Classification Map Research Articles

Polarimetric synthetic aperture radar image classification for accurate landcover mapping with advanced encoder–decoder networks using multi-dimensional probabilistic voting ensemble

Polarimetric synthetic aperture radar image classification for accurate landcover mapping with advanced encoder–decoder networks using multi-dimensional probabilistic voting ensemble

Unsupervised PolSAR Image Classification Based on Superpixel Pseudo-Labels and a Similarity-Matching Network

Supervised polarimetric synthetic aperture radar (PolSAR) image classification demands a large amount of precisely labeled data. However, such data are difficult to obtain. Therefore, many unsupervised methods have been proposed for unsupervised PolSAR image classification. The classification maps of unsupervised methods contain many high-confidence samples. These samples, which are often ignored, can be used as supervisory information to improve classification performance on PolSAR images. This study proposes a new unsupervised PolSAR image classification framework. The framework combines high-confidence superpixel pseudo-labeled samples and semi-supervised classification methods. The experiments indicated that this framework could achieve higher-level effectiveness in unsupervised PolSAR image classification. First, superpixel segmentation was performed on PolSAR images, and the geometric centers of the superpixels were generated. Second, the classification maps of rotation-domain deep mutual information (RDDMI), an unsupervised PolSAR image classification method, were used as the pseudo-labels of the central points of the superpixels. Finally, the unlabeled samples and the high-confidence pseudo-labeled samples were used to train an excellent semi-supervised method, similarity matching (SimMatch). Experiments on three real PolSAR datasets illustrated that, compared with the excellent RDDMI, the accuracy of the proposed method was increased by 1.70%, 0.99%, and 0.8%. The proposed framework provides significant performance improvements and is an efficient method for improving unsupervised PolSAR image classification.

Constructing Soil–Landscape Units Based on Slope Position and Land Use to Improve Soil Prediction Accuracy

Topography is one of the dominant factors in regional soil formation and development. Soil distribution has a certain pattern from high to low in space, and this pattern has a high degree of consistency with slope position. Most of the current research on soil mapping uses landscape types generated by existing methods directly as environmental covariates, and there are few landscape classification methods specifically oriented toward soil surveys. There is rarely any research on landform classification using relative slope position (RSP) and elevation. Therefore, we designed a landform classification method based on RSP and elevation, Terrainforms (TF), and combined the landform type with land use type to construct soil–landscape units for soil type and attribute spatial prediction. In this study, two commonly used landform classification methods, Geomorphons and Landforms, were also used to compare with this design method. It was found that the constructed soil–landscape units had a high consistency with the soil spatial distribution. The landform types based on RSP and elevation obtained the second-highest prediction accuracy in both soil type and soil organic carbon (SOC), and the constructed soil–landscape types obtained the highest prediction accuracy. The results show that the landform classification method based on RSP and elevation is not easily limited by the analysis scale, and is an efficient and accurate landform classification method. The TF landform type and its constructed soil–landscape types can be used as an important environmental variable in soil prediction and sampling, which can provide some guidance and reference for landform classification and digital soil mapping.

MSMTRIU-Net: Deep Learning-Based Method for Identifying Rice Cultivation Areas Using Multi-Source and Multi-Temporal Remote Sensing Images

Identifying rice cultivation areas in a timely and accurate manner holds great significance in comprehending the overall distribution pattern of rice and formulating agricultural policies. The remote sensing observation technique provides a convenient means to monitor the distribution of rice cultivation areas on a large scale. Single-source or single-temporal remote sensing images are often used in many studies, which makes the information of rice in different types of images and different growth stages hard to be utilized, leading to unsatisfactory identification results. This paper presents a rice cultivation area identification method based on a deep learning model using multi-source and multi-temporal remote sensing images. Specifically, a U-Net based model is employed to identify the rice planting areas using both the Landsat-8 optical dataset and Sentinel-1 Polarimetric Synthetic Aperture Radar (PolSAR) dataset; to take full into account of the spectral reflectance traits and polarimetric scattering traits of rice in different periods, multiple image features from multi-temporal Landsat-8 and Sentinel-1 images are fed into the network to train the model. The experimental results on China’s Sanjiang Plain demonstrate the high classification precisions of the proposed Multi-Source and Multi-Temporal Rice Identification U-Net (MSMTRIU-NET) and that inputting more information from multi-source and multi-temporal images into the network can indeed improve the classification performance; further, the classification map exhibits greater continuity, and the demarcations between rice cultivation regions and surrounding environments reflect reality more accurately.

A Comparison of the Efficacy of Fuzzy Overlay and Random Forest Classification for Mapping and Shaping Perceptions of the Post-Mining Landscape of Gauteng, South Africa

Post-mining landscapes are multifaceted, comprising multiple characteristics, more so in big metropolitan regions such as Gauteng, South Africa. This paper evaluates the efficacy of Fuzzy overlay and Random Forest classification for integrating and representing post-mining landscapes and how this influences the perception of these landscapes. To this end, this paper uses GISs, MCDA, Fuzzy overlay, and Random Forest classification models to integrate post-mining landscape characteristics derived from the literature. It assesses the results using an accuracy assessment, area statistics, and correlation analysis. The findings from this study indicate that both Fuzzy overlay and Random Forest classification are applicable for integrating multiple landscape characteristics at varying degrees. The resultant maps show some similarity in highlighting mine waste cutting across the province. However, the Fuzzy overlay map has higher accuracy and extends over a larger footprint owing to the model’s use of a range of 0 to 1. This shows both areas of low and high memberships, as well as partial membership as intermediate values. This model also demonstrates strong relationships with regions characterised by landscape transformation and waste and weak relationships with areas of economic decline and inaccessibility. In contrast, the Random Forrest classification model, though also useful for classification purposes, presents a lower accuracy score and smaller footprint. Moreover, it uses discrete values and does not highlight some areas of interaction between landscape characteristics. The Fuzzy overlay model was found to be more favourable for integrating post-mining landscape characteristics in this study as it captures the nuances in the composition of this landscape. These findings highlight the importance of mapping methods such as Fuzzy overlay for an integrated representation and shaping the perception and understanding of the locality and extent of complex landscapes such as post-mining landscapes. Methods such as Fuzzy overlay can support research, planning, and decision-making by providing a nuanced representation of how multiple landscape characteristics are integrated and interact in space and how this influences public perception and policy outcomes.

Temporal and Spatial Dynamics of Subsidence in Eastern Jharia, India

Abstract. Jharia, one of the oldest and most significant mining areas, is facing the issue of subsidence for different reasons, such as coal fires, underground mining, and soil sensitivity towards seasonal change. This paper concentrates on the subsidence analysis of the Eastern region of the Jharia Coalfield from January 2018 to January 2021. Sentinal-1 SLC SAR imagery is used for multi-image sparse point processing and generating time series. Data processing is done using SARPROZ software. Further, the PS points inside the study area are filtered, and a classification map is drawn using ArcGIS software. The yearly percentage change of different classified zones is examined. The percentage change is significant for subsiding and uplifting zones but minimal for stable zones. Different critically and highly subsiding areas are identified by overlaying the classification zones on the topographic map. The seasonal variation of cumulative displacement is also examined, and patterns are analyzed. Different regions have different sensitivity towards seasonal variation. Overall, this paper provides insightful deformation results over Eastern Jharia for 2018–2021.

Enhanced lithological mapping in arid crystalline regions using explainable AI and multi-spectral remote sensing data

Lithological classification is essential for understanding the spatial distribution of rocks, especially in arid crystalline areas. Artificial intelligence (AI) recent advancements with multi-spectral satellite imagery have been utilized to enhance lithological mapping in these areas. Here we employed different AI models namely, Support Vector Machine (SVM), Random Forest Classification (RFC), Logistic Regression, XGBoost, and K-nearest neighbors (KNN) for lithological mapping. This was followed by the application of explainable AI (XAI) for lithological discrimination (LD) which is still not widely explored. Based on the highest accuracy and F1 score of the previously mentioned models, RFC model outperformed all of them, and hence, it was integrated with XAI, using the SHapley Additive exPlanations (SHAP) method.This approach successfully identified critical multi-spectral features for LD in arid crystalline zones when applied on the Landsat-8, Advanced Spaceborne Thermal Emission and Reflection Radiometer (ASTER), and SRTM-DEM datasets covering the Hammash and the Wadi Fatimah areas in Egypt and the Kingdom of Saudi Arabia, respectively. Field validation in the Hammash area confirmed the RFC model's efficacy, achieving a satisfactory 94% overall accuracy for 18 features. SHAP was able to identify the top ten features for proper LD over the Hammash area with 90.3% accuracy despite the complex nature of the ophiolitic mélange. For validation purposes, RCF was then utilized in the Wadi Fatimah region, using only the top 10 critical features rendered from the SHAP analysis. It performed well and had 93% accuracy. Notably, XAI/SHAP results indicated that elevation data, Landsat-8's Green Band (B3), and the two ASTER SWIR bands (B5 and B6) were essential and significant for identifying island arc rocks. Moreover, the SHAP model effectively delineated complex mélange matrices, primarily using ASTER SWIR band (B8). Our findings highlight the successful combination of RFC with XAI for LD and its potential utilization in similar arid crystalline environments worldwide.

Assessment, Characterization, Identification and Prioritization of Major Constraints and Potentials of Three Selected Community Watersheds of Agarfa District, Bale Zone, Oromia, Ethiopia

The severity of land degradation due to different socioeconomic and biophysical pressures is a key problem encountered in watersheds. In addition, the lack of research-based references to a given community watershed, particularly with regard to socioeconomic and biophysical aspects, leads to the failure of the interventions. This study aimed to assess and characterize the socioeconomic and biophysical conditions of three selected (Oda Chefo, Wabe Seada, and Oda Nagelle) Community Watersheds of the Agarfa District of Bale Zone, Oromia, Ethiopia. Furthermore, it identifies and prioritizes constraints and opportunities for scientists, planners, intervention, impact analysis, and project performance evaluation. Communities' watersheds were selected and delineated, followed by household interviews, focus group discussions, and biophysical characterization to generate data. The study used a random sampling technique and a total of 121 sample sizes for socioeconomic data, watershed delineation, slope classification, soil type, and LULC classification map developed based on the preliminary outlet identified with the help of GPS reading and ArcGIS 10.5 software. The socioeconomic parameters were analyzed using SPSS version 20 software. The result of the baseline survey identified key constraints such as soil erosion, soil fertility decline, deforestation and climate change, feed and fodder shortage, livestock disease, human disease, unemployment, food insecurity, water shortage, lack of credit access, market, road, cooperatives, high input price, pest and disease, yield decline and lack of irrigation access. The results revealed that the availability of the labor force, local market accessibility, transport services, informal farmer cooperatives, livestock clinics, youth and women associations, and informal intuitions are the main opportunities in selected community watersheds. In conclusion, baseline surveying before any watershed management practice intervention plays ....

Anthropogenic influence on precipitation in Aotearoa New Zealand with differing circulation types

This study quantifies the influences of anthropogenic forcing to date on precipitation over Aotearoa New Zealand (ANZ). Large ensembles of simulations from the weather@home regional climate model experiments are analysed under two scenarios, a natural (NAT) or counter-factual scenario which excludes human-induced changes to the climate system and an anthropogenic (ANT) or factual scenario. The impacts of anthropogenic forcing on precipitation are analysed in the context of large-scale circulation types characterized using an existing Self Organizing Map classification. The combined effect of both thermodynamics and dynamics are compared with values expected from the Clausius–Clapeyron (C–C) relation. Changes in the precipitation intensity due to greenhouse gas-forced temperature rise are lower than the expected C–C value. However extreme precipitation changes approach the C–C value for some circulation types. Specifically westerly flows enhance precipitation change across ANZ relative to the C–C rate, particularly over the West Coast. Conversely, northwesterly flows reduce the change over the North Island relative to the C–C value. Moreover, the wet day frequency generally reduces in the ANT scenario relative to NAT, reductions are largest on the West Coast of the South Island for westerly flows. Additionally, the frequency of days with extreme precipitation rises over ANZ for most circulation patterns, except in Northland and for northwesterly flows. This underscores the combined influence of dynamics and thermodynamics in shaping both precipitation intensity and frequency patterns across ANZ.

Accuracy assessment of the geomorphon approach to detect ecological sites in the Dry Chaco region of Argentina

Ecological sites are a classification of local-land types based on differences in important environmental factors including soil properties, slope and landscape position within a geomorphologic and climatic zone. The concept is pivotal to conduct adaptative management in arid rangelands because it defines homogeneous areas over which specific soil-vegetation-disturbance dynamic occurs. Geomorphon is a computationally efficient method that uses Digital Elevation Models (DEMs) for the classification of landforms at multiple scales. The objective of this study was to evaluate the accuracy of the geomorphon approach to map ecological sites in a 11,259-ha study area within the Dry Chaco region of Argentina, utilizing local topographic positions along soil catena as a predictor of broader ecological sites classes. We used two DEM pixel resolutions (12.5 m and 30 m) and optimized the flatness threshold (t) and search radius (L) geomorphon parameters. As “ground truth” we used legacy data of 62 soil profiles descriptions. The geomorphon elements detected were reclassified into the three main ecological sites of the study area: highlands, midlands and lowlands. We used the overall disagreement (D) as the main metric for evaluating the accuracy of ecological site classifications. We found that: i) the lowest t value (0.05°) captured subtle topographical changes and thus more effectively reflected the soil-landscape relationship, and ii) larger L values paired with the lower pixel resolution (30 m) diminished the impact of minor landforms, improving the accuracy of ecological site detections. We determined that the geomorphon model with the pixel resolution of 30 m, t-value of 0.05°, and L-value of 12 produced the ecological site classification map with the highest accuracy, achieving a moderate-high accuracy (D of 33.9 %). Our study suggests that the geomorphon approach shows potential for consistent, reproducible and easily updatable ecological site mapping over larger areas.

Category Mapping of Emergency Supplies Classification Standard Based on BERT-TextCNN

In recent years, the escalation in emergency occurrences has underscored the pressing need for expedient responses in delivering essential supplies. Efficient integration and precise allocation of emergency resources under joint government–enterprise stockpiling models are pivotal for enhancing emergency response effectiveness and minimizing economic repercussions. However, current research predominantly focuses on contract coordination and cost-sharing within these joint reserve modes, overlooking significant discrepancies in emergency supply classification standards between government and enterprise sectors, as well as the asymmetry in cross-sectoral and cross-regional supply information. This oversight critically impedes the timeliness and accuracy of emergency supply responses. In practice, manual judgment has been used to match the same materials under differing classification standards between government and enterprise reserves. Still, this approach is inefficient and prone to high error rates. To mitigate these challenges, this study proposes a methodology leveraging the BERT pre-trained language model and TextCNN neural network to establish a robust mapping relationship between these classification criteria. The approach involves abstracting textual representations of both taxonomical classes, generating comparable sentence vectors via average pooling, and calculating cosine similarity scores to facilitate precise classification mapping. Illustrated with China’s Classification and Coding of Emergency Supplies standards and Global Product Classification standards, empirical validation on annotated data demonstrates the BERT-TextCNN model’s exceptional accuracy of 98.22%, surpassing other neural network methodologies such as BERT-CNN, BERT-RNN, BERT-BiLSTM, etc. This underscores the potential of advanced neural network techniques in enhancing emergency supply management across diverse sectors and regions.

Exploring long term Impervious Surface Areas (ISA) dynamics using Landsat imagery, Μachine Learning and GEE: The case of Attica, Greece

Accurate data on Impervious Surface Areas (ISA) are essential for various studies concerning urban environments, as the constant proliferation of these surfaces is a noticeable result of urbanization, especially in metropolitan cities. The present study proposes a methodology approach in performing a long-term mapping of ISA changes in Attica Prefecture, Greece, from 1984 to 2022, exploiting the Landsat archive and contemporary machine learning (ML) methods of geospatial data processing, namely Support Vector Machines (SVM) and Random Forests (RF). Using Google Earth Engine cloud platform, the SVM and RF classifiers are developed and implemented for four single dates (in years 1984, 1999, 2013 and 2022). Accuracy assessment of the classification maps was based on the computation of a series of statistical metrics based on the confusion matrix, ans the McNemar's chi-square test which was used to evaluate the statistical significance of the difference in the classification maps, derived from SVM and RF classifiers. Both SVM and RF provided very accurate results, with Overall Accuracy (OA) higher than 90% and kappa coefficient (Kappa) higher than 0.8 for all classification maps, with SVM performing better in 1984 and 2022 and RF outperforming SVM in 2013. In addition, the McNemar's test confirmed the statistical significance of the research findings reported herein. Change detection results, highlighted the wide sprawl of the urban fabric, especially in sub-urban areas, surrounding the metropolitan center of Athens. The employed methodology represents a significant advancement in the application of GEE, beyond their general use, by integrating cutting-edge ML techniques with available remote sensing data to create an automated analysis process. This innovative fusion not only enhances the precision and efficiency of ISA mapping but also establishes the basis for a pioneering standard in the field by harnessing the power of advanced technologies and accessible data sources.

The Hydrological Impact of Historical and Modern Earthquakes in Central-Southern Italy: Data Analysis and Seismotectonic Insights

Abstract We present the results of research conducted on the hydrological effects induced by historical and modern earthquakes in the central-southern Apennines of Italy. We investigated thirty-nine seismic events of magnitude between M 4.1 and 7.1 that occurred between 1688 and 2020. We collected 526 observations of coseismic and postseismic hydrological effects such as increase or decrease in streamflow, variations in the water levels in wells, formation and/or disappearance of springs and changes in their discharge, and changes in the chemical and physical characteristics of waters. More than half of the observations were new data unpublished to date in the scientific literature. We find that the ease of finding data of interest is strongly influenced by the historical period in which the seismic event occurred. We summarize the methodology of data retrieval and its classification and present examples and maps of coseismic hydrological changes associated with individual seismic events. Most of our novel data derive from seismic postcards, macroseismic questionnaires, and hydrographic annals. However, a nonnegligible set of data comes from a careful rereading of sources—both historical and modern—that were at first considered fruitless. The majority of data concerns an excess flow in streams and springs, and physical–chemical variations such as turbidity, an increase in temperature, and gas emission. We also find that the maximum distance to which seismically induced streamflow responses have been reported can be related to the earthquake magnitude and use this distance to derive an alternative magnitude for some of the strongest earthquakes of our dataset. Finally, we show a potential application of this type of research because the distribution of coseismic hydrological changes can provide constraints in discriminating between the causative faults of strong historical seismic events for which the instrumental data are scarce or not available.

Predicting gully formation: An approach for assessing susceptibility and future risk

AbstractGully erosion is a significant natural hazard and a form of soil erosion. This research aims to predict gully formation in the Kalshour basin, Sabzevar, Iran. Employing the Information Gain Ratio (IGR) index, we identified 13 key factors out of 22 for modeling, with elevation emerging as the most influential factor in gully formation. The study evaluated the performance of individual machine learning algorithms and ensemble algorithms, including the Functional Tree (FT) as the main classifier, Bagging (Bagg), AdaBoost (Ada), Rotation Forest (RoF), and Random Subspace (RSS). Using a data set of 400 gully and non‐gully points obtained through field investigations (70% for training and 30% for testing), the RoF model achieved an area under the curev (AUC) value of 0.99, indicating its high predictive ability for gully‐susceptible areas. Other algorithms also performed well (Ada: 0.90, FT: 0.92, RSS: 0.94, Bagg: 0.95). However, the RoF algorithm with the functional tree as the main classifier (RoF_FT) demonstrated the highest ability in gully classification and susceptibility mapping, enhancing the functional tree's performance. In addition to AUC, the RoF_FT model achieved an F1 score of 0.89 and an MCC of 0.78 on the validation set, indicating a high balance between precision and recall, and a strong correlation between predicted and actual classes, respectively. Similarly, other models showed robust performance with high F1 scores and MCC values, but the RoF_FT model consistently outperformed them, underscoring its robustness and reliability. The resulting gully erosion‐susceptibility map can be valuable for decision‐makers and local managers in soil conservation and minimizing damages. Implementing proactive measures based on these findings can contribute to sustainable land management practices in the Kalshour basin.Recommendations Gully erosion threat: Gully erosion poses a significant threat to soil, with far‐reaching environmental consequences. Predictive modeling: This research focuses on predicting gully formation in the Kalshour basin, Sabzevar, Iran, using advanced machine learning algorithms. Key findings for decision‐makers: The study evaluates the performance of various machine learning algorithms and ensemble algorithms, with the Functional Tree serving as the main classifier. This not only enhances our ability to predict gully formation but also provides a valuable tool for decision‐makers and local managers in soil conservation. Impact on sustainable land management: By offering a gully erosion‐susceptibility map, the research empowers decision‐makers to implement proactive measures, minimizing damage and contributing to sustainable land management practices. Interdisciplinary approach: The study's combination of geospatial analysis, machine learning, and soil conservation aligns with the journal's mission to advance understanding in environmental modeling.

Mussel culture monitoring with semi-supervised machine learning on multibeam echosounder data using label spreading

High diversity seabed habitats, such as shellfish aggregations, play a significant role in marine ecosystem sustainability but are susceptible to bottom disturbance induced by anthropogenic activities. Regular monitoring of these habitats with effective mapping methods is therefore essential. Multibeam echosounder (MBES) has been widely used in recent decades for seabed characterization due to its non-destructive manner and extensive spatial coverage compared to traditional methods like bottom sampling. Nevertheless, bottom sampling remains essential to link ground truth with acoustic seabed classification. Using seabed samples and MBES measurements, machine learning techniques are commonly employed to model their relationships and generate classification maps of an extended seabed. However, limited ground truth data, resulting from constraints in regulations, budget, or time, may impede the development of robust machine learning models. To address this challenge, we applied a semi-supervised machine learning method to classify seabed sediments of a blue mussel (Mytilus edulis) cultivation area in the Oosterschelde, the Netherlands. We utilized nine boxcore samples to generate pseudo-labels on MBES data. These pseudo-labels enlarged the training data size, facilitated the training of three comprehensive machine learning algorithms (Gradient Boosting, Random Forest, and Support Vector Machine), and helped to classify the study site into mussel and non-mussel areas. We found the geomorphological and backscatter-related features to be complementary for mussel culture detection. Our classification results were demonstrated effective through expert knowledge of this cultivation area and brought insights for future research on natural mussel habitats.

Hierarchical classification for improving parcel-scale crop mapping using time-series Sentinel-1 data

Parcel-scale crop classification utilizing time-series satellite observations is of significant importance in precision agriculture. The prior knowledge that crop types can be organized in a hierarchical tree structure is beneficial for improving crop classification. Moreover, the crop hierarchy aligns with the coarse-to-fine cognitive process of geographic scenes. Based on the crop hierarchy, this study developed a general hierarchical classification framework for enhancing crop mapping using time-series Sentinel-1 data. Central to this method is a deep-learning-based hierarchical classification model that explores and makes use of crop hierarchical knowledge. First, preprocessed Sentinel-1 data were geometrically overlaid onto farmland parcel maps to derive parcel-scale time-series features. Second, we constructed a hierarchical crop type system for study areas based on the crop phenology of labeled crop-type samples. Third, we developed a deep-learning-based hierarchical classification model to identify crop types for each parcel, to generate final crop-type classification maps. The proposed approach was further discussed and verified through the implementation of parcel-scale time-series crop hierarchical classifications in a study area in France with farmland parcel maps and time-series Sentinel-1 data. The classification results, indicating significant improvements greater than 4.0% in overall accuracy and 5.0% in F1 score over comparative methods, demonstrated the effectiveness of the proposed method in learning multi-scale time-series features for hierarchical crop classification utilizing Sentinel-1 data sequences.

Fine-Resolution Wetland Mapping in the Yellow River Basin Using Sentinel-1/2 Data via Zoning-Based Random Forest with Remote Sensing Feature Preferences

Accurate wetland classification in the Yellow River Basin (YRB) is crucial for China’s ecological security, sustainable development, and wetland resource management. This calls for more sustained research on regional variations and studies on remote sensing features, especially with temporal considerations. To address this and the optimization of feature extraction as well as ranking, Sentinel-1 and Sentinel-2 images were used. Additionally, to achieve more precise wetland classification, the YRB was subdivided into four regions for random forest classification. The results show that different remote sensing indices effectively distinguish various wetland types and that key percentiles play a significant role in distinguishing wetland types. The 10 m refined wetland classification map for 2020, with an overall accuracy of 85%, demonstrates that this framework can meet the needs of conventional large-scale wetland analysis and management. The total area of wetlands in the YRB in 2020 was 33,554.67 km2, mainly distributed in the upper reaches of the YRB (71%), with seasonal marshes being predominant. The total water area reached 8538.64 km2, primarily distributed in the upper reaches of the YRB (57.40%). This high-resolution wetland map offers crucial insights and tools for monitoring, protecting wetland resources, and shaping policies, advancing regional sustainable development goals.

An explainable weakly supervised model for multi-disease detection and localization from thoracic X-rays

Thoracic diseases are a major source of mortality, often requiring diagnosis from plain chest X-rays. However, differentiating between complex conditions based on subtle radiographic patterns poses challenges even for experts. Recently, deep learning methods have shown promise in automating thoracic disease detection from chest radiographs. Many existing approaches focus on the diseased organs in the radiographs by utilizing spatial regions that contribute significantly to the model’s prediction. Expert radiologists, on the other hand, first identify the prominent region before determining whether those regions are abnormal or not. Therefore, incorporating localization information through deep learning models could result in significant improvements in automatic disease classification. Motivated by this, we have proposed a generalized weakly supervised Confidence-Aware Probabilistic Class Activation Map (CAPCAM) classification model that localizes anomalies for thoracic disease. The CAPCAM used CX-Ultranet as the backbone with the combination of Confidence Aware Network (CAN) and Anomaly Detection Network (ADN) without having any localization labeling. This learning from the backbone helps the model to utilize all components of the feature extracted and, therefore eliminating the need to train them individually reducing the time taken. We have experimentally shown that the proposed CAPCAM method sets a new state-of-the-art benchmark by achieving accuracy in terms of Intersection of bounding box (IoBB) in the range of 85 % - 94 %, and Dice scores in the range of 88 %-90 % for all thirteen diseases on two publicly available large-scale CXR datasets–NIH, Stanford and CheXpert. Testing across different noise levels and different levels of blurred level assessed real-world viability. We have also added a layer of explainability to show how the image is processed. This study demonstrates deep learning’s potential to augment radiologists’ decision-making by providing fast, accurate automated aids for thoracic disease diagnosis. The proposed CAPCAM model could be readily translatable to improve clinical workflows.

Soil cover on complex glacial terrain and challenges for large-scale soil mapping using the World Reference Base (WRB) classification system

In conditions of complex glacial topography, large-scale soil mapping (1:10 000) according to the World reference base for soil resources (WRB) 2022 classification faces significant challenges. High diversity of reference soil groups (RSG) and qualifiers can be found in a small area, and this diversity is not related to the influence of a single but rather to a set of soil-forming factors. As a part of the study, the classification of soils on postglacial landscape was conducted using the WRB 2022 classification system. The analysis was focused on examining relationships between RSG and qualifiers, and also with type of geological deposits, location on the terrain, human activities (drainage of agricultural land, soil tillage and erosion). Survey showed that, in a relatively small area, soil cover consisted of WRB RSG such as Luvisols, Retisols, Regosols, Stagnosols, Gleysols Phaeozems, Planosols, Podzols, Histosols and Anthrosols, with the respective sets of qualifiers. Soils corresponding to the Anthrosol RSG were formed during the construction of a drainage system by burying the former soil with deeper material and later by translocation of colluvium by soil erosion. In the complex glacial topography, the distribution of RSG and their qualifiers is specific, which poses a number of challenges for soil mapping. The study confirmed the possibility of WRB classification for large-scale mapping of agricultural soils on postglacial landscape at the RSG level. The use of qualifiers for definition of mapping units in similar conditions of complex terrain and geological deposits (when mapping on a scale of 1:10 000) is possible only by increasing sampling density.

A 10-m scale chemical industrial parks map along the Yangtze River in 2021 based on machine learning

Strengthening industrial pollution control in the Yangtze River is a fundamental national policy of China. There is a lack of detailed distribution of chemical industrial parks (CIPs). This Study utilized random forest (RF) and active learning to generate the distribution map of CIPs along the Yangtze River at 10-m resolution. Based on Sentinel-2 imagery, spectral and texture features are extracted. Combined with the Points of Interest (POI), a multidimensional feature space is constructed. By employing partitioned training, classification of CIPs map is achieved on Google Earth Engine (GEE). Technical validation along the entire Yangtze River demonstrates a model accuracy of 80%. Compared to traditional manual survey methods, this approach saves significant time and economic costs while also being timelier. As the first publicly available CIPs map within a 5-km range along the Yangtze River, this research will provide a scientific basis for the fine governance of chemical industries in the region. Additionally, it offers a model guide for the accurate identification of the chemical industry.