Search

Determining the geographical origin of kimchi holds significance because of the considerable variation in quality and price among kimchi products from different regions. This study explored the feasibility of employing Fourier transform near-infrared spectroscopy in conjunction with supervised chemometric techniques to differentiate domestic and imported kimchi products. A total of 30 domestic and 30 imported kimchi products were used to build datasets. Three categories of preprocessing methods such as scattering correction (multiplicative signal correction and standard normal variate), spectral derivatives (the first derivative and the second derivative), and data smoothing (Savitzky–Golay filtering and Norris derivative filtering) were used. K-nearest neighbors, support vector machine, random forest, and partial least squares-discriminant analysis were employed. By appropriately preprocessing spectral data, these four methods successfully distinguished between the two sample groups based on their origin. Notably, the k-nearest neighbors method exhibited exceptional performance, accurately classifying the sample groups irrespective of the preprocessing method employed and swiftly achieving this classification. In comparison, classification and regression tree as well as naïve Bayes methods were outperformed by the aforementioned four classification techniques. Particularly, the efficiency and accuracy of the k-nearest neighbors method make it the most recommended chemometric tool for determining the geographical origins of kimchi. [ABSTRACT FROM AUTHOR]

Human activities, such as reservoir construction and riverbed sand extraction, significantly influence the hydrological and sedimentary dynamics of natural rivers, thereby directly or indirectly affecting river landscape pattern distribution. This study primarily focused on the lower Beijiang River (LBR) in China, an area characterized by intensive human activity. River landscape patterns were studied using historical topographical data and time-series Landsat remote sensing images. Natural and anthropogenic factors were considered to explore the driving forces behind the evolution of landscape patterns. The results indicated that the topography of the LBR underwent significant downcutting from 1998 to 2020. The average elevation of the study area decreased by 3.6 m, and the minimum thalweg elevation decreased by 6.7 m. Over the past 30 years, the local vegetation showed a relatively stable spatial distribution, whereas the area of sand remained relatively stable before 2012, followed by a sudden decline, and tended to stabilize in the last decade. The water area exhibited a gradually increasing trend. The transition maps indicated that the spatial changes in sand were the most significant, with only 39.6% of the sand remaining unchanged from 1998 to 2009 and 32.3% from 2009 to 2020. The corresponding landscape patterns showed that the fragmentation degree of sand increased, with the mean patch size decreasing by 69.2%. The aggregation of water intensified, as its aggregation index increased from 93.31% to 95.41%, while the aggregation of vegetation remained relatively minor, ranging from 89.52% to 90.12%. The annual average temperature, annual average maximum temperature, and annual rainfall days had the strongest correlations with the vegetation landscape pattern indices. Additionally, human activities may have been the primary driver of the landscape pattern evolution of water and sand. The findings of this study have positive implications for the maintenance of the diversity and stability of river ecosystems. [ABSTRACT FROM AUTHOR]

This paper investigates the ability of a relatively low cost, commercially available uncrewed aerial vehicle (UAV), the DJI Mavic 3 Multispectral, to perform cryospheric research. The performance of this UAV, where applicable, is compared to a similar but higher cost system, the DJI Matrice 350, equipped with a Micasense RedEdge-MX Multispectral dual-camera system. The Mavic 3 Multispectral was tested at three field sites: the Lemon Creek Glacier, Juneau Icefield, AK; the Easton Glacier, Mt. Baker, WA; and Bagley Basin, Mt. Baker, WA. This UAV proved capable of mapping the spatial distribution of red snow algae on the surface of the Lemon Creek Glacier using both spectral indices and a random forest supervised classification method. The UAV was able to assess the timing of snowmelt and changes in suncup morphology on snow-covered areas within the Bagley Basin. Finally, the UAV was able to classify glacier surface features using a random forest algorithm with an overall accuracy of 68%. The major advantages of this UAV are its low weight, which allows it to be easily transported into the field, its low cost compared to other alternatives, and its ease of use. One limitation would be the omission of a blue multispectral band, which would have allowed it to more easily classify glacial ice and snow features. [ABSTRACT FROM AUTHOR]

Canopy cover fraction is one of the most important criteria for investigating the crop growth and yield and is one of the input data of most plant models. Canopy cover fraction is an easier measurement than the other methods which id depended on field observations or image processing beyond the visible spectrum. In this study, drone images of the sugar beet field in the cropping season of 2015-2016 and on the four dates from late May to late June at the Lindau center of plant sciences research, Switzerland were used. The research was conducted by six plant discrimination indices and three distinct thresholding algorithms to segment sugar beet vegetation. Then, among the 18 investigated methods, the best 6 methods were evaluated by comparing their values with the ground truth values in 30 different regions of the farm and on four dates from the beginning of the four-leaf stage to the end of the six-leaf stage. Results showed that the ExG, GLI, and RGBVI indices, in combination with the Otsu and RidlerCalvard thresholding algorithms, demonstrate optimal performance in vegetation segmentation. The evaluation statistics of NRMSE and R² for the ExG&Otsu method as the most accurate method were obtained as 5.13 % and 0.96, respectively. Conversely, the RGBVI&RC method exhibits the least accuracy in the initial evaluation, with NRMSE and R² values of 8.18 % and 0.87, respectively. Comparative analysis of statistical indicators showed that the ExG&Otsu and ExG&RC methods with similar performance, displaying the highest correlation with ground truths. Additionally, the GLI&Otsu method consistently demonstrates the lowest error compared to ground truths. [ABSTRACT FROM AUTHOR]

Glaciers are highly responsive to climate variations, yet monitoring them in the rugged Himalaya region poses significant challenges. This study explores the effectiveness and cost-efficiency of using machine learning models integrated with remote sensing data from Google Earth Engine (GEE) to map glacier accumulation (snow) zones in the Pārbati Valley. We tested various machine learning algorithms, including Otsu (image segmentation), K-means and cascade K-means (unsupervised classification), and random forest, minimum distance, smile CART, naive Bayes, robust tree, and support vector machine (supervised classification). Our analysis shows that the Otsu method, along with K-means, cascade K-means, and all supervised classification methods except smile CART and naive Bayes, perform similarly in mapping snowlines. Notably, the Otsu method achieved a maximum predictable error of 57 meters, which is a substantial improvement over traditional methods and indicates higher accuracy in snowline mapping. The study reveals that the regional snowline in the Pārbati Valley ranged between 5048 meters and 5113 meters during the study period. Given its superior performance, the Otsu method is recommended for identifying snowline altitudes across a wide range of glaciers in the Himalayas. [ABSTRACT FROM AUTHOR]

• Landsat bands alone may not give adequate quality of LULC mapping in a heterogeneous landscape. • Remote sensing-derived indices and auxiliary data improve the accuracy of LULC mapping. • LULC maps classified under different classification algorithms have shown a significant discrepancy. Land use/land cover (LULC) information is regarded as one of the most important variables in global change studies. Several LULC classification algorithms are available with different levels of accuracy in LULC mapping under different geographical setups. Furthermore, different remote sensing (RS) based indices and auxiliary data have been reported to have contributed to the accuracy of LULC mapping. Hence, the main aim of this study was to compare the different ML algorithms for the LULC mapping and explicitly assess the potential contribution of different RS-derived indices and auxiliary data on classification accuracy in the Upper Tekeze-Atbarah (UTA) river basin in Ethiopia. The overall classifiers evaluation result revealed that random forest (RF) performed best and followed by K-Nearest Neighbour (KNN), Support Vector Machine (SVM), Artificial Neural Network (ANN), Maximum Likelihood Classification (MLC), and Classification and Regression Tree (CART). Compared to RF, the MLC method showed less accuracy by 16.2% (19.7%) in OA (kappa coefficient) respectively, which showed that the currently emerging ML classifiers contributed to an improvement in LULC mapping. The use of RS-derived indices and DEM as predictors together with the Landsat bands improved the overall accuracy and kappa coefficient by 5.5% and 7% respectively. Furthermore, the discrepancy in the classified LULC map from RF and other classifiers was compared at pixel-level and the result showed a considerable disagreement between the LULC maps. For instance, when the LULC map from RF and KNN are compared, only 80.6% of the area has the same LULC condition. This result reflects the potential discrepancy that could exist in LULC maps from different classifiers. The hydrological simulation under each of the classified map also resulted in a considerable difference in the major water balance components. In a conclusion, given the considerable difference in classifier performance and the potential propagation of errors in LULC maps to further applications such as water resources assessment, it is highly recommended to explicitly evaluate the available classifiers. Users should also harness the power of RS indices and auxiliary datasets for improved LULC mapping. [ABSTRACT FROM AUTHOR]

Copyright of Turkish Journal of Remote Sensing & GIS is the property of Halil Akinci and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Green spaces play a critical role in enhancing the urban environment, improving livability, and providing essential ecosystem services. A city should have at least 25% green space from an environmental and health point of view. However, quantitative estimation is required to assess the extent and pattern of green space changes for proper urban management. The present study aimed to identify and track the changes in urban green spaces within the Dhaka South City Corporation (DSCC) of Bangladesh over a 30-year period (i.e., 1991–2021). Geospatial techniques were utilized to analyze green space dynamics using Landsat 4–5 TM satellite images from 1991, 2001, and 2011 and Landsat 8 images from 2021. Supervised image classification techniques and Normalized Difference Vegetation Index (NDVI) analysis were performed to assess the urban green space dynamics in DSCC. The results of our study revealed a significant 36.5% reduction in vegetation cover in the DSCC area over the study period. In 1991, the green area coverage in DSCC was 46%, indicating a relatively healthy environment. By 2001, this coverage had declined sharply to 21.3%, further decreasing to 19.7% in 2011, and reaching a low of just 9.5% in 2021. The classified maps generated in the study were validated through field observations and Google Earth images. The outcomes of our study will be helpful for policymakers and city planners in developing and applying appropriate policies and plans to preserve and improve urban green spaces in DSCC in Bangladesh and other Asian megacities with high population density. [ABSTRACT FROM AUTHOR]

Vegetation density extraction is influenced by the characteristics of satellite images, vegetation type, classification algorithm, and region, but there is little information about multispectral imaging (MSI). Studying the compatibility of the information content of sensors to replace sensors in areas where there is no easy access to their data is necessary for remote sensing (RS) studies. This study aims to assess the suitability of MSI from Sentinel-2 and Spot-5 satellites for generating pasture density maps. The Middle Kashkan watershed in the Lorestan Province of Iran was the study area. Geometric correction of the images was performed using ground control points (GCP) and the area's digital elevation model, achieving an accuracy of 0.21 pixels or better. Supervised classification techniques including parallelogram, minimal distance, maximum likelihood, and artificial neural network (ANN) algorithms were applied to the primary MSI of each satellite, as well as the integrated image of Spot-5 and the resulting pasture density map. Three density categories were considered: 5–25%, 25–50%, and over 50%. To validate the accuracy of the classification, a ground truth map of the region was created by interpreting a referenced official digital orthophotomosaic image at a scale of 1:40,000. Comparative analysis of the classified images revealed that the Sentinel-2 image with PCA-2-8 band composition and ANN classification algorithm yielded superior results, with an overall accuracy of 65.72% and a kappa coefficient of 0.08, compared to the Spot-5 image with PCA-3-1 band composition and the ANN classification algorithm. Spot-5 satellite images demonstrated greater effectiveness in generating pasture cover maps across the three density categories. These findings suggest that satellite images with suitable spatial and spectral resolution can be effectively utilized for generating accurate pasture density maps and monitoring long-term pasture preservation, particularly in regions characterized by high aerial photography altitudes in pasture areas. This approach holds the potential for effective pasture management and conservation efforts on a global scale. [ABSTRACT FROM AUTHOR]

Abstract Determining the geographical origin of kimchi holds significance because of the considerable variation in quality and price among kimchi products from different regions. This study explored the feasibility of employing Fourier transform near-infrared spectroscopy in conjunction with supervised chemometric techniques to differentiate domestic and imported kimchi products. A total of 30 domestic and 30 imported kimchi products were used to build datasets. Three categories of preprocessing methods such as scattering correction (multiplicative signal correction and standard normal variate), spectral derivatives (the first derivative and the second derivative), and data smoothing (Savitzky–Golay filtering and Norris derivative filtering) were used. K-nearest neighbors, support vector machine, random forest, and partial least squares-discriminant analysis were employed. By appropriately preprocessing spectral data, these four methods successfully distinguished between the two sample groups based on their origin. Notably, the k-nearest neighbors method exhibited exceptional performance, accurately classifying the sample groups irrespective of the preprocessing method employed and swiftly achieving this classification. In comparison, classification and regression tree as well as naïve Bayes methods were outperformed by the aforementioned four classification techniques. Particularly, the efficiency and accuracy of the k-nearest neighbors method make it the most recommended chemometric tool for determining the geographical origins of kimchi.

ABSTRACTMastering the changes in the planting area of crops are critical for formulating sustainable agricultural development strategies. The Landsat 9 satellite provides continuous observational data for crop mapping. It is necessary to evaluate the potential of Landsat 9 images for canola mapping. According to literatures, some canola indices have been proposed in relation to the spectral features of the yellow canola flower, such as the canola ratio index (CRI), normalised difference yellowness index (NDYI), canola index (CI), canola flower index (CFI), normalised difference rapeseed flower index (NRFI) and winter rapeseed index (WRI). However, it is unclear which index has more potential to extract canola based on the Landsat 9 images. Therefore, the potentials of these indices for canola mapping were quantitatively compared by using different classification methods including supervised and unsupervised classification methods. For supervised classification methods and the CFI, the overall accuracy of canola mapping was above 90% and the kappa coefficient was above 0.8. For unsupervised classification methods, CFI also performs best. It was demonstrated that the CFI outperformed the other five indices for canola mapping. It was also confirmed that Landsat 9 images and the CFI exhibit promising potential for canola mapping via quantitative comparison.

Scientists increasingly approach the world through machine learning techniques, but philosophers of science often question their epistemic status. Some philosophers have argued that the use of unsupervised clustering algorithms is more justified than the use of supervised classification, because supervised classification is more biased, and because (parametric) simplicity plays a different and more interesting role in unsupervised clustering. I call these arguments the No-Bias Argument and the Simplicity-Truth Argument. I show how both arguments are fallacious and how, on the contrary, the use of supervised classification is at least as justified as the use of unsupervised clustering. [ABSTRACT FROM AUTHOR]

Many conventional statistical and machine learning methods face challenges when applied directly to high dimensional temporal observations. In recent decades, Functional Data Analysis (FDA) has gained widespread popularity as a framework for modeling and analyzing data that are, by their nature, functions in the domain of time. Although supervised classification has been extensively explored in recent decades within the FDA literature, ensemble learning of functional classifiers has only recently emerged as a topic of significant interest. Thus, the latter subject presents unexplored facets and challenges from various statistical perspectives. The focal point of this paper lies in the realm of ensemble learning for functional data and aims to show how different functional data representations can be used to train ensemble members and how base model predictions can be combined through majority voting. The so-called Functional Voting Classifier (FVC) is proposed to demonstrate how different functional representations leading to augmented diversity can increase predictive accuracy. Many real-world datasets from several domains are used to display that the FVC can significantly enhance performance compared to individual models. The framework presented provides a foundation for voting ensembles with functional data and can stimulate a highly encouraging line of research in the FDA context. [ABSTRACT FROM AUTHOR]

The research subject is the application of geographic information systems (GIS) in assessing land suitability for agriculture in the Sana River Basin in Bosnia and Herzegovina. The aim of the research is to apply the analytic hierarchy process (AHP) in identifying suitable areas for agricultural production. Within the AHP framework, the following factors were considered: pedology, land use, elevation, slope, aridity index, and distance from rivers. The results of the suitability assessment underwent reclassification (RP) and cluster analysis processes (CAPs). It was found that very unsuitable land (1) covers an area of 0.15% (RP) or 5.83% (CAP), unsuitable land (2) covers 3.44% (RP) or 17.52% (CAP), conditionally suitable land (3) covers 32.11% or 28.47% (CAP), suitable land (4) covers 56.29% or 28.57% (CAP), and very suitable land (5) covers 7.98% (RP) or 19.59% (CAP). At the study area level, a supervised classification process was conducted to identify land use classes: meadows/pastures, water, forest, agricultural, and built-up areas. RP and CAP results were overlaid with supervised classification results to determine the amount of land used for agricultural purposes within each suitability class. It was determined that currently, for agricultural purposes, 0.04 km2 (RP) or 0.88 km2 (CAP) of very unsuitable land (1) is used, 0.41 km2 (RP) or 7.28 km2 (CAP) of unsuitable land (2), 15.75 km2 (RP) or 27.52 km2 (CAP) of conditionally suitable land (3), 185.15 km2 (RP) or 107.06 km2 (CAP) of suitable land (4), and 42.99 km2 (RP) or 101.65 km2 (CAP) of very suitable land (5). The research findings hold substantial importance in elucidating both the potential and constraints of land use practices as a vital natural resource within agriculture. They also have practical importance for relevant institutions in terms of agricultural sector development and making timely land use planning decisions for sustainable development.

Abstract Vegetation density extraction is influenced by the characteristics of satellite images, vegetation type, classification algorithm, and region, but there is little information about multispectral imaging (MSI). Studying the compatibility of the information content of sensors to replace sensors in areas where there is no easy access to their data is necessary for remote sensing (RS) studies. This study aims to assess the suitability of MSI from Sentinel-2 and Spot-5 satellites for generating pasture density maps. The Middle Kashkan watershed in the Lorestan Province of Iran was the study area. Geometric correction of the images was performed using ground control points (GCP) and the area's digital elevation model, achieving an accuracy of 0.21 pixels or better. Supervised classification techniques including parallelogram, minimal distance, maximum likelihood, and artificial neural network (ANN) algorithms were applied to the primary MSI of each satellite, as well as the integrated image of Spot-5 and the resulting pasture density map. Three density categories were considered: 5–25%, 25–50%, and over 50%. To validate the accuracy of the classification, a ground truth map of the region was created by interpreting a referenced official digital orthophotomosaic image at a scale of 1:40,000. Comparative analysis of the classified images revealed that the Sentinel-2 image with PCA-2-8 band composition and ANN classification algorithm yielded superior results, with an overall accuracy of 65.72% and a kappa coefficient of 0.08, compared to the Spot-5 image with PCA-3-1 band composition and the ANN classification algorithm. Spot-5 satellite images demonstrated greater effectiveness in generating pasture cover maps across the three density categories. These findings suggest that satellite images with suitable spatial and spectral resolution can be effectively utilized for generating accurate pasture density maps and monitoring long-term pasture preservation, particularly in regions characterized by high aerial photography altitudes in pasture areas. This approach holds the potential for effective pasture management and conservation efforts on a global scale.

Spectral indices developed to extract features from satellite images are simple and fast methods that reduce processing time compared to traditional satellite image classification.In this paper, the effectiveness of the normalized difference building index (NDBI), the normalized difference vegetation index (NDVI), and the Normalized Difference Water Index (NDWI) were evaluated in land cover mapping and detecting its changes in the period from 2013 to 2023 in Fayoum Governorate, Egypt, using Landsat 8-OLI images. The results of supervised classification showed a decrease in green areas between 2013 and 2023 by 76.03 square kilometers, with a slight decrease in the areas occupied by water amounting to 3.8 square kilometers and an increase in built-up areas by 79.83 square kilometers, at the expense of green lands. On the other hand, the results of using spectral indices showed a decrease in green areas between 2013 and 2023 by 91.12 square kilometers, with a slight decrease in the areas occupied by water amounting to 3.35 square kilometers. Meanwhile, we noticed an increase in built-up areas by 94.47 square kilometers at the expense of green areas. The results showed a general convergence in the changes in the studied classes during the study period, with a great convergence in the change in the area of the water bodies resulted from the classification and from the NDWI and a convergence in the effectiveness of both the NDVI and NDBI.

With the increased availability of chemical data in public databases, innovative techniques and algorithms have emerged for the analysis, exploration, visualization, and extraction of information from these data. One such technique is chemical grouping, where chemicals with common characteristics are categorized into distinct groups based on physicochemical properties, use, biological activity, or a combination. However, existing tools for chemical grouping often require specialized programming skills or the use of commercial software packages. To address these challenges, we developed a user-friendly chemical grouping workflow implemented in KNIME, a free, open-source, low/no-code, data analytics platform. The workflow serves as an all-encompassing tool, expertly incorporating a range of processes such as molecular descriptor calculation, feature selection, dimensionality reduction, hyperparameter search, and supervised and unsupervised machine learning methods, enabling effective chemical grouping and visualization of results. Furthermore, we implemented tools for interpretation, identifying key molecular descriptors for the chemical groups, and using natural language summaries to clarify the rationale behind these groupings. The workflow was designed to run seamlessly in both the KNIME local desktop version and KNIME Server WebPortal as a web application. It incorporates interactive interfaces and guides to assist users in a step-by-step manner. We demonstrate the utility of this workflow through a case study using an eye irritation and corrosion dataset. Scientific contributions This work presents a novel, comprehensive chemical grouping workflow in KNIME, enhancing accessibility by integrating a user-friendly graphical interface that eliminates the need for extensive programming skills. This workflow uniquely combines several features such as automated molecular descriptor calculation, feature selection, dimensionality reduction, and machine learning algorithms (both supervised and unsupervised), with hyperparameter optimization to refine chemical grouping accuracy. Moreover, we have introduced an innovative interpretative step and natural language summaries to elucidate the underlying reasons for chemical groupings, significantly advancing the usability of the tool and interpretability of the results. [ABSTRACT FROM AUTHOR]

Objective The focus of this study is on providing tools to enable researchers and practitioners to screen for dyslexia in adults entering university. The first aim is to validate and provide diagnostic properties for a set of seven tests including a 1-min word reading test, a 2-min pseudoword reading test, a phonemic awareness test, a spelling test, the Alouette reading fluency test, a connected-text reading fluency test, and the self-report Adult Reading History Questionnaire (ARHQ). The second, more general, aim of this study was to devise a standardized and confirmatory procedure for dyslexia screening from a subset of the initial seven tests. We used conditional inference tree analysis, a supervised machine learning approach to identify the most relevant tests, cut-off scores, and optimal order of test administration. Method A combined sample of 60 university students with dyslexia (clinical validation group) and 65 university students without dyslexia (normative group) provided data to determine the diagnostic properties of these tests including sensitivity, specificity, and cut-off scores. Results Results showed that combinations of four tests (ARHQ, text reading fluency, phonemic awareness, pseudoword reading) and their relative conditional cut-off scores optimize powerful discriminatory screening procedures for dyslexia, with an overall classification accuracy of approximately 90%. Conclusions The novel use of the conditional inference tree methodology explored in the present study offered a way of moving toward a more efficient screening battery using only a subset of the seven tests examined. Both clinical and theoretical implications of these findings are discussed. [ABSTRACT FROM AUTHOR]

Spectral indices developed to extract features from satellite images are simple and fast methods that reduce processing time compared to traditional satellite image classification. In this paper, the effectiveness of the normalized difference building index (NDBI), the normalized difference vegetation index (NDVI), and the Normalized Difference Water Index (NDWI) were evaluated in land cover mapping and detecting its changes in the period from 2013 to 2023 in Fayoum Governorate, Egypt, using Landsat 8-OLI images. The results of supervised classification showed a decrease in green areas between 2013 and 2023 by 76.03 square kilometers, with a slight decrease in the areas occupied by water amounting to 3.8 square kilometers and an increase in built-up areas by 79.83 square kilometers, at the expense of green lands. On the other hand, the results of using spectral indices showed a decrease in green areas between 2013 and 2023 by 91.12 square kilometers, with a slight decrease in the areas occupied by water amounting to 3.35 square kilometers. Meanwhile, it was noticed that, increasing in the built-up areas by 94.47 square kilometers at the expense of green areas. The results showed a general convergence in the changes in the studied classes during the study period, with a great convergence in the change in the area of the water bodies resulted from the classification and from the NDWI and a convergence in the effectiveness of both the NDVI and NDBI. Finally, the effectiveness of the spectral indices in land cover mapping using check points was evaluated. The results showed a high percentage of the number of correctly identified check points for the NDWI index, with this percentage being noticeably low in the case of the NDVI and NDBI. [ABSTRACT FROM AUTHOR]

Rodent-infested bald spots are crucial indicators of rodent infestation in grasslands. Leveraging Unmanned Aerial Vehicle (UAV) remote sensing technology for discerning detrimental bald spots among plateau pikas has significant implications for assessing associated ecological hazards. Based on UAV-visible light imagery, we classified and recognized the characteristics of plateau pika habitats with five supervised classification algorithms, i.e., minimum distance classification (MinD), maximum likelihood classification (ML), support vector machine classification (SVM), Mahalanobis distance classification (MD), and neural network classification (NN). The accuracy of the five methods was evaluated using a confusion matrix. Results showed that NN and SVM exhibited superior performance than other methods in identifying and classifying features indicative of plateau pika habitats. The mapping accuracy of NN for grassland and bald spots was 98.1% and 98.5%, respectively, with corresponding user accuracy was 98.8% and 97.7%. The overall model accuracy was 98.3%, with a Kappa coefficient of 0.97, reflecting minimal misclassification and omission errors. Through practical verification, NN exhibited good stability. In conclusion, the neural network method was suitable for identifying rodent-damaged bald spots within alpine meadows. [ABSTRACT FROM AUTHOR]

Introduction: Growing grass-legume mixtures for forage production improves both yield productivity and nutritional quality, while also benefiting the environment by promoting species biodiversity and enhancing soil fertility (through nitrogen fixation). Consequently, assessing legume proportions in grass-legume mixed swards is essential for breeding and cultivation. This study introduces an approach for automated classification and mapping of species in mixed grass-clover swards using object-based image analysis (OBIA). Methods: The OBIA procedure was established for both RGB and ten band multispectral (MS) images capturedby an unmanned aerial vehicle (UAV). The workflow integrated structural (canopy heights) and spectral variables (bands, vegetation indices) along with a machine learning algorithm (Random Forest) to perform image segmentation and classification. Spatial k-fold cross-validation was employed to assess accuracy. Results and discussion: Results demonstrated good performance, achieving an overall accuracy of approximately 70%, for both RGB and MS-based imagery, with grass and clover classes yielding similar F1 scores, exceeding 0.7 values. The effectiveness of the OBIA procedure and classification was examined by analyzing correlations between predicted clover fractions and dry matter yield (DMY) proportions. This quantification revealed a positive and strong relationship, with R2 values exceeding 0.8 for RGB and MS-based classification outcomes. This indicates the potential of estimating (relative) clover coverage, which could assist breeders but also farmers in a precision agriculture context. [ABSTRACT FROM AUTHOR]

With the advent and improvement of ontological dictionaries (WordNet, Babelnet), the use of synsets-based text representations is gaining popularity in classification tasks. More recently, ontological dictionaries were used for reducing dimensionality in this kind of representation (e.g., Semantic Dimensionality Reduction System (SDRS) (Vélez de Mendizabal et al., 2020)). These approaches are based on the combination of semantically related columns by taking advantage of semantic information extracted from ontological dictionaries. Their main advantage is that they not only eliminate features but can also combine them, minimizing (low-loss) or avoiding (lossless) the loss of information. The most recent (and accurate) techniques included in this group are based on using evolutionary algorithms to find how many features can be grouped to reduce false positive (FP) and false negative (FN) errors obtained. The main limitation of these evolutionary-based schemes is the computational requirements derived from the use of optimization algorithms. The contribution of this study is a new lossless feature reduction scheme exploiting information from ontological dictionaries, which achieves slightly better accuracy (specially in FP errors) than optimization-based approaches but using far fewer computational resources. Instead of using computationally expensive evolutionary algorithms, our proposal determines whether two columns (synsets) can be combined by observing whether the instances included in a dataset (e.g., training dataset) containing these synsets are mostly of the same class. The study includes experiments using three datasets and a detailed comparison with two previous optimization-based approaches. [ABSTRACT FROM AUTHOR]

Given the growing urge for plastic management and regulation in the world, recent studies have investigated the problem of plastic material identification for correct classification and disposal. Recent works have shown the potential of machine learning techniques for successful microplastics classification using Raman signals. Classification techniques from the machine learning area allow the identification of the type of microplastic from optical signals based on Raman spectroscopy. In this paper, we investigate the impact of high-frequency noise on the performance of related classification tasks. It is well-known that classification based on Raman is highly dependent on peak visibility, but it is also known that signal smoothing is a common step in the pre-processing of the measured signals. This raises a potential trade-off between high-frequency noise and peak preservation that depends on user-defined parameters. The results obtained in this work suggest that a linear discriminant analysis model cannot generalize properly in the presence of noisy signals, whereas an error-correcting output codes model is better suited to account for inherent noise. Moreover, principal components analysis (PCA) can become a must-do step for robust classification models, given its simplicity and natural smoothing capabilities. Our study on the high-frequency noise, the possible trade-off between pre-processing the high-frequency noise and the peak visibility, and the use of PCA as a noise reduction technique in addition to its dimensionality reduction functionality are the fundamental aspects of this work. [ABSTRACT FROM AUTHOR]

Large language models (LLMs) have the ability to generate text by stringing together words from their extensive training data. The leading AI text generation tool built on LLMs, ChatGPT, has quickly grown a vast user base since its release, but the domains in which it is being heavily leveraged are not yet known to the public. To understand how generative AI is reshaping print media and the extent to which it is being implemented already, methods to distinguish human-generated text from that generated by AI are required. Since college students have been early adopters of ChatGPT, we sought to study the presence of generative AI in newspaper articles written by collegiate journalists. To achieve this objective, an accurate AI detection model is needed. Herein, we analyzed university newspaper articles from different universities to determine whether ChatGPT was used to write or edit the news articles. We developed a detection model using classical machine learning and used the model to detect AI usage in the news articles. The detection model showcased a 93% accuracy in the training data and had a similar performance in the test set, demonstrating effectiveness in AI detection above existing state-of-the-art detection tools. Finally, the model was applied to the task of searching for generative AI usage in 2023, and we found that ChatGPT was not used to revise articles to any appreciable measure to write university news articles at the schools we studied. [ABSTRACT FROM AUTHOR]

Hydrology is an important environmental factor for the evolution of wetland landscape patterns. In the past 20 years, Poyang Lake, the largest freshwater lake in China, has experienced significant inundation shrinkage and water level decrease, posing a significant threat to the local vegetation community. To explore the potential relationship between aquatic vegetation and hydrological processes in the recent hydrological situation, in this study, the landscape patterns of aquatic vegetation communities in Poyang Lake were studied using time-series Landsat remote sensing images and a support vector machine classifier. The stepwise regression analysis method was adopted to analyze the relationship between the vegetation area and hydrological factors. The results indicated that the area of submerged and emergent vegetation in the entire lake decreased significantly from 2001 to 2017, whereas the area of moist vegetation showed a remarkably increasing trend. The average distribution elevation of the submerged vegetation increased by 0.06 m per year. The corresponding landscape patterns showed that the degree of fragmentation of aquatic vegetation communities in Poyang Lake increased. Several hydrological factors were selected to quantify the potential impact of water level fluctuations. The correlation analysis results indicated that hydrological conditions during the rising- and high-water periods may be the key factors affecting the area of aquatic vegetation. This study systematically investigated the evolution of vegetation communities in Poyang Lake wetlands over the past two decades, which contributes to the protection and management of this unique ecosystem. [ABSTRACT FROM AUTHOR]

Copyright of Remote Sensing for Natural Resources is the property of Remote Sensing for Natural Resources Editorial Office and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Pine wilt disease (PWD) is a highly destructive infectious disease that affects pine forests. Therefore, an accurate and effective method to monitor PWD infection is crucial. However, the majority of existing technologies can detect PWD only in the later stages. To curb the spread of PWD, it is imperative to develop an efficient method for early detection. We presented an early stage detection method for PWD utilizing UAV remote sensing, hyperspectral image reconstruction, and SVM classification. Initially, employ UAV to capture RGB remote sensing images of pine forests, followed by labeling infected plants using these images. Hyperspectral reconstruction networks, including HSCNN+, HRNet, MST++, and a self-built DW3D network, were employed to reconstruct the RGB images obtained from remote sensing. This resulted in hyperspectral images in the 400-700nm range, which were used as the dataset of early PWD detection in pine forests. Spectral reflectance curves of infected and uninfected plants were extracted. SVM algorithms with various kernel functions were then employed to detect early pine wilt disease. The results showed that using SVM for early detection of PWD infection based on reconstructed hyperspectral images achieved the highest accuracy, enabling the detection of PWD in its early stage. Among the experiments, MST++, DW3D, HRNet, and HSCNN+ were combined with Poly kernel SVM performed the best in terms of cross-validation accuracy, achieving 0.77, 0.74, 0.71, and 0.70, respectively. Regarding the reconstruction network parameters, the DW3D network had only 0.61M parameters, significantly lower than the MST++ network, which had the highest reconstruction accuracy with 1.6M parameters. The accuracy was improved by 27% compared to the detection results obtained using RGB images. This paper demonstrated that the hyperspectral reconstruction-poly SVM model could effectively detect the Early stage of PWD. In comparison to UAV hyperspectral remote sensing methods, the proposed method in this article offers a same precision, but a higher operational efficiency and cost-effectiveness. It also enables the detection of PWD at an earlier stage compared to RGB remote sensing, yielding more accurate and reliable results.

In Italy, irrigated agriculture is often managed by Reclamation Consortia, but they generally lack the proper tools for monitoring the irrigation water requirements (IWR), forbidding the required sustainability level by the European Water Framework Directive. In this context, the study aims at monitoring the IWR of citrus orchards of a Sicilian irrigation district by implementing a satellite-based methodological approach, during the irrigation seasons 2019 and 2020. Firstly, neural networks were implemented to map the citrus orchards, by using Normalized Difference Vegetation Index time series as input, and obtaining accuracy values of 94% and 87%, in 2019 and 2020, respectively. Then, the satellite-based ArcDualKc model was used to estimate crop evapotranspiration (ETc) over the identified citrus orchards. The estimated ETc rates were validated at the farm scale in terms of irrigation volumes and compared to those obtained by the traditional FAO-56 approach. Then, the spatially distributed irrigation volumes estimated at district level were compared with those declared by the Reclamation Consortium, obtaining absolute error values of 3.28 Mm3 (294%) and 7.08 Mm3 (647%) for the years 2019 and 2020, respectively. The results of the study confirmed the usefulness of the satellite-based methodological approach for determining spatial distributed IWR estimates.

One significant challenge in sentiment analysis is the presence of negation, which reverses the meanings of sentences, transforming positive statements into negative ones and impacting the sentiment conveyed in the text. This issue is particularly pronounced in Arabic, a language known for its complex morphology. Detecting negation is crucial for enhancing sentiment analysis performance and various natural language processing applications. This paper presents an approach for automatically detecting negation in user-generated Arabic hotel reviews through lexical and structural features. It comprises several stages: data collection, text pre-processing, feature extraction, supervised learning classification, and evaluation. The study employed multiple supervised classification techniques, including naïve Bayes, random forest, logistic regression, support vector machines, and deep learning, to analyse lexical and structural features extracted from the dataset. The results of the experiments yielded promising outcomes, demonstrating the feasibility of the approach for practical applications. The classifiers exhibited highly comparable performance in identifying negation, with only marginal deviations in their performance metrics. Notably, the deep learning classifier consistently emerged as the top performer, achieving an exceptionally high overall accuracy rate of 99.24 percent, surpassing established benchmarks in Arabic text processing and underscoring its potential for practical applications. These findings hold significant implications for advancing Arabic text processing, particularly in sentiment analysis and related NLP tasks. The high accuracy of 99.24 percent achieved by the deep learning classifier highlights its robustness in accurately detecting negation, a critical challenge in sentiment analysis. This classifier performance demonstrates the potential to be integrated into real-world applications, such as automated review systems and opinion mining tools, where accurate sentiment interpretation is essential.

The rapid increase in population and urban development are exacerbating the transformation of natural environments into unnatural forms. While detailed assessment of the environment is beneficial for efficient ecosystem system management, it can also be time and resources-consuming. This study aimed to map and quantify the spatio-temporal changes in land use and land cover (LULC) using the Ouémé River Basin as a case study. The supervised classification in Google Earth Engine (GEE) cloud-computing platform was employed to distinguish Landsat images for 1986, 2000, 2015 and 2023 into forest areas, settlements/bare lands, savanna areas (woodlands), agricultural lands and water bodies. Analysis of the LULC changes revealed that savanna areas and woodlands which were predominant in the basin in 1986 have steadily declined by 24 % in area in 2023. Forest areas have diminished by 4.3 % at an annual rate of 4 %. Agricultural lands have however grown exponentially by 28 % since 1986, with a more rapid increase between 2015 and 2023 at an annual rate of 3.7 %, driven by rising food demand due to population growth within and around the basin. Settlements and bare areas tripled in area, reflecting a similar trend to Benin's urban population growth. Accuracy statistics of the LULC classification showed overall accuracy and kappa statistic values above 90 % and 86 %, respectively, indicating the admirable performance and reliability of the Simple Composite Landsat algorithm for image composition, and the Random Forest Classifier for LULC classification approach applied in this study. The approach also demonstrates the robustness and potential of LULC mapping in large and complex ecosystems using the GEE cloud-based remote sensing tool, which is underutilized in the study area. Overall, the LULC trends provide beneficial insights useful to policy-makers and any other stakeholders involved in sustainable ecosystem management planning in the basin.

The subject of this article is land cover classification based on geospatial data. The supervised classification methods are appropriate for most of the thematic tasks of remote sensing because they provide the opportunity to set the characteristics of the initial classes in the form of a training sample set, in contrast to unsupervised methods. There are many approaches to processing such a set; however, their common disadvantage is that they do not consider the factor of training sample separability. This characteristic indicates the extent to which signatures representing different classes do not overlap. A low degree of separability is inherent in high-level training sample mixing. Thus, separability affects classification accuracy. One possible ways to increase separability is training sample clustering. Considering the above, the goal of this study is to develop a training sample clustering technique to improve land cover classification accuracy by increasing the separability of training samples. The tasks of this work are as follows: 1) develop a method for training sample separability assessment; 2) develop a training sample clustering technique based on training sample separability; 3) test the effectiveness of the developed technique by applying it to experimental land cover classification. In the experiments, two land cover classifications were obtained for each of the two selected study areas (i.e., one before and another after training sample clustering. Six land cover classes were defined for each experiment. The training samples were selected for each class. Conclusions. After the application of the developed technique, an increase in the separability of the training samples was evidenced by the developed separability index. In turn, this approach led to an improvement in land cover classification. For the first experiment, this was evidenced by an increase in the overall accuracy and kappa coefficient by 20% (from 63 to 83%) and 21% (from 60% to 81%), respectively. In the second experiment, the increase was 4% (from 77% to 81%) and 5% (from 66% to 71%), respectively.

Abstract Monitoring and understanding Land Use/Land Cover (LU/LC) is critical for sustainable development, as it can impact various environmental, social, and economic systems. For example, deforestation and land degradation can lead to soil erosion, loss of biodiversity, and greenhouse gas emissions, affecting the quality of soil, air, and water resources. The present research examined changes in (LU/LC) within the underdeveloped regions of Balochistan and Sindh provinces, which are situated in Pakistan. In order to monitor temporal variations of LU/LC, we employed Geographic Information System (GIS) technique, to conduct an analysis of satellite imagery obtained from the Landsat 8 Operational Land Imager (OLI) during the time period spanning from 2013 to 2023. In order to obtain an accurate LU/LC classification, we used principal component analysis (PCA) and a supervised classification approach using the maximum likelihood algorithm (MLC). According to the results of our study, there was a decrease in the extent of water bodies (− 593.24 km2) and vegetation (− 68.50 km2) by − 3.43% and − 0.40% respectively. In contrast, the area occupied by settlements in the investigated region had a 2.23% rise, reaching a total of 385.66 square kilometers. Similarly, the extent of barren land also expanded by 1.60%, encompassing a total area of 276.04 square kilometers, during the course of the last decade. The overall accuracy (94.25% and 95.75%) and K value (91.75% and 93.50%) were achieved during the year 2013 and 2023 respectively. The enhancement of agricultural output in Pakistan is of utmost importance in order to improve the income of farmers, mitigate food scarcity, stimulate economic growth, and facilitate the expansion of exports. To enhance agricultural productivity, it is recommended that the government undertake targeted initiatives that aimed at enhancing water infrastructure and optimizing land use to foster a sustainable ecological framework. Integrating the sustainable ecological framework provides a foundation for informed decision-making and effective resource management. By identifying areas of urban expansion, agricultural intensification, or alterations in natural LU/LC, stakeholders can design targeted conservation strategies, mitigating potential environmental degradation and promoting biodiversity conservation. In conclusion, the integration of GIS and Remote Sensing (RS) may effectively facilitate the monitoring of land use patterns over a period of time. This combined approach offers valuable insights and recommendations for the judicious and optimal management of land resources, as well as informing policy decisions.

This research seeks to assess historically the urban expansion of Agadir city in Morocco within the 35-year timespan (1984-2019), and the influence of those changes on the regulating services of Agadir. It was achieved by applying Support Vector Machine supervised (SVM) algorithm on each Landsat products to derive Land Use/Land Cover (LULC) maps. High accuracy assessment values were obtained for all Landsat classified maps. Spectral radiance model was exploited successfully to highlight the spatiotemporal changes of thermal behavior of city surfaces. Terrestrial carbon dynamics of Agadir LULC was evaluated by applying a process-based carbon model. Outcomes of this paper revealed an important urban expansion within the 35-year timespan with an important loss of vegetation and bare land. This urban evolution impacts the Land Surface Temperature (LST) and caused carbon storage loss that contributes to local climate change. These findings could assist policy-makers to characterize a sustainable evolution of urban area, especially, to interpret how and where LULC changes might alter the dynamics of climate regulation and ecosystem services.

Abstract Natural products are a diverse class of compounds with promising biological properties, such as high potency and excellent selectivity. However, they have different structural motifs than typical drug-like compounds, e.g., a wider range of molecular weight, multiple stereocenters and higher fraction of sp 3 -hybridized carbons. This makes the encoding of natural products via molecular fingerprints difficult, thus restricting their use in cheminformatics studies. To tackle this issue, we explored over 30 years of research to systematically evaluate which molecular fingerprint provides the best performance on the natural product chemical space. We considered 20 molecular fingerprints from four different sources, which we then benchmarked on over 100,000 unique natural products from the COCONUT (COlleCtion of Open Natural prodUcTs) and CMNPD (Comprehensive Marine Natural Products Database) databases. Our analysis focused on the correlation between different fingerprints and their classification performance on 12 bioactivity prediction datasets. Our results show that different encodings can provide fundamentally different views of the natural product chemical space, leading to substantial differences in pairwise similarity and performance. While Extended Connectivity Fingerprints are the de-facto option to encoding drug-like compounds, other fingerprints resulted to match or outperform them for bioactivity prediction of natural products. These results highlight the need to evaluate multiple fingerprinting algorithms for optimal performance and suggest new areas of research. Finally, we provide an open-source Python package for computing all molecular fingerprints considered in the study, as well as data and scripts necessary to reproduce the results, at https://github.com/dahvida/NP_Fingerprints .

Abstract The challenge of urban growth and land use land cover (LULC) change is particularly critical in developing countries. The use of remote sensing and GIS has helped to generate LULC thematic maps, which have proven immensely valuable in resource and land-use management, facilitating sustainable development by balancing developmental interests and conservation measures. The research utilized socio-economic and spatial variables such as slope, elevation, distance from streams, distance from roads, distance from built-up areas, and distance from the center of town to determine their impact on the LULC of 2016 and 2019. The research integrates Artificial Neural Network with Cellular Automta to forecast and establish potential land use changes for the years 2025 and 2040. Comparison between the predicted and actual LULC maps of 2022 indicates high agreement with kappa hat of 0.77 and a percentage of correctness of 86.83%. The study indicates that the built-up area will increase by 8.37 km2 by 2040, resulting in a reduction of 7.08 km2 and 1.16 km2 in protected and agricultural areas, respectively. These findings will assist urban planners and lawmakers to adopt management and conservation strategies that balance urban expansion and conservation of natural resources leading to the sustainable development of the cities.

We present the first major release of the Classification Algorithms Comparison Pipeline (CACP). The proposed software enables one to compare newly developed classification algorithms in Python with other classifiers to evaluate classification performance and ensure both outcomes’ reproducibility and statistical reliability. CACP simplifies and accelerates the entire classifier evaluation process considerably and helps prepare the professional documentation of the experiments conducted. The upgrade introduces enhancements to existing tools and adds new features: (1) - support for River machine learning library datasets in incremental learning, (2) - capability to include user-defined datasets, (3) - use of River classifiers for incremental learning, (4) - use of River metrics for incremental learning, (5) - flexibility to create user-defined metrics, (6) - record-by-record testing for incremental learning, (7) - enhanced summary of incremental testing results with dynamic visualization of the learning process, (8) - Graphical User Interface (GUI).

ABSTRACTThe current land cover (LC) mapping paradigm relies on automatic satellite imagery classification, predominantly through supervised methods, which depend on training data to calibrate classification algorithms. Hence, training data have a critical influence on classification accuracy. Although research on specific aspects of training data in the LC classification context exists, a study that organizes and synthetizes the multiplicity of aspects and findings of these researches is needed. In this article, we review the training data used for LC classification of satellite imagery. A protocol of identification and selection of relevant documents was followed, resulting in 114 peer-reviewed studies included. Main research topics were identified and documents were characterized according to their contribution to each topic, which allowed uncovering subtopics and categories and synthetizing the main findings regarding different aspects of the training dataset. The analysis found four research topics, namely construction of the training dataset, sample quality, sampling design and advanced learning techniques. Subtopics included sample collection method, sample cleaning procedures, sample size, sampling method, class balance and distribution, among others. A summary of the main findings and approaches provided an overview of the research in this area, which may serve as a starting point for new LC mapping initiatives.

Many segmentation or change‐point detection methods for homogenizing climate time series compare candidate station data with reference data to eliminate common climate signals and more efficiently detect spurious, non‐climatic changes. One drawback is that it is difficult to decide whether the detected change‐point is due to the candidate series or to the reference. A so‐called attribution procedure is typically applied in a post‐processing step for each detected change‐point. This article describes a new statistical method for the attribution of change‐points detected in Global Navigation Satellite System (GNSS) minus reanalysis series of integrated water vapour. It requires at least one nearby station with similar GNSS and reanalysis data. Six series of differences are formed from the four base series (BS) and are tested for a significant jump at the time of the change‐point detected in the candidate station. The six test results are analysed with a statistical predictive rule to attribute the change‐point to one, or several, of the four BS. Original aspects of our method are: (1) the significance test, which is based on a generalized linear regression approach, taking both heteroscedasticity and autocorrelation into account; (2) the predictive rule, which uses a machine learning method and is constructed from the test results obtained with the real data by using a resampling strategy. Four popular machine learning methods have been compared using cross‐validation and the best one was applied to a real data set (49 main stations with 114 change‐points). The results depend on the choice of the test significance level and the aggregation method combining the prediction results when several nearby stations are available. We find that 62% of the change‐points are attributed to GNSS, 19% to the reanalysis, and 10% are due to coincident detections. [ABSTRACT FROM AUTHOR]