Regional Mapping Research Articles

Machine learning prediction of health risk and spatial dependence of geogenic contaminated groundwater from the Hetao Basin, China

Geogenic contaminated groundwater (GCG), characterized by elevated arsenic, fluoride, and iodine levels, present a significant challenge to public health and government management. Conventional survey-based approaches of collecting groundwater samples, conducting physicochemical tests, and performing spatial interpolation to obtain regional groundwater chemical component maps are inefficient and costly. More importantly, it does not take into account the actual hydrogeological conditions or the characteristics of pollutant transport and enrichment. To address this issue, we utilized Support Vector Machine (SVM), Random Forest (RF), Adaptive Boosting (AdaBoost), and Extreme Gradient Boosting (XGBoost) to analyze the likelihood of occurrence of arsenic, fluoride, and iodine as well as their spatial distribution in shallow groundwater from the Hetao Basin. Our study incorporated 20 indicators related to meteorology, soil physicochemical properties, and groundwater conditions, along with 1505 labeled samples consisting of groundwater arsenic, fluoride, and iodine concentrations and their corresponding coordinates. Subsequently, the study automatically analyzed the meteorological, soil physicochemical properties and groundwater conditions by constructing a machine learning model using the available data. In order to optimise and select the best prediction model, this paper presents a quantitative evaluation of the prediction performance of various machine learning models. The accuracy (AC), area under curve (AUC) and mean squared error (MSE) were calculated to predict the spatial distribution of CGC. Subsequently, the optimized model for predicting the spatial distribution of GCG was selected. The results showed that the XGBoost algorithm provided optimal predictions for groundwater with arsenic concentrations above 10 μg/L and fluoride concentrations exceeding 1.5 mg/L, whereas the RF model provided the best predictions for groundwater with arsenic concentrations surpassing 50 μg/L and iodine concentrations exceeding 100 μg/L. Subsequently, groundwater health risk zones were delineated based on an optimal prediction model, and demographic analysis was conducted in both the direct and potential groundwater risk zones. Model predictions indicated that hundreds of thousands of people in the Hetao Basin were facing a public health crisis caused by high concentrations of arsenic, fluoride and iodine in groundwater. These findings underscore the significant health challenge in the study area. Considering the agricultural development and increasing groundwater use in the area, our findings can guide local governments in managing the extent of groundwater development, establishing control zones, and enhancing protection measures for populations at risk from groundwater contamination.

High-resolution mapping and multivariate technique (factor analysis) to support hydrogeochemical analysis and identification of surface water contamination

The study presented a high-resolution regional mapping of a significant Brazilian watershed, which is heavily influenced by mining, agriculture, and domestic/industrial effluents. Upper São Francisco Basin encompasses the largest karst area in the country and includes three important Brazilian biomes: Cerrado, Atlantic Forest, and Caatinga. Surface water (1418 samples) was collected during the dry season and was analyzed for physical-chemical parameters, cations, anions, and some metals. The spatial distribution and abundance of variables were assessed, and the processes controlling the sources of dissolved loads in surface waters were discussed. The results indicate that rock weathering is the primary factor controlling water chemistry, with a strong influence of carbonate and silicate minerals. Anthropogenic activities, particularly agriculture, play a key role in the chemical composition of the microbasins. Soil erosion and leaching processes also contribute significantly to the region, driven by land use practices and mineral extraction, which intensify erosion processes. The northern sector of the Upper São Francisco Basin, characterized by an arid climate and Caatinga vegetation, experiences low precipitation and high evapotranspiration rates. The VG stands out due to the presence of the karst zone and for the mixture of natural to anthropogenic sources.

Learning spectral-indices-fused deep models for time-series land use and land cover mapping in cloud-prone areas: The case of Pearl River Delta

Mapping of highly dynamic changes in land use and land cover (LULC) can be hindered by various cloudy conditions with optical satellite images. These conditions result in discontinuities in high-temporal-density LULC mapping. In this paper, we developed an integrated time series mapping method to enhance the LULC mapping accuracy and frequency in cloud-prone areas by incorporating spectral-indices-fused deep models and time series reconstruction techniques. The proposed method first reconstructed cloud-contaminated pixels through time series filtering, during which the cloud masks initialized by a deep model were refined and updated during the reconstruction process. Then, the reconstructed time series images were fed into a spectral-indices-fused deep model trained on samples collected worldwide for classification. Finally, post-classification processing, including spatio-temporal majority filtering and time series refinement considering land–water interactions, was conducted to enhance the LULC mapping accuracy and consistency. We applied the proposed method to the cloud- and rain-prone Pearl River Delta (i.e., Guangdong–Hong Kong–Macao Greater Bay Area, GBA) and used time series Sentinel-2 images as the experimental data. The proposed method enabled seamless LULC mapping at a temporal frequency of 2–5 days, and the production of 10 m resolution annual LULC products in the GBA. The assessment yielded a mean overall accuracy of 87.01% for annual mapping in the four consecutive years of 2019–2022 and outperformed existing mainstream LULC products, including ESA WorldCover (83.98%), Esri Land Cover (85.26%), and Google Dynamic World (85.06%). Our assessment also reveals significant variations in LULC mapping accuracies with different cloud masks, thus underscoring their critical role in time series LULC mapping. The proposed method has the potential to generate seamless and near real-time maps for other regions in the world by using deep models trained on datasets collected globally. This method can provide high-quality LULC data sets at different time intervals for various land and water dynamics in cloud- and rain-prone regions. Notwithstanding the difficulties of obtaining high-quality LULC maps in cloud-prone areas, this paper provides a novel approach for the mapping of LULC dynamics and the provision of reliable annual LULC products.

Investigating the Hydraulic Behaviours of an Alluvial Meandering River Reach Between Two Barrages

The Abassia-Shammia is a meandering stream in Najaf province. Predicting and estimating the flow behavior of meandering rivers is crucial for designing hydraulic structures in an accurate manner in the vicinity and conducting environmental and ecological studies. The hydraulic properties of an alluvial stream are typically subject to change due to its location between two barrages. In this study, HEC RAS 2D, developed by the Hydrologic Engineering Center’s River Analysis System, was employed to simulate the hydraulic performance of the Euphrates River reach between two series of barrages, i.e., Abbassia and Shammia. Reliable input data, such as Digital Elevation Models (DEMs), land cover classification, and data for the 2023 hydrograph as a boundary condition, were utilized to develop the hydraulic model. The model was calibrated by using the observed water surface elevation from field measurements downstream of Abbassia to match the ones calculated by the model. Hence, the hydraulic model of the Euphrates River was created using an appropriate Manning roughness coefficient value (n = 0.04) based on the most suitable values of statistical indices, correlation coefficient (R²), and root mean squared error (RMSE) to assess the agreement between the observed and simulated data throughout the calibration and validation phases. To visualize the HECRAS2D output, the hydraulic maps for the study region were presented. The ten cross-sections from the field study (investigated at the same period of flow hydrograph) were presented for modeling to emphasize the river's hydraulic behaviors. Based on the results, the water surface elevation ranged between 19.1–29.2 m.a.s.l., and the flow velocity was 2.50 m/s. Meanwhile, the values of bed shear stress (Pa) and the water depth (m) ranged between 0.1 Pa and 8.93 m for the entire river. The results also proved the superiority of the HEC RAS2D model to reliably represent the hydraulic performance of the Euphrates River reach located between the two barrages. Doi: 10.28991/CEJ-2024-010-05-013 Full Text: PDF

Mapping Quaking Aspen Using Seasonal Sentinel-1 and Sentinel-2 Composite Imagery across the Southern Rockies, USA

Quaking aspen is an important deciduous tree species across interior western U.S. forests. Existing maps of aspen distribution are based on Landsat imagery and often miss small stands (<0.09 ha or 30 m2), which rapidly regrow when managed or following disturbance. In this study, we present methods for deriving a new regional map of aspen forests using one year of Sentinel-1 (S1) and Sentinel-2 (S2) imagery in Google Earth Engine. Using observed annual phenology of aspen across the Southern Rockies and leveraging the frequent temporal resolution of S1 and S2, ecologically relevant seasonal imagery composites were developed. We derived spectral indices and radar textural features targeting the canopy structure, moisture, and chlorophyll content. Using spatial block cross-validation and Random Forests, we assessed the accuracy of different scenarios and selected the best-performing set of features for classification. Comparisons were then made with existing landcover products across the study region. The resulting map improves on existing products in both accuracy (0.93 average F1-score) and detection of smaller forest patches. These methods enable accurate mapping at spatial and temporal scales relevant to forest management for one of the most widely distributed tree species in North America.

Classification of Autism Spectrum Disorder using Resting State-Functional Magnetic Resonance Imaging and Artificial Neural Network

Autism Spectrum Disorder (ASD) represents a growing challenge in public health, characterized by irreversible neurodevelopmental abnormalities. Despite a rising prevalence, the underlying aetiology and neural substrates of ASD remain incompletely understood. Resting state-functional Magnetic Resonance Imaging (rs-fMRI) has emerged as a valuable non-invasive tool for probing the organization and cognitive functions of the brain by capturing hemodynamic changes. This study explores the relationship between Functional Connectivity (FC) alterations, measured by rs-fMRI, and the manifestation of ASD-related brain disorders. In this paper, we propose a hybrid approach employing an InfoMax Independent Component Analysis (ICA) algorithm and Artificial Neural Network to distinguish between the ASD subjects and Healthy Controls (HCs). Initially, rs-fMRI datasets are preprocessed using Statistical Parametric Mapping (SPM). Further, these datasets are processed using InfoMax ICA to extract the distinct features such as fractional Amplitude of Low-Frequency Fluctuations (fALFF) and Dynamic Range and visualize the FC alterations by region mapping. In addition to this, the number of activated voxels for each brain regions are estimated to observe the neural abnormalities. Finally, the extracted features are fed as input to train, test and validate the ANN classifier. The efficacy of the proposed network is evaluated using the Autism Brain Imaging Data Exchange (ABIDE) dataset and an accuracy of 75.3 percentage is achieved.

Assessment of Site Effects and Numerical Modeling of Seismic Ground Motion to Support Seismic Microzonation of Dushanbe City, Tajikistan

In the territory of Dushanbe city, the capital of Tajikistan, detailed geological and geophysical data were collected during geophysical surveys in 2019–2020. The data comprise 5 microtremor array measurements, 9 seismic refraction tomography profiles, seismological data from 5 temporary seismic stations for standard spectral ratio calculations, 60 borehole datasets, and 175 ambient noise measurements. The complete dataset for Dushanbe was used to build a consistent 3D geologic model of the city with a size of 12 × 12 km2. The results of the seismological and geophysical surveys were compared and calibrated with borehole data to define the boundaries of each layer in the study area. The Leapfrog Works software was utilized to create a 3D geomodel. From the 3D geomodel, we extracted six 12 km long 2D geological cross-sections. These 2D geological cross-sections were used for 2D dynamic numerical modeling with the Universal Distinct Element Code software to calculate the local seismic response. Finally, the dynamic numerical modeling results were compared with the amplification functions obtained from the seismological and ambient noise data analysis. The 2D dynamic numerical modeling results allowed a better assessment of the site effects in the study area to support seismic microzonation and the determination of local peak ground acceleration changes in combination with regional seismic hazard maps. In addition, our results confirm the strong seismic amplification effects noted in some previous studies, which are attributed to the influence of local topographic and subsurface characteristics on seismic ground motions.

Multi-hazard could exacerbate in coastal Bangladesh in the context of climate change

Floods and landslides have cascading effects on coastal areas of Bangladesh. This study aims to develop multi-hazard maps (e.g., floods and landslides) for the coastal region, by integrating a genetic algorithm optimizer with Long Short-Term Memory deep learning algorithm (GA-LSTM-DLA), global climate model, and geospatial data. It assesses vulnerabilities to multiple hazards and projects future risks considering the Australian Community Climate and Earth System Simulator Earth System Model 1.5 (ACCESS-ESM1-5) under three climate scenarios, i.e., Shared Socioeconomic Pathways1-2.6, 2–4.5, and 5–8.5 (SSP1-2.6, SSP2-4.5, and SSP5-8.5). The Receiver Operating Characteristic (ROC) curve is used to assess the performance of GA-LSTM-DLA model. According to important feature obtained by random forest (RF) algorithm, most important features for flash, riverine, tidal floods, and landslides are drainage density, rainfall, and geology, respectively. The baseline susceptibility maps for flash, riverine, tidal floods, and landslides are initially recorded as 0.11%, 7.99%, 3.46%, and 0.03%. Projections for the year 2100, under different SSPs, show significant increase, i.e., SSP1-2.6—flash 1.31%, riverine 23.74%, tidal 26.97%, landslides 2.05%; SSP2-4.5—flash 0.12%, riverine 30.97%, tidal 10.23%, landslides 0.18%; SSP5-8.5—flash 0.02%, riverine 17.42%, tidal 6.19%, landslides 0.14%. These projections highlight urgent need for mitigation and adaptation measures against hazards susceptibility, particularly under more extreme socioeconomic scenarios. Overall, the findings of this work are critical for policymakers to develop informed strategies for climate resilience, sustainable development, and disaster risk reduction in the coastal region of Bangladesh.

Novel solution strategies for multiparametric nonlinear optimization problems with convex objective function and linear constraints

AbstractThis paper expands the multiparametric quadratic programming (mp-QP) framework presented in Narciso et al. (Comput Chem Eng 164:107882, 2022. https://doi.org/10.1016/j.compchemeng.2022.107882) to the more general multiparametric nonlinear programming (mp-NLP) case. First, the vector of parameters in mp-NLP problems is recast so that a unique transformed parameter is implicitly assigned to each of the inequality constraints. Maps of critical regions in this transformed space of parameters feature a set of 1-dimensional parametric edges (two per inequality constraint), which then greatly facilitate solution calculation. In the mp-NLP case, however, parametric edges define nonlinear semi-infinite lines; this requires an adaptation to the mp-QP algorithm (deals with linear parametric edges only), to enable a suitable calculation path to the more general nonlinear case. Three routes are proposed to mp-NLPs: the first route delivers solutions in compact form (same format as in mp-QP) using a single reference point per edge; the second route delivers explicit solutions using a hybrid approach for critical region construction, where all active sets not detected in the parameters space are excluded from the solution (equivalent to first route concerning accuracy); the third route builds on the initial explicit solution and further partitions the parameters space until all solution fragments satisfy an error check. Five algorithms were coded for these routes, and tested in a large range of mp-NLP problems. These strategies enable significant improvements in terms of solution accuracy, algorithm efficiency, and interpretability when compared to the state-of-the-art mp-NLP algorithms.

DETERMINING THE SPECIES COMPOSITION OF FOREST VEGETATION IN THE KOSTANAY REGION USING REMOTE SENSING DATA

During the scientific investigation, woody species of forest vegetation were identified and a map of forest vegetation in the Kostanay region was produced using various data sources: field materials, Earth remote sensing data, and ArcGIS10.9 software. An algorithm was developed to detect tree species based on Landsat 9 satellite imagery, characterized by high spatial resolution. Recognition of dominant tree species was performed using various combinations of spectral bands from Landsat 9 imagery, analysis of vegetation indices (NDVI, EVI) across different seasons, and supervised local adaptive classification. The obtained data were validated against field research materials (August-September 2023) and forest management records. The chosen algorithm implements contemporary approaches to acquiring and processing necessary data from satellite remote sensing imagery. Further differentiation and creation of the forest vegetation map of the Kostanay region were based on the established map of tree species, digital elevation model, geological-geomorphological features, field research, thematic maps, and physical geography of the region. As a result of the conducted research, six classes of forest stands were delineated in the Kostanay region, including light-coniferous and deciduous tree species such as pine, birch, aspen, larch, shrubbery, and meadow vegetation. These research findings and the algorithm developed can be applied to other study areas and hold practical significance.

Examining chromatin heterogeneity through PacBio long-read sequencing of M.EcoGII methylated genomes: an m6A detection efficiency and calling bias correcting pipeline.

Recent studies have combined DNA methyltransferase footprinting of genomic DNA in nuclei with long-read sequencing, resulting in detailed chromatin maps for multi-kilobase stretches of genomic DNA from one cell. Theoretically, nucleosome footprints and nucleosome-depleted regions can be identified using M.EcoGII, which methylates adenines in any sequence context, providing a high-resolution map of accessible regions in each DNA molecule. Here, we report PacBio long-read sequence data for budding yeast nuclei treated with M.EcoGII and a bioinformatic pipeline which corrects for three key challenges undermining this promising method. First, detection of m6A in individual DNA molecules by the PacBio software is inefficient, resulting in false footprints predicted by random gaps of seemingly unmethylated adenines. Second, there is a strong bias against m6A base calling as AT content increases. Third, occasional methylation occurs within nucleosomes, breaking up their footprints. After correcting for these issues, our pipeline calculates a correlation coefficient-based score indicating the extent of chromatin heterogeneity within the cell population for every gene. Although the population average is consistent with that derived using other techniques, we observe a wide range of heterogeneity in nucleosome positions at the single-molecule level, probably reflecting cellular chromatin dynamics.

Prospects for Geological Storage of CO2 in Carbonate Formations of the Adriatic Offshore

Croatia has both significant CO2 emissions from the point sources and a history of oil and gas exploration, and this is why the CCS technology surfaced as a viable solution for curbing CO2 emissions on a national level. Since approximately half of emissions from the stationary industrial sources occur along the Adriatic coastline, the entire offshore area became an exploration target. Regional studies revealed the potential storage plays, one of which is in the aquifer of the Mesozoic carbonate complex with dual porosity extending all along the Croatian offshore area. Three structures were chosen in its central part–Klara, Kate and Perina. For the first two, the models were constructed based on the data from old exploration wells and a regional structural map, while for the Perina structure, a new seismic interpretation was added to better characterise its properties. It came out that the Kate structure appears to be the most prospective in general (45 Mt), with neighbouring Klara as the second (39 Mt), while the initially promising Perina (7 Mt) turned out to be of far lesser importance. The Perina structure case is an example that new seismic interpretation can reduce the capacity estimate if it reveals certain limiting factors, in this case, the limitation of structural closure.

Stability Analysis and Hopf Bifurcation for the Brusselator Reaction–Diffusion System with Gene Expression Time Delay

This paper investigates the effect of a gene expression time delay on the Brusselator model with reaction and diffusion terms in one dimension. We obtain ODE systems analytically by using the Galerkin method. We determine a condition that assists in showing the existence of theoretical results. Full maps of the Hopf bifurcation regions of the stability analysis are studied numerically and theoretically. The influences of two different sources of diffusion coefficients and gene expression time delay parameters on the bifurcation diagram are examined and plotted. In addition, the effect of delay and diffusion values on all other free parameters in this system is shown. They can significantly affect the stability regions for both control parameter concentrations through the reaction process. As a result, as the gene expression time delay increases, both control concentration values increase, while the Hopf points for both diffusion coefficient parameters decrease. These values can impact solutions in the bifurcation regions, causing the region of instability to grow. In addition, the Hopf bifurcation points for the diffusive and non-diffusive cases as well as delay and non-delay cases are studied for both control parameter concentrations. Finally, various examples and bifurcation diagrams, periodic oscillations, and 2D phase planes are provided. There is close agreement between the theoretical and numerical solutions in all cases.

New stimulation procedures for language mapping in stereo-EEG.

Cortical intracerebral electrical stimulation is an important tool for language mapping in the presurgical work-up of patients with drug-resistant focal epilepsy. Language mapping with stereo-electroencephalography (EEG) is usually performed by high-frequency stimulations (HFS: 50 Hz), whereas low-frequency stimulations (LFS: 1 Hz) are usually considered useful for primary cortices mapping. Little is known in literature about "intermediate" frequencies (IFS: 6-15 Hz). Our objective is to explore the clinical usefulness of IFS in language mapping and identify factors, beyond the electrical parameters, that impact the mapping. We studied 23 patients submitted to stereo-EEG for presurgical evaluation. Language mapping was performed in the anterior, posterior and/or basal language region of the dominant hemisphere for language. We included all contact positions within these regions stimulated by HFS (50 Hz, 5 s, 1-3 mA) and IFS (6-15 Hz, 15 s, 5 mA). We compared the capability of both stimulation methods to induce a language deficit without afterdischarges (ADs), and we analyzed factors related to clinical examination, region, and stimulation technique by multivariate analysis. A total of 211 stimulations (98 HFS, 113 IFS) in 70 cortical sites within the anterior (84 stimulations), posterior (137), and basal language region (60) were included. IFS induced more frequently language deficits not associated to AD compared to HFS (37.1% vs 25.7%, p = .0043), whereas HFS provoked more diffuse AD (34.7% vs 15.0%, p = .001). Investigating multiple language functions increased the probability of revealing a deficit (odds ratio [OR] 3.16, p = .0016), independently of the stimulation method. IFS are valuable for language mapping, thereby improving the probability of inducing a clinical deficit not accompanied by an AD. The completeness of the clinical examination independently affects the sensitivity of the mapping. IFS are a new tool with potential usefulness for the cortical mapping of other associative cortical regions.

The crinoid Jimbacrinus bostocki from the Lower Permian Cundlego Formation near Gascoyne Junction, Western Australia

Invertebrate macrofossils are superbly preserved in slabs of calcareous silty sandstone exposed in the bed of the Gascoyne River just west of Gascoyne Junction, Western Australia. Based on regional mapping, these rocks have been assigned to the shallow marine Cundlego Formation, which has been dated to the Early Permian. Many of the slabs have preserved the cladid, inadunate crinoid Jimbacrinus bostocki in large numbers, with densities of 150 individuals or more per square metre. Articulated crowns with complete or partial stems attached are often haphazardly aggregated in pods. Details on the morphology of J. bostocki are provided, particularly on juveniles which have cirriferous stems. Adult stems lack any obvious holdfast and are acutely geniculate below the calyx before being preferentially directed linearly in the homocrinid (E–BC) symmetry plane in the E ray direction. Crowns are commonly preserved with their arms arranged in a protective manner, also referred to as the ‘trauma’ posture. It is inferred that such individuals were likely transported alive by storm induced turbidity currents from a feeding position on a marine shelf to deeper, possibly more anoxic, waters, often accumulating en masse in syndepositional lows such as swales. They were subsequently smothered by sediment and rapidly buried. These fossiliferous deposits are interpreted as an “obrution” Lagerstätte. Using taphonomic and functional morphology analysis, possible options for the feeding posture of J. bostocki are proposed. Because of its advanced arm morphology comprising mainly oblique muscular articulations between brachials, the question whether adults were motile, rather than sessile, is addressed. Robbert J Willink [robblink@ozemail.com.au], 11 Coral Sea Court, Sunshine Beach, Queensland 4567, Australia. Tom Kapitany [tomk@crystal-world.com] Crystal World, 13 Olive Road, Devon Meadows, Victoria 3977, Australia.

The universal variability of the stellar initial mass function probed by the TIMER survey

The debate about the universality of the stellar initial mass function (IMF) revolves around two competing lines of evidence. While measurements in the Milky Way, an archetypal spiral galaxy, seem to support an invariant IMF, the observed properties of massive early-type galaxies (ETGs) favor an IMF somehow sensitive to the local star-formation conditions. However, the fundamental methodological and physical differences between the two approaches have hampered a comprehensive understanding of IMF variations. Here, we describe an improved modeling scheme that, for the first time, allows consistent IMF measurements across stellar populations with different ages and complex star-formation histories (SFHs). Making use of the exquisite MUSE optical data from the TIMER survey and powered by the MILES stellar population models, we show the age, metallicity, [Mg/Fe], and IMF slope maps of the inner regions of NGC 3351, a spiral galaxy with a mass similar to that of the Milky Way. The measured IMF values in NGC 3351 follow the expectations from a Milky Way-like IMF, although they simultaneously show systematic and spatially coherent variations, particularly for low-mass stars. In addition, our stellar population analysis reveals the presence of metal-poor and Mg-enhanced star-forming regions that appear to be predominantly enriched by the stellar ejecta of core-collapse supernovae. Our findings therefore showcase the potential of detailed studies of young stellar populations to provide the means to better understand the early stages of galaxy evolution and, in particular, the origin of the observed IMF variations beyond and within the Milky Way.

Exploring school food provision programs and links to local foods in Pacific Island countries

Providing access to food in schools can serve as a platform for food system transformation, while simultaneously improving educational outcomes and livelihoods. Locally grown and procured food is a nutritious, healthy, and efficient way to provide schoolchildren with a daily meal while, at the same time, improving opportunities for smallholder farmers(1). While there is significant potential for school food provision activities to support healthy dietary behaviours in the Pacific Islands region, there is limited evidence of these types of activities(2), including scope and links to local food production in the region. Therefore, the aim of this scoping study was to understand the current state of school food activities (school feeding, gardening and other food provision activities) and any current, and potential links to local agriculture in the Pacific Islands. A regional mapping activity was undertaken, initially covering 22 Pacific Island countries. The mapping included two steps: 1) a desk based scoping review including peer-reviewed and grey literature (2007-2022) and 2) One-hour semi-structured online Zoom interviews with key country stakeholders. Twelve sources were identified, predominately grey literature (n = 9). Thirty interviews were completed with at least 1 key stakeholder from 15 countries. A variety of school food provision activities were identified, including school feeding programs (n = 16, of varying scale), programs covering both school feeding and school gardens (n = 2), school garden programs (n = 12), and other school food provision activities (n = 4, including taste/sensory education, food waste reduction, increasing canteen capacity for local foods, supply chain distribution between local agriculture and schools). Existing links to local agriculture varied for the different programs. Of the 16 school feeding programs, 8 had a requirement for the use of local produce (policy requirement n = 6, traditional requirement from leaders n = 2). Of the 12 school garden programs, 6 used local or traditional produce in the garden and 5 involved local farmers in varying capacities. Challenges to linking local agriculture into school food provision programs were reported for 17 activities and were context dependent. Common challenges included limited funding, inflation, Covid-19, inadequate produce supply for the scale of program, limited farmer capacity, limited institutional support for local produce, low produce storage life, climatic conditions and disasters, water security, delayed procurement process, and limited professional development and upskilling opportunities. Modernisation and colonisation of food systems resulting in a preference for hyperpalatable foods and challenges in incorporating local produce in a way that is accepted by students was also identified as a challenge. This evidence can be used to develop a pathway to piloting and implementing models of school food provision programs and promoting opportunities for shared learning and collaboration with key stakeholders across the Pacific Islands region.

MRG-T: Mask-Relation-Guided Transformer for Remote Vision-Based Pedestrian Attribute Recognition in Aerial Imagery

Nowadays, with the rapid development of consumer Unmanned Aerial Vehicles (UAVs), utilizing UAV platforms for visual surveillance has become very attractive, and a key part of this is remote vision-based pedestrian attribute recognition. Pedestrian Attribute Recognition (PAR) is dedicated to predicting multiple attribute labels of a single pedestrian image extracted from surveillance videos and aerial imagery, which presents significant challenges in the computer vision community due to factors such as poor imaging quality and substantial pose variations. Despite recent studies demonstrating impressive advancements in utilizing complicated architectures and exploring relations, most of them may fail to fully and systematically consider the inter-region, inter-attribute, and region-attribute mapping relations simultaneously and be stuck in the dilemma of information redundancy, leading to the degradation of recognition accuracy. To address the issues, we construct a novel Mask-Relation-Guided Transformer (MRG-T) framework that consists of three relation modeling modules to fully exploit spatial and semantic relations in the model learning process. Specifically, we first propose a Masked Region Relation Module (MRRM) to focus on precise spatial attention regions to extract more robust features with masked random patch training. To explore the semantic association of attributes, we further present a Masked Attribute Relation Module (MARM) to extract intrinsic and semantic inter-attribute relations with an attribute label masking strategy. Based on the cross-attention mechanism, we finally design a Region and Attribute Mapping Module (RAMM) to learn the cross-modal alignment between spatial regions and semantic attributes. We conduct comprehensive experiments on three public benchmarks such as PETA, PA-100K, and RAPv1, and conduct inference on a large-scale airborne person dataset named PRAI-1581. The extensive experimental results demonstrate the superior performance of our method compared to state-of-the-art approaches and validate the effectiveness of mask-relation-guided modeling in the remote vision-based PAR task.

Advancing subsurface analysis: Integrating computer vision and deep learning for the near real-time interpretation of borehole image logs in the Illinois Basin-Decatur Project

The accurate quantification and mapping of subsurface natural fracture systems using borehole imaging logs are critical for the success of CO2 sequestration in geologic formations, optimization of engineered geothermal systems, and hydrocarbon production enhancement. However, traditional interpretation processes suffer from time-consuming procedures and human bias. To address these challenges and expedite fracture analysis, we investigated the application of integrated computer vision and DL workflows to automate image log analysis. Specifically, the design of our workflow was crafted to swiftly detect fractures and baffles by using actual electrical resistivity of borehole wall from microresistivity imaging device alongside their binary representation. This novel approach significantly reduces computational time while providing invaluable insights. By incorporating conventional logging and microseismic data, we present a regional subsurface natural fracture mapping technique. Through the minimization of human bias in image log analysis, our automated workflow achieves reduced fracture interpretation time and costs while ensuring robust and reproducible results. We demonstrated the efficacy of our approach by applying the workflow to the Illinois Basin-Decatur Project site. The automated workflow successfully identified major fractured zones, multiple baffles, and an interbedded layer with a high resolution of 0.01 ft or 0.12 in. (0.3 cm) and can be upscaled to any desired resolution. Validation through microseismic and image log interpretations allows for accurate and near-real-time mapping of fractures and baffles, significantly enhancing CO2 pressure forecasting and postinjection site care. Our approach stands out due to its robustness, consistency, and reduced computational cost compared with alternative feature extraction technologies. It presents exciting possibilities for advancing CO2 sequestration and engineered geothermal efforts by offering comprehensive and efficient fracture mapping solutions. This technology can contribute significantly to the optimization of CO2 sequestration projects, facilitating sustainable environmental practices, and combating climate change.

Updating of soil map of mountaneous regions of Uzbekistan

: One of the latest updates on the soil cover of the mountain regions of Uzbekistan is contained in the “Atlas of the Soil Cover of the Republic of Uzbekistan”, published in 2010. It contains soil maps of the regions of the country at the scales of 1 : 350 000 to 1 : 2 500 000 and provides brief charateristics of the soils. The Atlas was compiled on the basis of traditional methods of soil mapping. As a result, its contour part is typical of maps of the mentioned scales and rather schematic. The aim of the research was to update the contour part of the soil maps of mountain territories of Uzbekistan, contained in this Atlas, by means of the analysis of Landsat 8 satellite data. The contour part of the map was updated for the territory with absolute terrain altitude exceeding 900 m. Updating of the map contours was based on the methods of interactive indirect interpretation, when the boundaries of the contours were specified in the GIS using as a substrate the color composites of satellite data obtained at the optimal time of survey. Map correction, mountainous area delineation, and area counting were performed using the GIS ILWIS v.3.3 software package. About 18% of all soil mapping units were divided into several subunits. For 37% of the soil mapping units the boundaries changed significantly (the area of the units changed – by more than 30% with an average change in the length of the boundary of 15–38%). For 45% of soil mapping units the boundaries had changed less significantly (the area of the units had changed by no more than 30% and the boundary length had changed by no more than 20%). No cases of merging of soil mapping units were recorded. As a result, the contour part of the corrected map, compared to the original one, became much more detailed with more indented boundaries. The updated map shows the natural soil cover, excluding the anthropogenically changed soils. But the approach used for updating the original soil map may be also applied to expand the information on anthropogenical load as well. Moreover, this information can be obtained by interpretation of the same satellite data that were used for the map updating.