High Spatial Resolution Data Research Articles

AI-driven optimization of agricultural water management for enhanced sustainability

Optimizing agricultural water resource management is crucial for food production, as effective water management can significantly improve irrigation efficiency and crop yields. Currently, precise agricultural water demand forecasting and management have become key research focuses; however, existing methods often fail to capture complex spatial and temporal dependencies. To address this, we propose a novel deep learning framework that combines remote sensing technology with the UNet-ConvLSTM (UCL) model to effectively integrate spatial and temporal features from MODIS and GLDAS datasets. Our model leverages the high-resolution spatial data from UNet and the temporal dependencies captured by ConvLSTM to significantly improve prediction accuracy. Experimental results demonstrate that our UCL model achieves the best R2\\documentclass[12pt]{minimal} \\usepackage{amsmath} \\usepackage{wasysym} \\usepackage{amsfonts} \\usepackage{amssymb} \\usepackage{amsbsy} \\usepackage{mathrsfs} \\usepackage{upgreek} \\setlength{\\oddsidemargin}{-69pt} \\begin{document}$$R^2$$\\end{document} compared to existing methods, reaching 0.927 on the MODIS dataset and 0.935 on the GLDAS dataset. This approach highlights the potential of AI and remote sensing technologies in addressing critical challenges in agricultural water management, contributing to more sustainable and efficient food production systems.

Evaluating the Patterns of Maize Development in the Hetao Irrigation Region Using the Sentinel-1 GRD SAR Bipolar Descriptor.

Assessing maize yield is critical, as it is directly influenced by the crop's growth conditions. Therefore, real-time monitoring of maize growth is necessary. Regular monitoring of maize growth indicators is essential for optimizing irrigation management and evaluating agricultural yield. However, quantifying the physical aspects of regional crop development using time-series data is a challenging task. This research was conducted at the Dengkou Experimental Station in the Hetao irrigation area, Northwest China, to develop a monitoring tool for regional maize growth parameters. The tool aimed to establish a correlation between satellite-based physical data and actual crop growth on the ground. This study utilized dual-polarization Sentinel-1A GRD SAR data, accessible via the Google Earth Engine (GEE) cloud platform. Three polarization descriptors were introduced: θc (pseudo-scattering type parameter), Hc (pseudo-scattering entropy parameter), and mc (co-polar purity parameter). Using an unsupervised clustering framework, the maize-growing area was classified into several scattering mechanism groups, and the growth characteristics of the maize crop were analyzed. The results showed that throughout the maize development cycle, the parameters θc, Hc, and mc varied within the ranges of 26.82° to 42.13°, 0.48 to 0.89, and 0.32 to 0.85, respectively. During the leaf development stage, approximately 80% of the maize sampling points were concentrated in the low-to-moderate entropy scattering zone. As the plants reached the big trumpet stage, the entire cluster shifted to the high-entropy vegetation scattering zone. Finally, at maturity, over 60% of the sampling points were located in the high-entropy distribution scattering zone. This study presents an advanced analytical tool for crop management and yield estimation by utilizing precise and high-resolution spatial and temporal data on crop growth dynamics. The tool enhances the accuracy of crop growth management across different spatial and temporal conditions.

Monitoring of Heracleum sosnowskyi Manden Using UAV Multisensors: Case Study in Moscow Region, Russia

Detection and mapping of Sosnowsky’s hogweed (HS) using remote sensing data have proven effective, yet challenges remain in identifying, localizing, and eliminating HS in urban districts and regions. Reliable data on HS growth areas are essential for monitoring, eradication, and control measures. Satellite data alone are insufficient for mapping the dynamics of HS distribution. Unmanned aerial vehicles (UAVs) with high-resolution spatial data offer a promising solution for HS detection and mapping. This study aimed to develop a method for detecting and mapping HS growth areas using a proposed algorithm for thematic processing of multispectral aerial imagery data. Multispectral data were collected using a DJI Matrice 200 v2 UAV (Dajiang Innovation Technology Co., Shenzhen, China) and a MicaSense Altum multispectral camera (MicaSense Inc., Seattle, WA, USA). Between 2020 and 2022, 146 sites in the Moscow region of the Russian Federation, covering 304,631 hectares, were monitored. Digital maps of all sites were created, including 19 digital maps (orthophoto, 5 spectral maps, and 13 vegetation indices) for four experimental sites. The collected samples included 1080 points categorized into HS, grass cover, and trees. Student’s t-test showed significant differences in vegetation indices between HS, grass, and trees. A method was developed to determine and map HS-growing areas using the selected vegetation indices NDVI > 0.3, MCARI > 0.76, user index BS1 > 0.10, and spectral channel green > 0.14. This algorithm detected HS in an area of 146.664 hectares. This method can be used to monitor and map the dynamics of HS distribution in the central region of the Russian Federation and to plan the required volume of pesticides for its eradication.

Seasonally flooded landscape connectivity and implications for fish in the Napo Moist Forest: A high-resolution mapping approach

The Amazon River Basin's fish diversity is shaped by its dynamic flood-pulse system, critical for hydrological and ecological connectivity. This study examines the Napo Moist Forest (NMF) ecoregion, mapping permanent and seasonally flooded areas from 2018 to 2021 using remote sensing and deep learning models. We aimed to map these areas at a high spatial resolution (10-m pixels) and analyse their role in maintaining lateral connectivity essential for fish diversity. Using synthetic aperture radar data from Sentinel-1 combined with deep learning algorithms, we produced high-accuracy flood maps to assess landscape connectivity between rivers and floodplains. Our methodology included creating a ground truth dataset with the Normalized Difference Water Index and integrating high-resolution optical data for model training, overcoming challenges of cloud coverage and dense vegetation. Our predictive model achieved high accuracy (mean pixel accuracy = 97 %) and consistently predicted 4801 km² of surface water, with only 3 % (130 km²) being seasonally flooded areas over four years. The Caquetá, Bajo Marañón, Napo, and Pastaza watersheds accounted for nearly 60 % of the flooded areas, highlighting their ecological importance. Connectivity analysis in three areas of interest within the NMF ecoregion revealed important seasonal and interannual fluctuations in hydrological connectivity due to changes in flooded patch characteristics. Reductions in the number and flooded patch area during low water seasons increased the distance between patches, leading to a disconnection between flooded areas, channels and rivers. Despite hydrological fluctuations, certain patches maintained consistent flooding, critical for lateral connectivity and sustaining aquatic biodiversity. These seasonally flooded areas act as connectors, influencing patch dynamics and connectivity with tributaries. Seasonal and interannual variations in hydrological connectivity are crucial for sustaining fish diversity. Conserving dynamic floodplains supports migratory fish life cycles and biodiversity. This study underscores the importance of high-resolution temporal and spatial data in conservation planning for aquatic ecosystems.

Presenting a transdisciplinary robust approach for comprehensive assessment of large-scale underground water resources in western Indo-Gangetic Basin

Overexploitation, pollution, and anthropogenic activities threaten the sustainability of groundwater resources in the western Indo-Gangetic Basin. Meanwhile, distinguishing regions prone to contamination and understanding the natural and anthropogenic factors affecting groundwater quality is challenging due to the heterogeneous nature of aquifer systems and the lack of high-resolution spatial and temporal data on aquifer protective hydrogeological layers. This study presents a transdisciplinary robust approach combining regional electrical resistivity surveys, hydrogeological data, physicochemical analyses, and geospatial datasets to identify regions prone to contamination and understand the impacts of natural and anthropogenic factors on groundwater resources. This approach involves three key steps: evaluating the geohydraulic nature of aquifer protective hydrogeological layers, mapping the aquifer vulnerability index (AVI), and conducting comparative analyses of potentially vulnerable areas with groundwater quality index (GWQI) and hydrological factors. Firstly, model-based inversion of ID Vertical Electrical Sounding (VES) data provides insights into geoelectrical indices such as depth, thickness, apparent resistivity, longitudinal conductance, transverse resistance, and longitudinal resistivity of aquifer protective hydrogeological layers. Second, the Artificial Neural Network (ANN) model is used as a multilayer perceptron network to simulate hydraulic conductivity (K) using geoelectrical indices of aquifer protective hydrogeological layers. Subsequently, by considering ANN-derived K and VES-derived h of aquifer protective hydrogeological layers, the dynamic hydraulic resistance to the vertical flow of wastewater through the protective hydrogeological layers evaluated the index of the potentially vulnerable areas. Comparative analyses of potentially vulnerable areas with GWQI and hydrological factors (e.g., digital elevation model, soil, drainage density, lineament density, slope) enhance understanding regions prone to contaminants and land surface stress. Findings show that the ANN approach to simulate K, reducing effort with costs associated with slug testing is significant for AVI assessment. Furthermore, the geohydraulic characteristics, vulnerability indexing, and comparative analyses assist in identifying contamination-prone areas, improving groundwater resource protection and exploration activities.

A dataset of 0.05-degree leaf area index in China during 1983–2100 based on deep learning network

Leaf Area Index (LAI) is a critical parameter in terrestrial ecosystems, with high spatial resolution data being extensively utilized in various research studies. However, LAI data under future scenarios are typically only available at 1° or coarser spatial resolutions. In this study, we generated a dataset of 0.05° LAI (F0.05D-LAI) from 1983–2100 in a high spatial resolution using the LAI Downscaling Network (LAIDN) model driven by inputs including air temperature, relative humidity, precipitation, and topography data. The dataset spans the historical period (1983–2014) and future scenarios (2015–2100, including SSP-126, SSP-245, SSP-370, and SSP-585) with a monthly interval. It achieves high accuracy (R² = 0.887, RMSE = 0.340) and captures fine spatial details across various climate zones and terrain types, indicating a slightly greening trend under future scenarios. F0.05D-LAI is the first high-resolution LAI dataset and reveals the potential vegetation variation under future scenarios in China, which benefits vegetation studies and model development in earth and environmental sciences across present and future periods.

Accurate solar radiation site adaptation: Harnessing satellite data and in situ measurements

Accurate solar radiation data are essential to optimize solar energy systems and assess their feasibility. In this study, we propose a site-adaptation procedure based on a machine learning model trained to enhance the accuracy of solar radiation data using a combination of the National Solar Radiation Database (NSRDB) and in situ data collected in southern Colombia. The NSRDB provides high temporal and spatial resolution data, while in situ data offer accurate localized measurements specific to the study area. Our machine learning models were trained to learn the relationships between NSRDB data and in situ meteorological station data. The results demonstrate promising predictive capabilities, with the extreme grading boosting model effectively reducing mean absolute error, while a neural network model trained with the triplet loss function proved effective in minimizing mean bias error (MBE) and improving correlation between model-adjusted and in situ collected data. These findings make significant contributions to the field of solar radiation prediction, highlighting the effectiveness of amalgamating NSRDB and in situ data for precise solar radiation estimation, and promote the advancement of solar energy system design and decision-making processes.

Agricultural Drought Monitoring: A Comparative Review of Conventional and Satellite-Based Indices

Drought is a natural hazard that causes significant economic and human losses by creating a persistent lack of precipitation that impacts agriculture and hydrology. It has various characteristics, such as delayed effects and variability across dimensions like severity, spatial extent, and duration, making it difficult to characterize. The agricultural sector is especially susceptible to drought, which is a primary cause of crop failures and poses a significant threat to global food security. To address these risks, it is crucial to develop effective methods for identifying, classifying, and monitoring agricultural drought, thereby aiding in planning and mitigation efforts. Researchers have developed various tools, including agricultural drought indices, to quantify severity levels and determine the onset and evolution of droughts. These tools help in early-stage forecasting and ongoing monitoring of drought conditions. The field has been significantly advanced by remote sensing technology, which now offers high-resolution spatial and temporal data, improving our capacity to monitor and assess agricultural drought. Despite these technological advancements, the unpredictable nature of environmental conditions continues to pose challenges in drought assessment. It remains essential to provide an overview of agricultural drought indices, incorporating both conventional methods and modern remote sensing-based indices used in drought monitoring and assessment.

Quantitative analysis of the sensitivity and spatial stratified heterogeneity of extreme precipitation across river basins

Global warming is expected to lead to a continuous increase in extreme precipitation. However, the response of extreme precipitation to climate change remains not entirely clear. This study quantitatively analyzes extreme precipitation in multiple river basins of China over the past nearly 60 years using high spatial resolution data. Both extreme precipitation and mean precipitation exhibit a spatial distribution pattern of higher values in the southeast and lower values in the northwest. However, their sensitivity to temperature shows an asymmetric spatial pattern, with higher sensitivity in the northwest and lower sensitivity in the southeast. Overall, the sensitivity of extreme precipitation to temperature (9.6 %/K) is 1.1 times that of mean precipitation (8.8 %/K). Additionally, the sensitivity of extreme precipitation in relatively dry areas (Continental River Basin) is about five times that in relatively wet areas (other river basins). Vegetation has the highest explanatory power (i.e., q-value) for the spatial stratified heterogeneity of extreme precipitation, ranging from 0.61 to 0.72, with the explanatory power of natural factors exceeding that of societal factors. Furthermore, the interaction between vegetation and elevation enhances the explanatory power for the spatial stratified heterogeneity of extreme precipitation, reaching values between 0.74 and 0.82.

Predicting plants in the wild: Mapping arctic and boreal plants with UAS-based visible and near infrared reflectance spectra

Biophysical changes in the Arctic and boreal zones drive shifts in vegetation, such as increasing shrub cover from warming soil or loss of living mat species due to fire. Understanding current and future responses to these factors requires mapping vegetation at a fine taxonomic resolution and landscape scale. Plants vary in size and spectral signatures, which hampers mapping of meaningful functional groups at coarse spatial resolution. Fine spatial grain of remotely sensed data (<10 cm pixels) is often necessary to resolve patches of many Arctic and boreal plant groups, such as bryophytes and lichens, which are significant components of terrestrial vegetation cover. Separation of co-occurring small vegetation patches in images also requires high spectral resolution. Our goal here was to test the capabilities of UAS-based imaging spectroscopy for mapping plant functional types (PFT) using high spatial and spectral resolution data over Arctic and boreal vegetation at four sites in central Alaska. We then tested several Machine and Deep learning models of PFT cover using the reflectance spectra. The best models were very simple, balancing both bias (overfitting caused by imbalance sample sizes) and variance (fit to the independent validation data), explaining > 50 % of the independent ground cover estimation and > 84 % accuracy in estimating validation pixels. We explored the impact of spectral resolution on PFT mapping by including vegetation indices and a gradient of narrow (5 nm) to wide (50 nm) band features in our classification models across. Vegetation indices were the most important predictors for classifying PFTs, while including band features improved models, with narrow and wide bandwidths having similar importance but models with wide bandwidths performing slightly better. We conclude that Arctic and boreal PFT reflectance can be pooled across sites for mapping with relatively few labeled pixels. Underfit, simple algorithms outperformed deep learning, at least with these small sample sizes, in classifying PFTs by balancing bias and variance. Future work should aim to increase the number of labeled pixels and the detail of labels to further improve mapping taxonomic precision.

Thermal Emissions of Active Craters at Stromboli Volcano: Spatio‐Temporal Insights From 10 Years of Satellite Observations

AbstractOpen‐vent volcanoes continuously emit magmatic products and frequently feature multiple adjacent craters. Temporal shifts of thermal emissions between craters are especially detectable by InfraRed satellites. Here, SENTINEL‐2 and LANDSAT‐8/9 Short Wave InfraRed (SWIR) high‐spatial resolution satellite data, are combined to investigate 10 years (2013–2023) of thermal activity at Stromboli volcano (Italy). The correlation between Volcanic Radiative Power (VRP, in Watts) and Volcanic Radiative Energy (VRE, in Joules), retrieved by moderate MODIS and VIIRS Middle InfraRed (MIR) data, with the Thermal Index SWIR (TISWIR) data, allows us to quantify long‐term series of heat fluxes (VRPSWIR) and energy (VRESWIR). Combining moderate and higher spatial resolution data and fitting cumulative trends of TISWIR with VREMIR allows to measure thermal activity sourced by single craters during Strombolian activity. Long‐term results highlight that thermal emissions are clustered in the northern and southern parts of the crater terrace, with total energy emitted (∼12 × 1014 J) equally distributed. The thermal increase since April 2017 marked a reactivation of shallow magma transportation and an intensification of the activity after the 2014 eruption. Distinct thermal behaviors are shown by the NE, C, and SW craters, related to mechanisms of explosions. We found that short‐term thermal variations match well those resolved by ground‐based signals, and the NE crater as the most sensitive to the transition to higher‐intensity activity. Our multispatial/multisensory investigation allows, for the first time, the long‐term quantification of heat flux from Stromboli's craters, with an improved understanding of open‐vent dynamics and a new approach to monitor multiple active craters.

Graph Fourier transform for spatial omics representation and analyses of complex organs

Spatial omics technologies decipher functional components of complex organs at cellular and subcellular resolutions. We introduce Spatial Graph Fourier Transform (SpaGFT) and apply graph signal processing to a wide range of spatial omics profiling platforms to generate their interpretable representations. This representation supports spatially variable gene identification and improves gene expression imputation, outperforming existing tools in analyzing human and mouse spatial transcriptomics data. SpaGFT can identify immunological regions for B cell maturation in human lymph nodes Visium data and characterize variations in secondary follicles using in-house human tonsil CODEX data. Furthermore, it can be integrated seamlessly into other machine learning frameworks, enhancing accuracy in spatial domain identification, cell type annotation, and subcellular feature inference by up to 40%. Notably, SpaGFT detects rare subcellular organelles, such as Cajal bodies and Set1/COMPASS complexes, in high-resolution spatial proteomics data. This approach provides an explainable graph representation method for exploring tissue biology and function.

Big Data-driven MLOps workflow for annual high-resolution land cover classification models

Developing an annual and global high-resolution land cover map is one of the most ambitious tasks in remote sensing, with increasing importance due to the continual rise in validated data and satellite imagery. The success of land cover classification models largely hinges on the data quality, coupled with the application of Big Data techniques and distributed computing. This is essential for efficiently processing the extensive volume of available satellite data. However, maintaining the lifecycle of several annual Machine Learning models presents a complex challenge. The rise of Machine Learning Operations offers an opportunity to automate the maintenance of these models, a feature particularly beneficial in systems that require generating new models each year alongside the continuous integration of validated data. This article details the development of an end-to-end MLOps workflow, meticulously integrating land cover classification models that employ Big Data strategies for processing large-scale, high-resolution spatial data. The workflow is designed within a Kubernetes environment, achieving on-demand auto-scaling, distributed computing, and load balancing. This integration demonstrates the practicality and efficiency of managing and deploying models that treat satellite imagery in an automated, scalable framework, thus marking a significant advancement in remote sensing and MLOps.

An improved digital soil mapping approach to predict total N by combining machine learning algorithms and open environmental data

Digital Soil Mapping (DSM) is fundamental for soil monitoring, as it is limited and strategic for human activities. The availability of high temporal and spatial resolution data and robust algorithms is essential to map and predict soil properties and characteristics with adequate accuracy, especially at a time when the scientific community, legislators and land managers are increasingly interested in the protection and rational management of soil.Proximity and remote sensing, efficient data sampling and open public environmental data allow the use of innovative tools to create spatial databases and digital soil maps with high spatial and temporal accuracy. Applying machine learning (ML) to soil data prediction can improve the accuracy of maps, especially at scales where geostatistics may be inefficient. The aim of this research was to map the nitrogen (N) levels in the soils of the Nurra sub-region (north-western Sardinia, Italy), testing the performance of the Ranger, Random Forest Regression (RFR) and Support Vector Regression (SVR) models, using only open source and open access data. According to the literature, the models include soil chemical-physical characteristics, environmental and topographic parameters as independent variables. Our results showed that predictive models are reliable tools for mapping N in soils, with an accuracy in line with the literature. The average accuracy of the models is high (R2 = 0.76) and the highest accuracy in predicting N content in surface horizons was obtained with RFR (R2 = 0.79; RMSE = 0.32; MAE = 0.18). Among the predictors, SOM has the highest importance. Our results show that predictive models are reliable tools in mapping N in soils, with an accuracy in line with the literature. The results obtained could encourage the integration of this type of approach in the policy and decision-making process carried out at regional scale for land management.

‘Green or short: choose one’ - A comparison of walking accessibility and greenery in 43 European cities

Promoting environmentally and socially sustainable urban mobility is crucial for cities, with urban greening emerging as a key strategy. Contact with nature during travel not only enhances well-being but also promotes sustainable behaviour. However, the availability of travel greenery varies, and only recently have new datasets and computational approaches made it possible to compare the conditions in the distribution of travel greenery within and between cities quantitatively. In this study of 43 large European cities, we undertook a comparative analysis of travel greenery availability by using high-resolution spatial data and daily school trips as a marker of a daily travel need. By recognising walking accessibility as the most sustainable and equally available mode of transportation, we first estimated the proportion of the population residing within walking distance to upper secondary schools. Second, we associated the detailed school routes with monthly green cover data and compared the spatial variation in travel greenery availability between European cities, taking seasonal variation into account. Lastly, we analysed spatial inequalities of travel greenery availability within the study cities using the Gini index, the Kolm-Pollak equally-distributed equivalent (EDE) index and Moran's I. Our findings reveal a consistent negative association between accessibility and green cover implying a trade-off between access and greenery. We found large variations between European cities in the walking accessibility of schools, ranging from 44% to 98% of the population being within 1600 m of their school. Moreover, our results show substantial within-city disparities in travel greenery availability in large European cities. We demonstrated methodologically the importance of considering seasonal variations when measuring greenery availability. Our study offers empirical evidence of urban greenery availability from a mobility-focused perspective. It provides a novel understanding with which to support researchers and planners in affording the benefits of nature to more people as they travel.

Revisiting Duvensee 13: Additional Analyses of Lithic Artefacts and Site Contexts of a Small Dwelling at the Ancient Lake Duvensee, Germany

ABSTRACT The paper re-examines the Duvensee 13 site at Lake Duvensee, Germany, dating from 9900 to 8600 calBP, the latest in a series of well-known hazelnut roasting sites of a larger Mesolithic site complex. While the site has previously been studied, its lithic assemblage has not been fully analysed and published. This study presents this previously unstudied material, offering a comprehensive overview of its composition, metric information, and its spatial distribution. Lithic analysis revealed specialised production of pointed and triangular microliths. Additional elements of the assemblage (narrow blades, small cores) suggest microlith production as the primary goal. High-resolution spatial data revealed concentrations of microliths and microburins, pointing towards focussed areas of production. However, the overall assemblage is affected by a redistribution of artefacts through the reworking of the layers surrounding the hearth and repeated overlapping site occupations. Additional archaeological features suggest that in addition to hazelnut roasting, the site likely also accommodated dwelling, tool crafting, and game surveillance during off-harvest times.

On urban microclimate spatial-temporal dynamics: Evidence from the integration of fixed and wearable sensing and mapping techniques

Urban Heat Island (UHI) is acknowledged to generate harmful consequences on human health, and it is one of the main anthropogenic challenges to face in modern cities. Due to the urban dynamic complexity, a full microclimate decoding is required to design tailored mitigation strategies for reducing heat-related vulnerability. This study proposes a new method to assess intra-urban microclimate variability by combining for the first time two dedicated monitoring systems consisting of fixed and mobile techniques. Data from three fixed weather stations were used to analyze long-term trends, while mobile devices (a vehicle and a wearable) were used in short-term monitoring campaigns conducted in summer and winter to assess and geo-locate microclimate spatial variations. Additionally, data from mobile devices were used as input for Kriging interpolation in the urban area of Florence (Italy) as case study. Mobile monitoring sessions provided high-resolution spatial data, enabling the detection of hyperlocal variations in air temperature. The maximum air temperature amplitudes were verified with the wearable system: 3.3 °C in summer midday and 4.3 °C in winter morning. Physiological Equivalent Temperature (PET) demonstrated to be similar when comparing green areas and their adjacent built-up zone, showing up the microclimate mitigation contribution of greenery in its surrounding. Results also showed that mixing the two data acquisition and varied analysis techniques succeeded in investigating the UHI and the site-specific role of potential mitigation actions. Moreover, mobile dataset was reliable for elaborating maps by interpolating the monitored parameters. Interpolation results demonstrated the possibility of optimizing mobile monitoring campaigns by focusing on targeted streets and times of day since interpolation errors increased by 10% only with properly reduced and simplified input samples. This allowed an enhanced detection of the site-specific granularity, which is important for urban planning and policymaking, adaptation, and risk mitigation actions to overcome the UHI and anthropogenic climate change effects.

Assessing allergy risk from ornamental trees in a city: Integrating open access remote sensing data with pollen measurements

Platanus sp. pl. (plane trees) are common ornamental tree in Poland that produces a large amount of wind-transported pollen, which contains proteins that induce allergy symptoms. Allergy sufferers can limit their contact with pollen by avoiding places with high pollen concentrations, which are restricted mainly to areas close to plane trees. Their location is thus important, but creating a detailed street tree inventory is expensive and time-consuming. However, high-resolution remote sensing data provide an opportunity to detect the location of specific plants. But acquiring high-resolution spatial data of good quality also incurs costs and requires regular updates. Therefore, this study explored the potential of using open access remote sensing data to detect plane trees in the highly urbanized environment of Poznań (western Poland). Airborne light detection and ranging (LiDAR) was used to detect training treetops, which were subsequently marked as young plane trees, mature plane trees, other trees or artefacts. Spectral and spatial variables were extracted from circular buffers (r = 1 m) around the treetops to minimize the influence of shadows and crown overlap. A random forest machine learning algorithm was applied to assess the importance of variables and classify the treetops within a radius of 6.2 km around the functioning pollen monitoring station. The model performed well during 10-fold cross-validation (overall accuracy ≈ 92%). The predicted Platanus sp. pl. locations, aggregated according to 16 wind directions, were significantly correlated with the hourly pollen concentrations. Based on the correlation values, we established a threshold of prediction confidence, which allowed us to reduce the fraction of false-positive predictions. We proposed the spatially continuous index of airborne pollen exposure probability, which can be useful for allergy sufferers. The results showed that open-access geodata in Poland can be applied to recognize major local sources of plane pollen.

Unoccupied aerial system (UAS) Structure-from-Motion canopy fuel parameters: Multisite area-based modelling across forests in California, USA

There is a pressing need for well-informed management to reduce wildfire hazard and restore fire's beneficial ecological role in the Mediterranean- and temperate-climate forests of California, USA. These efforts rely upon the accessibility of high spatial and temporal resolution data on biomass and canopy fuel parameters such as canopy base height (CBH), mean canopy height, canopy bulk density (CBD), canopy cover, and leaf area index (LAI). Remote sensing using unoccupied aerial system Structure-from-Motion (UAS-SfM) presents a promising technology for this application due to its accessibility, relatively low cost, and possibility for high temporal cadence. However, to date, this method has not been studied in the complex mosaic of forest types found across California. In this study we examined the capacity of structural and multispectral information obtained from UAS-SfM, in conjunction with machine learning methods, to model aboveground biomass and forest canopy fuel structural parameters using an area-based approach across multiple sites representing a diversity of forest types in California.Based on correlations with field measurements, fuel parameters separated into vertical (biomass, CBH, and mean height) and horizontal (LAI, CBD, canopy cover) groups. UAS-SfM random forest models performed well for modelling the vertical structure canopy fuels parameters (R2 0.69–0.75). These models exhibited strong performance in comparison to ALS, as well as when transferred to a novel site. Vertical structure predictors were prominent in these models, and did not improve with the addition of spectral predictors. UAS-SfM random forest models of horizontal structure parameters mainly used raster-based spectral indices (primarily NDVI) and had relatively low performance (R2 0.49–0.59). In addition, these models underperformed ALS and had poor performance when applied to a novel site. When applied to a region with widespread UAS-SfM coverage, models from both groups successfully produced contiguous maps that could be used for modelling fire behavior or in management decision making and monitoring.These findings indicate that UAS-SfM, without the need for multispectral sensors, is well suited for mapping area-based vertical-structure canopy parameters across diverse landscapes supporting a wide range of forest types. In contrast, the identification of spectral mean variables for modelling horizontal structure canopy fuels suggests the potential of multi- or hyperspectral sensors or high-resolution satellite imagery for meeting management information needs.

Detection of Cliff Top Erosion Drivers through Machine Learning Algorithms between Portonovo and Trave Cliffs (Ancona, Italy)

Rocky coastlines are characterised by steep cliffs, which frequently experience a variety of natural processes that often exhibit intricate interdependencies, such as rainfall, ice and water run-off, and marine actions. The advent of high temporal and spatial resolution data, that can be acquired through remote sensing and geomatics techniques, has facilitated the safe exploration of otherwise inaccessible areas. The datasets that can be gathered from these techniques, typically combined with data from fieldwork, can subsequently undergo analyses employing/applying machine learning algorithms and/or numerical modeling, in order to identify/discern the predominant influencing factors affecting cliff top erosion. This study focuses on a specific case situated at the Conero promontory of the Adriatic Sea in the Marche region. The research methodology entails several steps. Initially, the morphological, geological and geomechanical characteristics of the areas were determined through unmanned aerial vehicle (UAV) and conventional geological/geomechanical surveys. Subsequently, cliff top retreat was determined within a GIS environment by comparing orthophotos taken in 1978 and 2022 using the DSAS tool (Digital Shoreline Analysis System), highlighting cliff top retreat up to 50 m in some sectors. Further analysis was conducted via the use of two Machine Learning (ML) algorithms, namely Random Forest (RF) and eXtreme Gradient Boosting (XGB). The Mean Decrease in Impurity (MDI) methodology was employed to assess the significance of each factor. Both algorithms yielded congruent results, emphasising that cliff top erosion rates are primarily influenced by slope height. Finally, a validation of the ML algorithm results was conducted using 2D Limit Equilibrium Method (LEM) codes. Ten sections extracted from the sector experiencing the most substantial cliff top retreat, as identified by DSAS, were utilised for 2D LEM analysis. Factor of Safety (FS) values were identified and compared with the cliff height of each section. The results from the 2D LEM analyses corroborated the outputs of the ML algorithms, showing a strong correlation between the slope instability and slope height (R2 of 0.84), with FS decreasing with slope height.