Geospatial Datasets Research Articles

The first geospatial dataset of irrigated fields (2020–2024) in Vojvodina (Serbia)

Irrigation is a cornerstone of global food security, enabling sustainable agricultural production and helping to ensure that food is available for people around the world, now and in the future. Mapping irrigated fields provides valuable information for sustainable water management, agricultural development, and environmental conservation efforts. However, the collection of high-quality training data, which is necessary for accurate irrigation mapping remains costly and labour-intensive. To address this, we created a georeferenced regional dataset consisting of location, crop type, and occurrence of the irrigation equipment which are essential information for mapping irrigated fields. Four main irrigated crops were considered: maize, soybean, sugar beet, and wheat. The dataset, consisting of a total of 1256 parcels, is created for Vojvodina, the main agricultural area in Serbia, spanning the period of five years (2020–2024). This study’s goal is to give accessibility to our dataset which further can be explored and used for building or fine-tuning machine learning and deep learning models for the automatic detection of irrigated fields using satellite imagery.

Soil erosion susceptibility maps and raster dataset for the hydrological basins of North Africa

Soil erosion in North Africa modulates agricultural and urban developments as well as the impacts of flash floods. Existing investigations and associated datasets are mainly performed in localized urban areas, often representing a limited part of a watershed. The above compromises the implementation of mitigation measures for this vast area under accentuating extremes and continuous hydroclimatic fluctuations. To address this deficiency, we use the Revised Universal Soil Loss Equation to map surface erosion, providing the first insight into the decadal impacts of land degradation, which are largely unconstrained on North Africa’s continental scale. We generate soil erosion maps for the major hydrological basins of North Africa using Google Earth Engine and multiple hydroclimatic and land use datasets, covering 5.8 million square kilometers. The generated geospatial dataset integrates land use, soil erodibility, slope, vegetation cover, and land practices. The resulting product is an expansive and publicly available Soil erosion susceptibility maps and rasters dataset (SESMAR). This dataset is a crucial step toward understanding the drivers of soil erosion in this vast, poorly characterized area as well as its potential to be used for future soil conservation campaigns for both agricultural and urban planning. We validate SESMAR using the Global Rainfall Erosivity Database (GloREDa) and the European Soil Data Centre (ESDAC) datasets as well as published peer-reviewed reports across 20 watersheds, demonstrating a robust agreement in assessing the average annual soil loss values and soil erosion classes in local areas covered by independent study teams. Our continental maps show commendable accuracy, supporting scientists, practitioners, and policymakers in their efforts for more resilient land management practices across North Africa to mitigate rising hydroclimatic extremes.

Application of Google Earth Engine to Monitor Greenhouse Gases: A Review

Google Earth Engine (GEE) is a cloud-based platform revolutionizing geospatial analysis by providing access to vast satellite datasets and computational capabilities for monitoring environmental and societal issues. It incorporates machine learning (ML) techniques and algorithms as part of its tools for analyzing and processing large geospatial data. This review explores the diverse applications of GEE in monitoring and mitigating greenhouse gas emissions and uptakes. GEE is a cloud-based platform built on Google’s infrastructure for analyzing and visualizing large-scale geospatial datasets. It offers large datasets for monitoring greenhouse gas (GHG) emissions and understanding their environmental impact. By leveraging GEE’s capabilities, researchers have developed tools and algorithms to analyze remotely sensed data and accurately quantify GHG emissions and uptakes. This review examines progress and trends in GEE applications, focusing on monitoring carbon dioxide (CO2), methane (CH4), and nitrous oxide/nitrogen dioxide (N2O/NO2) emissions. It discusses the integration of GEE with different machine learning methods and the challenges and opportunities in optimizing algorithms and ensuring data interoperability. Furthermore, it highlights GEE’s role in pinpointing emission hotspots, as demonstrated in studies monitoring uptakes. By providing insights into GEE’s capabilities for precise monitoring and mapping of GHGs, this review aims to advance environmental research and decision-making processes in mitigating climate change.

Improvement of the Reliability of Urban Park Location Results Through the Use of Fuzzy Logic Theory

Green areas, thanks to their relatively unified natural systems, play several key roles. They contribute to the proper functioning and sustainable development of cities and also determine the quality of life for their inhabitants. As a result, urban planners and policy-makers frequently aim to maximize the benefits of green spaces by creating various programs and strategies focused on green infrastructure development, such as the Green City initiative. One of the objectives of this program is to create new urban parks. This research focuses on developing a new method for selecting sites for urban parks, taking into account factors related to the environment, accessibility, and human activity. The research was carried out for the area of Ciechanów city. To make the city areas more attractive to residents, the authorities aim to increase green spaces and also revitalize the existing greenery. The combination of the Fuzzy AHP method and fuzzy set theory (selecting appropriate fuzzy membership for each factor), along with the use of large and diverse geospatial datasets, minimized subjectivity in prioritizing criteria and allowed for a fully automated analysis process. Among the factors analyzed, land use emerged as the most significant, followed by the normalized difference vegetation index (NDVI) and proximity to surface water. The results indicated that 16% of the area was deemed highly suitable for urban park development, while 15% was considered unsuitable. One-at-a-time (OAT) sensitivity analysis, based on changes in the weight of the land-use factor, revealed that a 75% reduction in weight resulted in a nearly 57.2% decrease in unsuitable areas, while a 75% increase in weight led to a 40% expansion of the most suitable locations. The potential park locations were compared with a heat map of urban activity in the city. The developed method contributes to the discourse on the transparency of location decisions and the validity of the criteria used, to promote sustainable urban development that provides residents with access to active recreation.

Analisis Uji Multikolinearitas Variabel Lingkungan Hutan Bakongan-Bengkung, Kawasan Ekosistem Leuser: Implikasi Terhadap Habitat Spesies Kunci

This study aims to analyze the multicollinearity of environmental variables in the Bakongan-Bengkung Forest, part of the Leuser Ecosystem, to understand its implications for the habitat of key species such as Sumatran elephants, Sumatran rhinoceros, Sumatran tigers, and Sumatran orangutans. The research was conducted in August 2023 across an area of 75.912,46 hectares spanning three districts in Aceh. The data utilized includes elevation, slope, river density estimation, Normalized Difference Vegetation Index (NDVI), distance from roads, and annual rainfall, sourced from various geospatial datasets. Data processing was performed using ArcGIS 10.3, Google Earth Engine (GEE), and RStudio 4.2.2. Multicollinearity testing was carried out using Pearson correlation coefficients to identify relationships between environmental variables. The analysis revealed a significant positive correlation between elevation and annual rainfall, with a correlation coefficient of 0,724, indicating a strong linear relationship. This correlation suggests that higher elevations in the area are associated with increased rainfall, likely due to orographic effects. These findings are crucial for conservation planning and habitat management for wildlife. The correlation between elevation and annual rainfall should be considered when developing accurate habitat models for key species in the Bakongan-Bengkung Forest, to ensure effective and sustainable conservation strategies.

Assessing the suitability of settlement delineations for monitoring infilling: A web- and GIS-based expert evaluation approach

21st century urbanisation features not only the growth of city populations but also the emergence of densification (infilling) as significant trends in urban development. While urban sprawl has long been acknowledged for its adverse effects, understanding densification remains challenging due to inadequate empirical and statistical frameworks. This study investigates the suitability of different geospatial datasets and methods for delineating settlement areas and assessing infill housing, an aspect crucial for urban planning and development. Quantitative and qualitative analyses reveal notable variations in the classification of settlement areas and infilling across datasets. Quantitatively, the study shows distinct differences in the delineation of settlement areas, with the share of infilling varying significantly. Qualitatively, expert assessments highlight the strengths and weaknesses of datasets regarding their accuracy and consistency, revealing that the method to delineate settlement areas significantly impacts the balance between infilling and greenfield development. The study underscores the need for a nuanced approach to conceptualising densification measurement, particularly in defining urban boundaries.

Coastal hardening and what it means for the world’s sandy beaches

Sea level rise is expected to cause chronic shoreline retreat, affecting over 10% of the world’s population in low-elevation coastal zones (LECZ). Sandy beaches supported by man-made structures are more vulnerable to substantial beach area loss due to restricted landward migration, affecting ecosystem services. However, the global extent of ‘hardened’ sandy coastlines at risk of ‘severe beach loss’ has not been comprehensively quantified. Here, using products and geospatial datasets derived from satellite imagery, we find that, 33% of the world’s sandy coastline is currently hardened. Analysis of the results by IPCC AR6 regions show that the most hardened coastal regions are the Bay of Bengal, Western & Central Europe, the Mediterranean, Western North America, and East Asia. Linking coastal hardening information with existing shoreline retreat projections, we find that under SSP5-8.5, up to 26% of the world’s sandy coastline (~52,100 km) is likely to face severe beach loss by the end of the 21st century. Under a moderate emissions scenario (SSP2-4.5), this projection decreases to 21% (~42,080 km), highlighting the potential mitigation gain. The results also show that the vast majority of projected severe sandy beach losses are in high and upper-middle-income countries, with up to 82% of severe losses under SSP5-8.5 and up to 81% under SSP2-4.5 by the end of the 21st century, relative to the total length of sandy coastline, including both hardened and natural coastlines. The IPCC AR6 regions with the highest projected sandy beach losses include Eastern North America, Northern South America, the Mediterranean, the Bay of Bengal, Western Africa, and South-east Asia.

A holistic approach to assessing REDD+ forest loss baselines through ex post analysis

Abstract The implementation of REDD+ (Reducing Emissions from Deforestation and Forest Degradation) projects has become a key Nature Based Solutions strategy to protect at-risk forests using the sale of verified emission reductions (carbon credits) as financing, generated by reducing forest loss against counterfactual baseline scenarios. Controversy over the reasonableness of such baseline scenarios has thrown this nascent market mechanism into disarray. While new technical approaches to baseline-setting that promise wider market acceptance are set to roll out in the coming years, existing projects are becoming unviable, as carbon credit buyers reduce investment due to lost confidence in the integrity of emissions reduction claims. Transparent, reproducible methods to assess existing REDD+ project baselines are needed in order to provide a clearer picture of the real impact of projects, and provide an objective basis on which investment decisions can be made today. Here we introduce such a method. In contrast to existing studies which utilize only one method to create a single ‘control,’ we integrate actual forest loss rates from a variety of control sites to establish a ‘zone of reasonable accuracy (or ZORA)’. Application of our method in Cambodia, using two geospatial datasets (one global and one locally calibrated), shows that all three project baselines fall within or below ZORA. This approach is fully reproducible, and provides a transparent way for analysts to assess REDD+ baselines during this critical time when investment in forest protection must increase dramatically and without delay.

Exploring deep learning models for roadside landslide prediction: Insights and implications from comparative analysis

This study undertakes a comparative analysis of four distinct deep learning models, i.e., Convolutional Neural Network (CNN), Deep Neural Network (DNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM), in the context of roadside landslide prediction, aiming to provide comprehensive insights into their strengths and weaknesses. A geospatial dataset from the Lai Châu province, Vietnam, with thirteen environmental factors (elevation, aspect, slope, curvature, topographic wetness index, stream power index, flow accumulation, geology, normalized difference vegetation index, maximum rainfall, average annual rainfall, and proximity to faults and rivers) and 284 road-along landslides was considered for analysis. Our modeling efforts yielded invaluable insights into the performance of these models during both training and validation phases. The DNN model emerged as the frontrunner in the training phase, boasting the highest area under the curve (AUC) of 0.94, accuracy of 87.47%, kappa of 0.748, and lowest RMSE of 0.125. However, during validation, the CNN model outshone others, exhibiting the highest AUC of 0.88 and overall accuracy of 80.00%. Despite variations in performance metrics across phases, CNN consistently demonstrated robust predictive prowess. The findings of this study underscore the significance of selecting appropriate machine learning models tailored to specific contexts and objectives. Moreover, they contribute valuable insights for decision-makers and researchers alike, ultimately aiming to enhance the safety and resilience of communities inhabiting landslide-prone areas. Moving forward, future research directions may explore ensemble methods, novel architectures, and interpretability techniques to further advance predictive accuracy and applicability in roadside landslide susceptibility modeling.

Using a discrete global grid system for a scalable, interoperable, and reproducible system of land-use mapping

ABSTRACT An accurate and timely land-use map of an area is a valuable geospatial dataset. Making one requires assembling heterogeneous geospatial input data. This becomes computationally expensive as the number of inputs grow or the combinational classification logic becomes more convoluted. We present as a solution an analytical framework based on a DGGS. This provides a spatial data structure that: facilitates horizontal scaling; improves geospatial data interoperability; and makes classified geospatial data easier to reproduce. We demonstrate a benchmark of land-use assignment with a DGGS against the vector and raster geospatial data models. Significant performance benefits are apparent over the vector case, while performance is equivalent to raster. Yet a DGGS has other compelling benefits that makes it more convenient to use in the domain of land-use assignment than the raster data model.

Geospatial Variation in Vaccination Coverage and Zero-Dose Prevalence at the District, Ward and Health Facility Levels Before and After a Measles Vaccination Campaign in Nigeria.

Many measles endemic countries with suboptimal coverage levels still rely on vaccination campaigns to fill immunity gaps and boost control efforts. Depending on local epidemiological patterns, national or targeted campaigns are implemented, following which post-campaign coverage surveys (PCCSs) are conducted to evaluate their performance, particularly in terms of reaching previously unvaccinated children. Due to limited resources, PCCS surveys are designed to be representative at coarse spatial scales, often masking important heterogeneities in coverage that could enhance the identification of areas of poor performance for follow-up via routine immunization strategies. Here, we undertake geospatial analyses of the 2021 measles PCCS in Nigeria to map indicators of coverage measuring the individual and combined performance of the campaign and routine immunization (RI) at 1 × 1 km resolution and the ward and district levels in 13 states. Using additional geospatial datasets, we also produced estimates of numbers of unvaccinated children during the campaign and numbers of measles-containing vaccine (MCV) zero-dose children before and after the campaign at these levels and within health facility catchment areas. Our study revealed that although the campaign reduced the numbers of MCV zero-dose children in all the districts, areas of suboptimal campaign and RI performance with considerable numbers of zero-dose children remained. Our analyses further identified wards and health facility catchment areas with higher numbers of unvaccinated children within these areas. Our outputs provide a robust evidence base to plan and implement follow-up RI strategies and to guide future campaigns at flexible and operationally relevant spatial scales.

Optimized AI-MPM: Application of PSO for tuning the hyperparameters of SVM and RF algorithms

Modern computational techniques, particularly Support Vector Machines (SVM) and Random Forest (RF) models, are revolutionizing predictive mineral prospectivity mapping. These advanced systems excel at identifying prime resource locations but require meticulous fine-tuning of their internal settings to achieve peak performance. Careful calibration of these configurations during the learning phase significantly enhances their ability to detect promising deposits. The main goal of this study is to introduce a hybrid model called PSO -SVM and PSO-RF, which aim to combine particle swarm optimization (PSO) with SVM (with RBF kernel) and RF models. This hybrid model automatically adjusts the optimized hyperparameters of SVM and RF, resulting in highly accurate predictions and a wide range of applicability. The PSO algorithm has been applied to fine-tune two main parameters (C and λ) for SVM-RBF and three main parameters (NT, NS, and d) for RF, creating efficient models for both. The proposed hybrid model as well as the traditional versions of SVM and RF models, were tested using a geo-spatial dataset related to Cu mineralization in Kerman belt, SE Iran. Forecasting algorithms were developed by integrating diverse datasets: multi-element concentrations from stream samples, bedrock and fault line maps, indicators of hot fluid interaction, aeromagnetic survey results, coordinates of previously identified copper-rich igneous intrusions, and verified ore body positions as reference points. The models' performance was evaluated using four validation methods: Multi-round data partitioning (K-fold), error classification tables (confusion matrix), true-positive vs. false-positive graphical analysis ((ROC) curve), and P-A plot were used to assess algorithms and models performance. Tests revealed that the PSO-SVM surpassed all competitors. Impressively, this fine-tuned classifier identified prime target zones in merely one-seventh of the region (14%), yet these areas encompassed nearly all verified resource sites (97%).

A geospatial dataset of lichen key attributes in the Earth's three poles.

In the Antarctic, Arctic, and Tibetan Plateau-recognized as the Earth's three poles characterized by extremely harsh environments-lichens prevail in the ecosystem and play crucial roles as pioneer species. Despite their importance, studies investigating the spatial distribution patterns of lichen attributes are scarce due to a lack of appropriate datasets. To bridge this gap and enhance our understanding of the growth preferences of lichens in these areas, here we present a geospatial dataset encompassing key attributes of lichens, such as color type and growth form, for over 2800 lichen species and 170,000 in-situ lichen records. The dataset facilitates the creation of the first spatial distribution map illustrating the variation of lichen attributes across different latitudes and longitudes. This can serve as a foundational resource for studies on the relationship between lichen types and their growing environment, which is a vital scientific question in the ecology domain. Additionally, it can contribute to the development of specialized remote sensing technique tailored for lichen monitoring, which is currently lacking.

Observational benchmarks inform representation of soil organic carbon dynamics in land surface models

Abstract. Representing soil organic carbon (SOC) dynamics in Earth system models (ESMs) is a key source of uncertainty in predicting carbon–climate feedbacks. Machine learning models can help identify dominant environmental controllers and establish their functional relationships with SOC stocks. The resulting knowledge can be integrated into ESMs to reduce uncertainty and improve predictions of SOC dynamics over space and time. In this study, we used a large number of SOC field observations (n=54 000), geospatial datasets of environmental factors (n=46), and two machine learning approaches (namely random forest, RF, and generalized additive modeling, GAM) to (1) identify dominant environmental controllers of global and biome-specific SOC stocks, (2) derive functional relationships between environmental controllers and SOC stocks, and (3) compare the identified environmental controllers and predictive relationships with those in models used in Phase 6 of the Coupled Model Intercomparison Project (CMIP6). Our results showed that the diurnal temperature, drought index, cation exchange capacity, and precipitation were important observed environmental predictors of global SOC stocks. While the RF model identified 14 environmental factors that describe climatic, vegetation, and edaphic conditions as important predictors of global SOC stocks (R2=0.61, RMSE = 0.46 kg m−2), current ESMs oversimplify the relationships between environmental factors and SOC, with precipitation, temperature, and net primary productivity explaining > 96 % of the variability in ESM-modeled SOC stocks. Further, our study revealed notable disparities among the functional relationships between environmental factors and SOC stocks simulated by ESMs compared with observed relationships. To improve SOC representations in ESMs, it is imperative to incorporate additional environmental controls, such as the cation exchange capacity, and refine the functional relationships to align more closely with observations.

Towards maximizing geospatial data usage in north eastern India using open-source scalable user-centric applications

Abstract. The north eastern region of India is characterized by limited physical connectivity and challenging terrain, that requires innovative approaches for effective developmental planning and monitoring using geospatial data and user-centric applications. This paper focuses on leveraging space-based data and applications to address these challenges and enhance decision-making processes in governance. A unified framework for interoperable spatial data sharing has been developed, ensuring that data is easily discoverable, searchable, and consumable through metadata standards and OGC interoperable data services. A dedicated spatial data repository has been established, offering real-time access to over 1400 geospatial datasets and facilitating better decision-making and geo-analytics among diverse user groups. The repository operates on an open-source platform with integrated map viewers and geo-analytics tools, allowing for interactive exploration and visualization of geospatial data. Additionally, 35 user-centric geospatial applications have been operationalized, all developed using open-source geospatial tools and standards. Capacity building programs have been conducted to increase awareness and maximize the utilization of geospatial data services and applications across the region. The platform has boosted utilization of geospatial data services and applications in the region for overall planning and developmental activities for smart governance and societal benefits.

Comprehensive Representations of Subpixel Land Use and Cover Shares by Fusing Multiple Geospatial Datasets and Statistical Data with Machine-Learning Methods

Land use and cover change (LUCC) is a key factor influencing global environmental and socioeconomic systems. Many long-term geospatial LUCC datasets have been developed at various scales during the recent decades owing to the availability of long-term satellite data, statistical data and computational techniques. However, most existing LUCC products cannot accurately reflect the spatiotemporal change patterns of LUCC at the regional scale in China. Based on these geospatial LUCC products, normalized difference vegetation index (NDVI), socioeconomic data and statistical data, we developed multiple procedures to represent both the spatial and temporal changes of the major LUC types by applying machine-learning, regular decision-tree and hierarchical assignment methods using northeastern China (NEC) as a case study. In this approach, each individual LUC type was developed in sequence under different schemes and methods. The accuracy evaluation using sampling plots indicated that our approach can accurately reflect the actual spatiotemporal patterns of LUC shares in NEC, with an overall accuracy of 82%, Kappa coefficient of 0.77 and regression coefficient of 0.82. Further comparisons with existing LUCC datasets and statistical data also indicated the accuracy of our approach and datasets. Our approach unfolded the mixed-pixel issue of LUC types and integrated the strengths of existing LUCC products through multiple fusion processes. The analysis based on our developed dataset indicated that forest, cropland and built-up land area increased by 17.11 × 104 km2, 15.19 × 104 km2 and 2.85 × 104 km2, respectively, during 1980–2020, while grassland, wetland, shrubland and bare land decreased by 26.06 × 104 km2, 4.24 × 104 km2, 3.97 × 104 km2 and 0.92 × 104 km2, respectively, in NEC. Our developed approach accurately reconstructed the shares and spatiotemporal patterns of all LUC types during 1980–2020 in NEC. This approach can be further applied to the entirety of China, and worldwide, and our products can provide accurate data supports for studying LUCC consequences and making effective land use policies.

Runoff Dynamics and Soil Erosion Assessment using a SWAT Model at Upper Cauvery River Basin

The increasing availability of geospatial datasets on watershed characteristics and hydro-meteorological variables emphasises the importance of integrated hydrological models for effective catchment management. Climatic and physiographic determinants such as topography, land use, soil properties, and anthropogenic interventions substantially influence a catchment's hydrological equilibrium. The SWAT model was used to elucidate rainfall-runoff dynamics in the Upper Cauvery River Basin, Karnataka, India (36,682 km²), applying the SCS Curve Number (CN) method for runoff estimation. Runoff was estimated for 2012–2021 using rainfall data from the Indian Meteorological Department (IMD), soil data from the FAO, and land use/land cover and slope datasets.Soil erosion, exacerbated by intensified agricultural practices, was evaluated using the Revised Universal Soil Loss Equation (RUSLE) model integrated with Geographic Information Systems (GIS). The SWAT model results showed that runoff accounted for 15-20% of the total precipitation, with an annual soil loss of 2027.95 tons. The predominance of agricultural land use, covering 66.29% of the basin, significantly contributed to high runoff, whereas the forested areas (26.48%) demonstrated a low runoff potential. About 38% of the basin exhibited a very low soil loss risk, while 11% was classified as high risk and 9% as very high risk. The SWAT model is recognized for its robustness, and this research aims to leverage its capabilities to validate its effectiveness in estimating runoff and erosion, providing crucial insights for advancing sustainable catchment resource management.

Application of Analytical Hierarchy Process (AHP) and Multi-Criteria Evaluation (MCE) for a case study and scenario assessment of flood risk in the White Volta Basin of the Upper East Region, Ghana

In recent years, Ghana, particularly the inhabitants of the Upper East Region, has experienced profound impact of flooding, largely attributable to the complex interplay of climatic factors. This research embarks on a comprehensive assessment of flood risk zones nestled within the White Volta Basin, situated in the Upper East Region. The study employs advanced cartographic methodologies and uses Geographic Information Systems (GIS) in conjunction with the Analytical Hierarchy Process (AHP) to systematically categorize areas susceptible to inundation. Leveraging geospatial datasets acquired from satellites such as Landsat and Sentinel. Topographic, slope, and Land Use/Land Cover (LULC) maps have been constructed. The empirical findings underscore the susceptibility of specific regions, including the Talensi District, territories within Bawku West, and some segments of the Bolgatanga Municipal area, to escalated flood risk. Additionally, the research underscores the high vulnerability of communities such as Nunku, Tolla, Zaare, Pwalugu, Balungu, Winkongo, Biung, and Tongo to the negative impact of inundation. Significantly, the study unveils a pivotal factor in the perpetuation of flood devastation—namely, the role of water discharge. This intrinsic linkage between discharge rates and flood occurrences underscores the pressing need to address this critical component in mitigation strategies to reduce adverse impacts on the basin’s resident communities. The insights derived from the study offer some level of hope for residents, providing essential knowledge concerning flood-prone areas and optimal timing for agricultural activities to safeguard their cherished livelihoods.

An automated system for 2D building detection from UAV-based geospatial datasets

The focus of this manuscript is on integrating optical images and laser point clouds carried on low-cost UAVs to create an automated system capable of generating urban city models. After pre-processing both datasets, we co-registered both datasets using the DLT transformation model. We estimated structure heights from the LiDAR dataset through a progressive morphological filter followed by removing bare ground. Unsupervised and supervised image classification techniques were applied to a six-band image created from the optical and LiDAR datasets. After finding building footprints, we traced their edges, outlined their borderlines, and identified their geometric boundaries through several image processing and rule-based feature identification algorithms. Comparison between manually digitized and automatically extracted buildings showed a detection rate of about 92.3 % with an average of 7.4 % falsely identified areas with the six-band image in contrast to classifying only the RGB image that detected about 63.2 % of the building pixels with 25.3 % pixels incorrectly identified. Moreover, our building detection rate with the 6-band image was superior to that attained by performing traditional image segmentation for only the LiDAR DEM. Shifts in the horizontal coordinates between corner points identified by a human operator and those detected by the proposed system were in the range of 10–15 cm. This is an improvement over traditional satellite and manned-aerial large mapping systems that have lower accuracies due to sensor limitations and platform altitude. These findings demonstrate the benefits of fusing multiple UAV remote sensing datasets over utilizing a single dataset for urban area mapping and 3D city modeling.

Urban forest cover and ecosystem service response to fire varies across California communities

Urban fires that result from wildfires are an emerging, extreme event affecting communities and urban forests globally. However, much of the fire effects on urban ecosystems literature is primarily focused on Wildland-Urban Interface (WUI) areas, correlates of building loss, risk mitigation, and wildland vegetation and fuels. Three recent urban fires in California USA provided an opportunity to explore these effects on urban forests: the 2017 Tubbs (Santa Rosa) and Thomas (Ventura) fires and the 2018 Camp fire that burned Paradise. Accordingly, we analyzed pre- and post-fire neighborhood level urban tree cover (nUTC) change over 5 years using Sentinel and LiDAR data (10 m resolution). Then, we explored the effects of fire severity on changes in several regulating ecosystem services (e.g., carbon, air pollution, stormwater). Findings from the Rapid Assessment of Vegetation Condition after Wildfire severity processes and other geospatial datasets show that fire effects were patchy with fire severity within neighborhoods ranging from unburned to extreme. We found that ∼5 years after the fires, and relative to adjacent non-fire affected neighborhoods, Ventura and Santa Rosa’s nUTC is recovering to pre-fire levels while Paradise’s nUTC is being consistently lost over time. Ventura and Santa Rosa had 20–25 % of their fire affected area outside established WUI boundaries. However, local-scale urban tree cover and ecosystem service supply are lagged, and recovery time depends on the surrounding biome and socio-ecological context. In inland, higher elevation communities – like Paradise – the recovery of nUTC and the associated ecosystem services might materialize over a much longer timeframe. Our study provides a roadmap to assess the response of urban wildfire-affected tree cover and ecosystem services across space and time. It is also one of the first assessments of fire effects on urban ecosystems and communities outside of WUI boundaries that are now experiencing increased threat from wildfires globally.