Raster Datasets Research Articles

Spatial Data Infrastructure and Mobile Big Data for Urban Planning Based on the Example of Mikolajki Town in Poland

Spatial Data Infrastructure (SDI) is a decision-making tool that is often used in the area of urban planning. At the same time, many other data sources with great utility potential, such as Big Data, can be identified. The aim of the paper is to present the possibility of using mobile Big Data collections with data from Polish SDI, for the purposes of local spatial planning on the example of the tourist town, Mikolajki in Poland. The publication also focuses on assessing the quality of data, as well as the decision-making process supported by these sources. The draft of the local spatial development plan was verified based on integrated data sources. The results showed that the visualization of Big Data as a heat map may be used in urban tasks and as the thematic layer integrated with vector and raster data sets from the SDI in the geographic information system software. The contribution is the practical example how information about users of mobile devices and some information from behavioral profiles may be analyzed for the purposes of verifying planned land use.

DGGSTools: An Open Source Python Package for the Manipulation of Vector and Raster Datasets in the rHEALPix Discrete Global Grid System

DGGSTools: An Open Source Python Package for the Manipulation of Vector and Raster Datasets in the rHEALPix Discrete Global Grid System

Study on Spatialization and Spatial Pattern of Population Based on Multi-Source Data—A Case Study of the Urban Agglomeration on the North Slope of Tianshan Mountain in Xinjiang, China

Study on Spatialization and Spatial Pattern of Population Based on Multi-Source Data—A Case Study of the Urban Agglomeration on the North Slope of Tianshan Mountain in Xinjiang, China

Interannual precipitation variability dominates the growth of alpine grassland above-ground biomass at high elevations on the Tibetan Plateau

The impact of global climate change on mountainous regions with significant elevational gaps is complex and often unpredictable. In particular, alpine grassland ecosystems, are experiencing changes in their spatial patterns along elevational gradients, which increases their vulnerability to degradation. Therefore, a more detailed understanding of spatiotemporal changes in alpine grassland productivity along elevational gradients and an elevation-dependent characterization of the effects of climatic variables on grassland productivity dynamics are essential. Thus, we conducted a study in the Tibetan Plateau, where we collected 2251 above-ground biomass (AGB) observations collected from 1986 to 2020. Mean annual temperature (TMP), annual precipitation (PRE), interannual precipitation variability (CVP), and snowmelt (SNMM) were chosen as influential variables. Using the Random Forest algorithm, we generated an AGB raster dataset covering the period 1989–2020 based on earth observation data at 30 m resolution to examine the dynamics of alpine grasslands and their response to climate change with respect to elevation. The results showed that the AGB of alpine grassland on the Tibetan Plateau was 49.17 g/m2. We observed an increasing trend in grassland AGB at high elevations, with a growth rate of about 0.28 g/m2 per year within the interval of 3100–4800 m. However, above the elevation of approximately 4400–4600 m, we observed a decoupling trend between grassland AGB and TMP. Moreover, at most elevations, the proportion of maximum partial correlation coefficients for CVP, PRE, and SNMM surpassed that of TMP. We found the dominant role of precipitation variability on grassland AGB dynamics, with 22.80 % and 18.86 % for CVP+ and CVP-, respectively. The proportion of CVP+ did not vary much at different elevations, whereas the proportion of CVP- increased with elevation, varying between 12.85 and 30.25 %. In the future, precipitation on the Tibetan plateau is expected to increase, potentially reversing its original positive impact.

Exploring dynamics relationship between carbon emissions and eco-environmental quality in Samarinda Metropolitan Area: A spatiotemporal approach

Carbon emissions have a negative impact on climate change. Environmental quality has faced significant challenges in the last decades. Eco-environmental quality helps assess the condition of the ecological environment to support humans' civilization and development. By using emissions raster dataset, remote sensing images, and LULC data, this study explores the status of carbon emissions (CE), eco-environmental quality (RSEICs), and the dynamic relationship between both variables in Samarinda Metropolitan Area, Indonesia. This study uses the spatiotemporal approach to deepen the understanding of CE-RSEICs during 2000–2021. The methods include the analysis of CE and the principal component of RSEICs. To understand the CE-RSEICs spatial features, the directional distribution ellipse method is used. Also, this study performs CE-RSEICs coupling analysis and identifies its LULC type composition. The findings show that CE status is still on an increasing trend, concentrating in the eastern region and keeping expanding during the period. The location of the low-emission ellipse is in the southwest, while the high-emission ellipse is in the east and intersects with the core cities. The mean RSEICs value is between 0.2878 to 0.4223, which indicates that the eco-environmental quality is categorized as fairly poor to inferior. Greenness, wetness, and Csink have a positive impact on RSEICs. The very poor-class ellipse is located in the inland region, and the very good-class ellipse is in the coastal area. The CE-RSEICs coupling status shows that the majority of the area has a weaker coupling degree. However, the higher coupling degree is concentrated in the population center and built-up region, which is the settlement area. The dominance composition of settlement area in higher coupling degree shows that settlement area has an impact on increasing CE-RSEICs coupling degree. So, sustainable low carbon development in coastal metropolitan area must continue to be carried out by considering CE-RSEICs and its spatial aspects.

Analysis of land use/ land cover changes and landscape fragmentation in the Baro-Akobo Basin, Southwestern Ethiopia

This study investigated the relationship between land use/land cover (LULC) changes and forested landscape fragmentation in the southwestern region of Ethiopia. Satellite images from 1986, 2002 and 2019 were collected and analyzed using standard procedures in ERDAS 2015 software. Fragstat 4.2.1 software was utilized to assess landscape fragmentation by examining a raster datasets derived from the classified LULC map over the research period. The study identified seven LULC classes in the study area. Findings revealed a substantial reduction in shrubland by 46.3%, dense forest by 23.75%, open forest by 17.3%, and wetland by 32.63%, while cropland increased by 38.06%, agroforestry by 20.29%, and settlements by 163.8% during the study period. These changes varied across different agroecological zones and slope gradients. Landscape metrics results indicated an increase in the number of patches and patch density for all LULC classes, demonstrating significant fragmentation of the landscape. The largest patch index, mean patch areas, and the percentage of landscape occupied by open forest, dense forest, shrubland, and wetland declined as a result of conversion to cropland, agroforestry, and settlement. Conversely, the largest patch index, the mean patch area and the percentage of the landscape occupied by agroforestry, cropland and settlement increased, indicating their increasing dominance in the landscape over the study periods. The findings highlighted the potential deleterious impacts of ongoing land use change and fragmentation on the environment, ecosystem function and local livelihoods. Therefore, it is crucial to implement appropriate conservation efforts and sustainable land management practices to mitigate the rapid change and fragmentation of land use and its negative impacts on sub-watershed ecosystems.

Carbon Loss from Earthquake Induced Landslides in Fiordland

Landslides triggered by two earthquakes in Fiordland, New Zealand, were mapped using Google Earth Pro retro satellite imagery (eye altitude of 1.5-2.5 km, enabling ± 50 m precision), then catalogued and classified in a GIS inventory. Ground acceleration during the 2003 Mw 7.2 Secretary Island Earthquake resulted in at least 1852 landslides, but the larger Mw 7.8 2009 Dusky Sound Earthquake had lower accelerations and produced only 313. Both events dislodged large swaths of native forest, grassland vegetation and soil from Fiordland’s steep slopes in similar proportions, some landing in rivers and fiords. The landslide maps and magnitude-frequency distributions show close similarity to a published Global Forest Loss dataset derived from 2001-2022 satellite imagery. Assuming forest loss in this wilderness is predominantly landslide-related, it enables the more-precise earthquake-induced landslide mapping to be placed in a longer-term context of other vegetation loss, mostly rainfall-induced landslides, during the past two decades. The total area of forest loss during the 2003 earthquake was anomalous, whereas during 2009 the earthquake losses were similar to areas of forest loss assumed to be rainfall-induced landslides throughout Fiordland each year. Carbon concentrations of landslide vegetation and soil were calculated by defining vegetation types from a published Land Cover Database, and soil organic carbon concentration from a 1 km resolution raster dataset. Total carbon loss from earthquake-induced landslides amounts to 2.05E+06 tonnes for the 2003 Mw7.2 and 2.17E+05 tonnes for the 2009 Mw 7.8. By way of comparison, New Zealand’s total annual carbon sequestration was 6.3E+06 tonnes in 2020. Earthquake-induced and rainfall-induced landslides are shown to account for significant changes in stored carbon and available carbon sequestration, especially in areas of densely vegetated land, such as Fiordland. Processes of landscape disturbance should be included in carbon accounting and estimates of national greenhouse gas emissions.
 
 Supervised by: Caroline Orchiston
 Scholarship Project Funded by: Centre for Sustainability

Connectivity conservation planning through deep reinforcement learning

Abstract The United Nations has declared 2021–2030 the decade on ecosystem restoration with the aim of preventing, stopping and reversing the degradation of the ecosystems of the world, often caused by the fragmentation of natural landscapes. Human activities separate and surround habitats, making them too small to sustain viable animal populations or too far apart to enable foraging and gene flow. Despite the need for strategies to solve fragmentation, it remains unclear how to efficiently reconnect nature. In this paper, we illustrate the potential of deep reinforcement learning (DRL) to tackle the spatial optimisation aspect of connectivity conservation planning. The propensity of spatial optimisation problems to explode in complexity depending on the number of input variables and their states is and will continue to be one of its most serious obstacles. DRL is an emerging class of methods focused on training deep neural networks to solve decision‐making tasks and has been used to learn good heuristics for complex optimisation problems. While the potential of DRL to optimise conservation decisions seems huge, only few examples of its application exist. We applied DRL to two real‐world raster datasets in a connectivity planning setting, targeting graph‐based connectivity indices for optimisation. We show that DRL converges to the known optimums in a small example where the objective is the overall improvement of the Integral Index of Connectivity and the only constraint is the budget. We also show that DRL approximates high‐quality solutions on a large example with additional cost and spatial configuration constraints where the more complex Probability of Connectivity Index is targeted. To the best of our knowledge, there is no software that can target this index for optimisation on raster data of this size. DRL can be used to approximate good solutions in complex spatial optimisation problems even when the conservation feature is non‐linear like graph‐based indices. Furthermore, our methodology decouples the optimisation process and the index calculation, so it can potentially target any other conservation feature implemented in current or future software.

Disentangling the response of vegetation dynamics to natural and anthropogenic drivers over the Qinghai-Tibet Plateau using dimensionality reduction and structural equation model

The Qinghai-Tibet Plateau (QTP), also referred to as the “roof of the world”, is a distinct alpine ecosystem located at an average elevation of more than 4000 m. Climate variation and anthropogenic activity have affected vegetation development on the QTP during the past few decades, but it is still debatable how significant a role any of these causes has played. According to land surface air temperature data around the world, during the past 50 years, temperatures on the QTP have risen twice as rapidly as the average global level. Previous studies have employed the residual method to examine the impacts of anthropogenic activities on vegetation development, with a lack of actual data validation and less attention to explaining the complex interactions and pathways between vegetation growth, natural factors (climate change and topography), and anthropogenic drivers. Furthermore, although the relationships between vegetation dynamics and terrain have been addressed, the interactions in which meteorological factors influence vegetation growth in accordance with topographical variations remain inadequately elucidated. The raster datasets employed in this study include MODIS NDVI, meteorology, topography, as well as anthropogenic activity from 2000 to 2018. A suite of methods including partial correlation coefficient (PCC), principal component analysis (PCA), and partial least squares structural equation model (PLS-SEM) were applied to explore the interrelationships between various influencing factors and regional vegetation development over the past two decades. The results suggested that: (1) an elevation-specific temperature threshold existed, indicating that temperature could promote or inhibit vegetation growth depending on whether it is below or above this threshold, respectively, which was controlled by a trendline equation; (2) the PLS-SEM and PCA results showed that vegetation development was dominantly promoted by temperature and was most sensitive to precipitation; (3) topography, especially elevation, affected vegetation growth indirectly by influencing climatic change, while anthropogenic drivers had positively contributed to vegetation dynamics on the QTP under the influence of implementing ecological management such as the nature reserves establishment.

Land Use/ Land use zoning Practice at Micro level in Nepal: An Assessment

The land use zoning is thought to be better for the sustainable use of land resources utilization in Nepal. Land use (LU) denotes the human activity associated with a specific piece of land and mainly refers to the use by human beings for specific purposes with some sorts of management practices (Khanal, 2000). Specially, Land use is affecting by various factors like, physiographic, topographic, climatic, lithology, soil types, climate, rainfall pattern, cultural and traditional practices as well as socio economic factors etc. With varying physiography conditions around Punchapuri Municipality the land use zones have been found to be a varying shapes and thickness. With the growth of population Punchapuri has expanded the cultivable land of the town. The land use in the Municipality is predominantly nonagricultural with forest, shrub, and grass, covering more than 77% of the total area. The Punchapuri Municipality which is located Surkhet district in province no.6 has been choosen as the study area. Land use map was prepared based on 0.5 m spatial resolution satellite imagery. Various other vector raster and imagery datasets were used ancillary data which enhanced interpretation and classification of land use classes.
 Information on the losses, damage and its future risk were collected through focus group discussion, key informants, interview, observation and measurement. The paper further emphasizes on a detail study of land use pattern, land system, land forms type, and land capability, geology and natural hazards in order to formulate a classification scheme for land use zoning. This study will certainly help the concerned authorities for the ongoing practices on the land, and land use zoning the finite resource of the country. It will further help to develop plan for the local areas and implement accordingly. Therefore, this study can be regarded as milestone for the planners and development working agencies within the area.

A satellite-based approach for thermal comfort simulation: A case study in the GBA

With global warming, the issue of urban surface overheating has emerged as one of the most urgent concerns for modern cities worldwide. However, the simulation of thermal comfort with high spatiotemporal resolution remains a challenge. In this study, an approach is presented to integrate several global meteorological raster data for the production of high spatial and temporal resolution thermal comfort raster datasets. Our approach produced a dataset in the Guangdong-Hong Kong-Macao Greater Bay Area (GBA) covering 98.30% of diurnal moments in 5 years, and the spatial coverage of the region exceeded 87%. The assessment results showed that from 2002 to 2020, mean universal thermal climate index (UTCI) slightly increases from 16.0 to 20.6 °C to 17.3–26.2 °C, dominated by no heat stress (9.0 °C–26.0 °C). The low-value center of UTCI locates in the north GBA, around Zhaoqing and northern Guangzhou, while the high-value center moved westward from Huizhou to Foshan, Dongguan, and the south of Guangzhou. Over the past 18 years, the heat stress has become larger in the spatial extent and more prolonged. The heat island effect has intensified over the past 18 years, resulting in a coexistence of the positive heat island intensity and the negative heat island intensity. The result investigates urban thermal comfort conditions for urban thermal environment management and provides a spatial reference for human-centered urban planning.

USING GHSL TO ANALYZE URBANIZATION AND LAND-USE EFFICIENCY IN THE PHILIPPINES FROM 1975–2020: TRENDS AND IMPLICATIONS FOR SUSTAINABLE DEVELOPMENT

Abstract. This study analyzed the trends and patterns of urbanization and changes in land-use efficiency in the Philippines from 1975–2020 using the Global Human Settlement Layers (GHSL). Utilizing the GHS-BUILT-S, GHS POP, and GHS-SMOD raster datasets from the GHSL Data Package 2023, we examined the spatiotemporal expansion of built-up areas and the growth of population in urban and rural regions of the country. Using the same datasets, we also measured the country's achievement of Sustainable Development Goal (SDG)11.3, particularly on inclusive and sustainable urbanization through efficient land utilization, by computing the ratio of land consumption rate (LCR) to the population growth rate (PGR), also known as LCRPGR. The results of our analysis revealed an increasing trend in the overall built-up area and population of the Philippines within the examined period. Built-up areas and population in urban regions more than tripled in size from 1975 to 2020, demonstrating a notable shift towards more urbanized regions over time. In addition to presenting evidence of the Philippines' developmental progress and urbanization, our analysis of GHSL data shows a decline in land consumption, a deceleration in population growth, and an overall enhancement in land-use efficiency within the country. These findings suggest a shift towards more controlled and sustainable land development practices, supporting the country's goal of sustainable urbanization and land management. The implications of these findings are crucial for policymakers and urban planners in the Philippines, offering valuable insights to guide the formulation of effective and comprehensive land management strategies. Further work includes conducting localized analyses at the city or municipality level to provide valuable insights into the unique urbanization patterns and land-use dynamics across different islands and regions, enabling tailored policy interventions and spatial planning strategies to promote sustainable development.

Exploring driving factors of soil erosion using a Multiscale GWR model: a case study at Central Citarum Watershed, West Java, Indonesia

To address challenges in soil erosion management and ecological rehabilitation, understanding the determinants of soil erosion is crucial. This research aims to achieve two primary objectives: (1) delineating the spatial patterns of soil erosion within the designated region and (2) identifying the influential factors using the Multiscale Geographical Weighted Regression (MGWR) methodology. The methodological framework involved the creation of grid datasets, with soil erosion as the response variable and a combination of physical and socioeconomic attributes as predictors. We extracted 550 data points from raster datasets, specifically centered on village locations, using the ‘extract multi-value to point’ tool in ArcGIS. The R Studio environment was utilized to select the relevant factors influencing soil erosion. The geographical detector technique was applied to determine the explanatory power of each determinant concerning the spatial patterns of soil erosion. Subsequently, data from the Ordinary Least Squares (OLS) model underwent MGWR analysis. The findings reveal that the Central Citarum Watershed experiences an estimated annual soil erosion of 23.16 million tons, averaging 102.01 tons per hectare. The analysis identified LS (slope length and gradient) and CP (vegetative cover and supportive practices) as the primary variables influencing the spatial variability of soil erosion. Notably, the MGWR model demonstrated enhanced explanatory capacity and effectiveness compared to both the OLS and Geographically Weighted Regression (GWR) methodologies.

A parallel strategy to accelerate neighborhood operation for raster data coordinating CPU and GPU

ABSTRACT This study presents an asynchronous parallel strategy coordinating central processing unit (CPU) and graphic processing unit (GPU) to accelerate neighborhood operation (NO). Specifically, we propose a data partitioning method called multi-anchor task queuing and a task scheduling method called bi-direction task scheduling, which can support CPU and GPU to find the responsible data blocks rapidly and concurrently handle their tasks via a bi-direction merge. Moreover, we optimize the organization of threads distributed among the CPU and GPU. Experimental results show that when a 1.7 GB raster dataset is processed, the speedup ratio achieved by the proposed parallel algorithm reaches 29.63, which is 19% and 18% higher than those of the GPU and standard asynchronous parallel algorithm, respectively. Additionally, the load balance index is below 0.085, which is significantly better than the value achieved by a conventional algorithm. Thus, the strategy achieves a higher speedup ratio and more adaptable load balance, thereby accelerating the NO more efficiently. Further, the impacts of the data volume, computational intensity, organization mode of the GPU threads, and granularity of the GPU stream on the parallel efficiency are evaluated and discussed. We also test the efficiency of four other common NOs with our strategy.

Large-scale multi-unit floor plan dataset for architectural plan analysis and recognition

Among automatic floor plan analysis, data-driven methods have become increasingly popular in recent years because of their superior accuracy and generalizability compared to traditional approaches while processing rasterized floor plans. However, the scarcity of public raster datasets with various styles and sufficient quantity hinders the development of new models, as current ones only contain a single apartment or house, limiting the analysis of large-scale plans usually designed in architectural and structural offices. In order to address that issue, this paper presents a multi-unit floor plan dataset comprising 954 high-resolution images of residential buildings with annotated walls and slabs as polygons, enabling large-scale plan analysis. Additionally, this study implements an automatic wall vectorization method that uses a learning discriminative-based semantic segmentation U-Net model to retrieve wall objects, followed by a deep-learning model that predicts the segmented primitives, providing a baseline for future comparison of automatic wall segmentation results.

Фотограмметрическая оценка деформационных процессов на оползневых склонах при обеспечении устойчивого развития территорий Кавказа

Introduction. Sustainable development of geo-resources in modern realities is a priority for ensuring sustainable development of the territories of the Russian Federation. In the absence of real mechanisms for its implementation, the territories most sensitive to climate change (the subtropical zone of the Caucasus) will be exposed to increased risks of an increase in dangerous hydro meteorological phenomena. At the same time, the issues of improving methods for assessing deformation processes on landslide slopes become particularly relevant. Materials and methods. The object of the study was a slope located near the “Winter Theater” (Sochi) on the road surface of the descent to the sea where a system of cracks was observed. The area under study was photographed point by point with a Nikon D3100 camera, after which the photographs were depixelized to obtain PNG ASCII files. After this file, standard smoothing processed the containing data arrays and three-dimensional interpolation procedures to obtain regression models that were presented in the software «gnuplot». Results. As a result of completed stage of research, a methodology for determining the deformation processes of slope systems using the photometric method, which is based on the processing of a high-precision raster image (photo) by analytical methods, was adapted and formed. In our case, there would be a series of values only for the line of sites (n = 9) for all pickets (N from 11 to 23). When analyzing only this series, we could conclude that ε varies nonlinearly from 12 (N= 23 m) to the first local maximum of 20 mm (N= 21 to 22 m). Afterwards there is a decline to 17 mm (N = 20 m) and so on, but in general, they do not exceed 23 mm. While when using the photometric method, we can observe in certain areas (segments) that the amount of deformation of the asphalt road reaches up to 40 mm. Discussion. Compared to most similar studies (geo-statistical methods for processing satellite images, classical geodetic methods, methods of geophysics, the photometric method for identifying fractured structures, as well as assessing their development, is more accurate and less labor-intensive in conducting field experiments. Conclusion. To ensure sustainable development of the Caucasus territories, it is necessary to significantly improve the quality of monitoring of road surfaces located in foothill and mountain areas (especially in the presence of serpentine roads). As a result of the completed stage of research, a methodology for determining the deformation processes of slope systems using the photometric method, which is based on the processing of a high-precision raster image (photo) by analytical methods, was adapted and formed. Future research should focus on the methodology for transitioning to displacement rates and considering the response spaces of crack profile dynamics. Resume. The article presents the results of studies of deformation processes of slope systems in a dangerous landslide zone (Winter Theater of Sochi) of the Eastern Black Sea region. It has been established that the width of the walls of crack No. 2 on the road section under study in 2022 increases nonlinearly according to a polynomial law, while the absolute values of deformations can vary from 3 to 40 mm. In addition, a methodology for using the photometric method to assess the degree of cracking in slope systems is presented. The results of the study can be used in the development of a methodology for geoecological monitoring of the condition of road surfaces of highways in mountainous areas. The proposed methodological approaches to processing raster data sets can be used to develop algorithms for managing natural and technical systems in the mining industry.

Research on the relationship between population distribution pattern and urban industrial facility agglomeration in China

Investigating the impact of industrial facility agglomeration on population distribution provides valuable insights for advancing urban and regional development, as well as aiding in planning, forecasting, and achieving regional equilibrium. However, there remains a notable gap in understanding the influence and mechanisms of industrial facility agglomeration on population distribution, particularly when considering different industry types and diverse regions comprehensively. Additionally, conventional panel data used to assess industrial facility agglomeration are constrained by limitations in coverage and timeliness. In contrast, Point of Interest (POI) data offers a superior solution with its real-time, fine-grained, and innovative advantages. This study utilizes real-time and fine-grained POI data in conjunction with the LandScan population raster dataset to precisely assess industrial facility agglomeration in 352 administrative units at the prefecture level and above in China. The key findings of this research can be summarized as follows: (1) factors influencing urban population growth rates have evolved, with increased significance attributed to Government Agencies and Social Groups, alongside a consistent impact from Science, Education, and Cultural Services. (2) The correlation between industrial facility agglomerations and population growth rates displayed linear relationships in 2015 and 2021, with varying strengths and directional shifts. (3) Regional disparities in industrial facility agglomeration patterns underscore the necessity for customized strategies to optimize industrial structures, foster innovation-driven sectors, and promote sustainable population growth.

Toward a Georeferencing Commons: A Crowdsourcing Case Study and the Creation of OldInsuranceMaps.net

As institutional archives digitize their historical map collections and make them publicly available online, researchers and members of the public can pursue new methods of engagement with the materials. Certain transformations, like “georeferencing” wherein a scanned map image is turned into a geospatial raster dataset, can be time-consuming and difficult to automate, but do lend themselves to crowdsourcing, a well-accepted means by which archival processing and public engagement can be carried out in concert. Inspired by the concept of an archival commons, this article recounts the design, creation, and public participation period of a new web-based, crowdsourced georeferencing platform—something like a georeferencing commons. This work took place as a masters thesis project through 2021 and 2022, and the result continues to grow and evolve as OldInsuranceMaps.net, a public space for georeferencing historical fire insurance maps from the Library of Congress digital Sanborn Map collection. While the initial iteration of this project was built from GeoNode and GeoServer, and focused on maps of Louisiana, this article concludes with significant updates on the platform, and how it is being used by institutions and individuals well outside of Louisiana today.

Is the existing methods sustainable? A hybrid approach to flood risk mapping

The hydraulic and integrated modeling approaches appear to stand out in the sequence of flood risk models that have been presented because of their predictive accuracy. The former has a high probability of under predicting and the latter has a high tendency to over-predict. This study proposed a methodological approach that combines the hydraulic and integrated models using analytical hierarchical raster fusion techniques to strengthen the weaknesses of the individual models. This study seeks to undertake a flood inundation model, a runoff model, and raster fusion models using GIS and HEC-RAS rain-on-grid methods to map flood risk in the Ona river basin of Ibadan city.•A hydraulic model was used to identify flood depth and inundation areas along a major stream channel, which was then extracted, rasterized, resampled, and reclassified to a spatial resolution of 5 m.•Several raster datasets (indicators) were created from land use, elevation, soil, and geological data layers using advanced GIS techniques.•AHP assisted raster data fusion model was used to combine all of the raster indicators into a single consolidated hybrid flood raster layer that revealed flood risk areas by magnitude.

National-Standards- and Deep-Learning-Oriented Raster and Vector Benchmark Dataset (RVBD) for Land-Use/Land-Cover Mapping in the Yangtze River Basin

A high-quality remote sensing interpretation dataset has become crucial for driving an intelligent model, i.e., deep learning (DL), to produce land-use/land-cover (LULC) products. The existing remote sensing datasets face the following issues: the current studies (1) lack object-oriented fine-grained information; (2) they cannot meet national standards; (3) they lack field surveys for labeling samples; and (4) they cannot serve for geographic engineering application directly. To address these gaps, the national-standards- and DL-oriented raster and vector benchmark dataset (RVBD) is the first to be established to map LULC for conducting soil water erosion assessment (SWEA). RVBD has the following significant innovation and contributions: (1) it is the first second-level object- and DL-oriented dataset with raster and vector data for LULC mapping; (2) its classification system conforms to the national industry standards of the Ministry of Water Resources of the People’s Republic of China; (3) it has high-quality LULC interpretation accuracy assisted by field surveys rather than indoor visual interpretation; and (4) it could be applied to serve for SWEA. Our dataset is constructed as follows: (1) spatio-temporal-spectrum information is utilized to perform automatic vectorization and label LULC attributes conforming to the national standards; and (2) several remarkable DL networks (DenseNet161, HorNet, EfficientNetB7, Vision Transformer, and Swin Transformer) are chosen as the baselines to train our dataset, and five evaluation metrics are chosen to perform quantitative evaluation. Experimental results verify the reliability and effectiveness of RVBD. Each chosen network achieves a minimum overall accuracy of 0.81 and a minimum Kappa of 0.80, and Vision Transformer achieves the best classification performance with overall accuracy of 0.87 and Kappa of 0.86. It indicates that RVBD is a significant benchmark, which could lay a foundation for intelligent interpretation of relevant geographic research about SWEA in the Yangtze River Basin and promote artificial intelligence technology to enrich geographical theories and methods.