetic algorithm (GA) were used for feature selection from the extracted spectral and textural features. Two classification models were established based on effective single spectral features and significant spectral textural fusion features: a partial least squares discriminant analysis (PLS_DA) and one-dimensional convolutional neural network (1D-CNN). A two-dimensional convolutional neural network (2D-CNN) was constructed based on five principal component (PC) coefficients extracted from the spectral data using PCA, weighted, and summed with 19-channel multispectral images to create new PC images.ResultsThe results indicated that the models using PCA for feature selection exhibit relatively stable classification performance. The accuracy of PLS-DA and 1D-CNN based on single spectral features is 82.6% and 83.3%, respectively, at the 48h mark. In contrast, the accuracy of PLS-DA and 1D-CNN based on spectral texture fusion reached 85.9% and 91.3%, respectively, at the same 48h mark. The accuracy of the 2D-CNN based on 5 PC images is 82%.ConclusionsThe research indicates that Phytophthora blight infection can be detected 48 h after inoculation (36 h before visible symptoms). This study provides an effective method for the early detection of Phytophthora blight in peppers.

Classification of aflatoxin B1 naturally contaminated peanut using visible and near-infrared hyperspectral imaging by integrating spectral and texture features

A decision-level fusion approach to tree species classification from multi-source remotely sensed data

Two merging techniques based on the Price algorithm and the high pass filter (HPF) have been used to merge SPOT XS with PAN data to evaluate the effect of merging in classification of urban areas. The Price algorithm has been found to produce a smaller distortion of the spectral characteristics of merged data compared to the HPF algorithm. It generates accuracies similar to the original data using spectral or a combination of spectral and textural features. The gain in overall accuracy by adding one texture band over pure spectral features is higher for merged data than with the original data. Both data merging algorithms result in inferior overall and individual class accuracies compared to the original data for pure spectral as well as for a combination of spectral and texture features. The Price algorithm should be used only for those spectral bands that are highly correlated with PAN data. For the poorly correlated band, the HPF algorithm should be used; while using the HPF algorithm, it is preferable to use the cubic convolution resampler.

Two merging techniques based on the Price algorithm and a high pass filter (HPF) have been used to merge SPOT XS with PAN data to evaluate the effect of merging on classification of an urban area. The Price algorithm gave smaller distortion of spectral characteristics of merged data compared to the HPF algorithm and provided accuracies similar to the original data using spectral or a combination of spectral and texture features. The gain in overall accuracy by adding one texture band over pure spectral features is higher for merged data than with the original data. Both data merging algorithms result in inferior overall and individual class accuracies compared to the original data for pure spectral as well as for a combination of spectral and texture features. The Price algorithm should be used for those spectral bands only, which are highly correlated with the PAN data. For the poorly correlated band, the HPF algorithm should be used.

Although many content-based image retrieval systems have been developed, few studies have focused on hyperspectral remote sensing images. In this paper, a hyperspectral remote sensing image retrieval system based on spectral and texture features is proposed. The main contributions are fourfold: (1)considering the "mixed pixel" in the hyperspectral image, endmembers as spectral features are extracted by an improved automatic pixel purity index algorithm, then the texture features are extracted with the gray level co-occurrence matrix; (2)similarity measurement is designed for the hyperspectral remote sensing image retrieval system, in which the similarity of spectral features is measured with the spectral information divergence and spectral angle match mixed measurement and in which the similarity of textural features is measured with Euclidean distance; (3)considering the limited ability of the human visual system, the retrieval results are returned after synthesizing true color images based on the hyperspectral image characteristics; (4) the retrieval results are optimized by adjusting the feature weights of similarity measurements according to the user's relevance feedback. The experimental results on NASA data sets can show that our system can achieve comparable superior retrieval performance to existing hyperspectral analysis schemes.

We established prediction models based on the combination of spectral and different advanced image features to improve the prediction accuracy of solid-soluble content (SSC) of apple. Eight optimal wavelengths were selected using a new variable selection method called variable combination population analysis (VCPA). Image textural features of the first three principal component score images were obtained using a gray level co-occurrence matrix (GLCM) and a local binary pattern (LBP). Next, a random frog algorithm was developed to select optimal textural features for further analysis. A support vector regression (SVR) model based on spectral and different textural features was developed to predict the SSC of the apple. The model based on eight optimal wavelengths and nine optimal GLCM features of principal component images yielded the best result with the determination coefficient for prediction (Rp2) of 0.9193, root mean square error for prediction (RMSEP) of 0.2955, and the ratio of the standard deviation of the prediction set to the root mean square error of prediction (RPD) with a value of 3.50. These results revealed that the spectral combined with optimal GLCM features from principal component images coupled with the SVR model has the potential for prediction of the SSC of apple.

<p indent="0mm">Plastic film mulching has been widely applied in conservation agriculture, and remote sensing provides an effective tool for monitoring the spatiotemporal dynamics of mulched farmland. However, in regions with complex natural conditions and a high risk of soil salinization, targeted datasets describing the spatial distribution and temporal variation of plastic-mulched farmland remain limited. Da’an City, located in the western part of the Songnen Plain, is characterized by low-lying terrain, pronounced salt accumulation, and poor soil fertility, making it a highly representative study area. In this study, the spatiotemporal distribution of plastic-mulched farmland in Da’an City from 2015 to 2023 was mapped and its temporal variation trends were analyzed. A Normalized Agricultural Film Index (NAFI) based on multi-temporal remote sensing data was proposed and applied to Landsat 8 OLI and Sentinel-2 MSI imagery acquired in April and May using the Google Earth Engine (GEE) platform. Spectral features and index-based features were extracted through GEE, and five feature combination schemes were designed. The optimal feature combination was selected based on classification accuracy and performance metrics. Using the optimal feature scheme, a random forest algorithm was employed to identify plastic-mulched farmland, resulting in a raster dataset representing the spatiotemporal distribution in Da’an City from 2015 to 2023. The overall classification accuracy of the random forest model ranged from 92.04% to 99.27%, with Kappa coefficients between 0.87 and 0.98. This dataset can serve as a valuable reference for regional-scale remote sensing identification and spatiotemporal analysis of plastic-mulched farmland.

Free amino acids are an important indicator of the freshness of yellow tea. This study investigated a novel procedure for predicting the free amino acid (FAA) concentration of yellow tea. It was developed based on the combined spectral and textural features from hyperspectral images. For the purposes of exploration and comparison, hyperspectral images of yellow tea (150 samples) were captured and analyzed. The raw spectra were preprocessed with Savitzky-Golay (SG) smoothing. To reduce the dimension of spectral data, five feature wavelengths were extracted using the successive projections algorithm (SPA). Five textural features (angular second moment, entropy, contrast, correlation, and homogeneity) were extracted as textural variables from the characteristic grayscale images of the five characteristic wavelengths using the gray-level co-occurrence matrix (GLCM). The FAA content prediction model with different variables was established by a genetic algorithm-support vector regression (GA-SVR) algorithm. The results showed that better prediction results were obtained by combining the feature wavelengths and textural variables. Compared with other data, this prediction result was still very satisfactory in the GA-SVR model, indicating that data fusion was an effective way to enhance hyperspectral imaging ability for the determination of free amino acid values in yellow tea.

Desert vegetation is an important part of arid and semi-arid areas, which plays an important role in preventing wind and fixing sand, conserving water and soil, maintaining the balanced ecosystem. Therefore, mapping the vegetation accurately is necessary to conserve rare desert plants in the fragile ecosystems that are easily damaged and slow to recover. In mapping desert vegetation, there are some weaknesses by using traditional digital classification algorithms from high resolution data. The traditional approach is to use spectral features alone, without spatial information. With the rapid development of drones, cost-effective visible light data is easily available, and the data would be non-spectral but with spatial information. In this study, a method of mapping the desert rare vegetation was developed based on the pixel classifiers and use of Random Forest (RF) algorithm with the feature of VDVI and texture. The results indicated the accuracy of mapping the desert rare vegetation were different with different methods and the accuracy of the method proposed was higher than the traditional method. The most commonly used decision rule in the traditional method, named Maximum Likelihood classifier, produced overall accuracy (76.69%). The inclusion of texture and VDVI features with RGB (Red Green Blue) data could increase the separability, thus improved the precision. The overall accuracy could be up to 84.19%, and the Kappa index with 79.96%. From the perspective of features, VDVI is less important than texture features. The texture features appeared more important than spectral features in desert vegetation mapping. The RF method with the RGB+VDVI+TEXTURE would be better method for desert vegetation mapping compared with the common method. This study is the first attempt of classifying the desert vegetation based on the RGB data, which will help to inform management and conservation of Ulan Buh desert vegetation.

Leaf chlorophyll content (LCC) is crucial for monitoring the physiological processes of crops. Many studies have utilized spectral features to develop regression models for accurate LCC estimation, enabling the quantitative assessment and evaluation of crop growth status. The selection of optimal spectral features and regression algorithms significantly affects the precision of LCC estimation. In this study, we compared and analyzed the optimal spectral features for LCC estimation, as well as the consistency of machine learning methods across different crop types, phenology periods, and sensors. First, we extracted various spectral features, including the original spectral features (OS), first-order derivative spectral features (FDS), original continuum-removed spectra (CR) along with their four related derivative spectral features, principal component variables derived from different spectral features, and highly correlated spectral features with LCC. These extracted spectral features were then employed to construct the LCC models using six common regression algorithms on different datasets. Finally, we analyzed the optimal combination of spectral features and regression algorithms for accurate LCC estimation considering various dimensions, such as crop type, phenological period, and sensor used in observation conditions. The results demonstrate that the combinations of the principal component variables of continuum-removed derivative reflectance with the top 10 correlations with LCC (PCA_CRDR_R) combined with Gaussian process regression (GPR) can be considered as the optimal choice for estimating LCC under diverse observation conditions at a canopy scale, and its R2 can reach 0.62 for sugar beet LCC estimation; thus providing valuable theoretical guidance for selecting appropriate spectral features for LCC estimation.

A key issue in modern fire management planning is the accurate fuel type mapping, required at many different spatial and temporal scales. Fuel type classification is critical for improving fire prevention schemes, developing accurate fire dispersion models and designing effective measures for mitigating the impacts of a potential wildfire event on the ecosystem. Remote sensing offers the potential to provide spatially distributed information on fuel types and it has been widely used both at regional and local scale. Theaim of this study is to develop and evaluate a fuel type mapping methodology on a national level, based on the geographic objectoriented classification approach and Landsat-8 OLI imagery. The proposed methodology was developed in the case study of Chalkidiki in the northern part of Greece and it was further tested for its transferability in the regional unit of Preveza and the whole administrative region of Attica. The classification scheme was determined taking under consideration the existing fuel models(Prometheus, FBP etc) and fuel type products (JRC FUELMAP, LIFE10 ArcFUEL) so as the final fuel type map could be easily adjusted and/or compared. Fifty-four Landsat-8 OLI images for summer and for winter season, covering the national territory, were acquired and several features (vegetation indices, textural and spectral features) were calculated for both seasons. The optimized feature selection for the discrimination of each fuel type category was empirically obtained. Results showcase the effectiveness of theemployed object-oriented classification approach in obtaining highly accurate fuel type maps. Specifically, the generated fuel map of Chalkidiki exhibited an overall accuracy of 89.47%, with a Kappa Index of Agreement (KIA) equal to 0.844. The application of the model to the two other regions resulted in overall accuracies of 80.30% (KIA=0.706) for Attica and 91.74% (KIA=0.867) for Preveza. Summarizing, the results proved the good transferability properties of the proposed methodology enabling the implementation of the model across the country.

The latest breed of very high resolution (VHR) commercial satellites opens new possibilities for cartographic and remote-sensing applications. In fact, one of the most common applications of remote-sensing images is the extraction of land-cover information for digital image base maps by means of classification techniques. The aim of the study was to compare the potential classification accuracy provided by pan-sharpened orthoimages from both GeoEye-1 and WorldView-2 (WV2) VHR satellites over urban environments. The influence on the supervised classification accuracy was evaluated by means of an object-based statistical analysis regarding three main factors: (i) sensor used; (ii) sets of image object (IO) features used for classification considering spectral, geometry, texture, and elevation features; and (iii) size of training samples to feed the classifier (nearest neighbour (NN)). The new spectral bands of WV2 (Coastal, Yellow, Red Edge, and Near Infrared-2) did not improve the benchmark established from GeoEye-1. The best overall accuracy for GeoEye-1 (close to 89%) was attained by using together spectral and elevation features, whereas the highest overall accuracy for WV2 (83%) was achieved by adding textural features to the previous ones. In the case of buildings classification, the normalized digital surface model computed from light detection and ranging data was the most valuable feature, achieving producer's and user's accuracies close to 95% and 91% for GeoEye-1 and VW2, respectively. Last but not least and regarding the size of the training samples, the rule of ‘the larger the better' was true but, based on statistical analysis, the ideal choice would be variable depending on both each satellite and target class. In short, 20 training IOs per class would be enough if the NN classifier was applied on pan-sharpened orthoimages from both GeoEye-1 and WV2.