Search Results (119)

The geosciences have witnessed a rapid expansion of analytical methods, from classical linear models to geostatistics and modern machine learning. However, no single resource compares a curated selection of these methods systematically while also providing reproducible code. This reproducibility-driven review evaluates seven analytical techniques applied to three simulated geoscience datasets: spatial points, time series, and a spatio-temporal grid. Methods were selected based on their availability in R to ensure transparency and accessibility. This paper serves as a historical review, a comparative benchmarking study, and a practical teaching resource with fully reproducible R code. The methods include linear regression, ARIMAX, ordinary kriging, regression-kriging, random forest, feed-forward neural networks, and BART. For spatial prediction, when evaluated against the true field, linear regression achieved the lowest mean RMSE (1.94 ± 0.23), followed by random forest (2.13 ± 0.23) and ordinary kriging (2.20 ± 0.26)—highlighting the importance of consistent out-of-sample validation. Regression-kriging performed similarly to ordinary kriging (2.22 ± 0.26). For time series, a feed-forward neural network (0.37 ± 0.09) substantially outperformed seasonal ARIMAX (1.90 ± 1.30). For spatio-temporal prediction, random forest and BART performed indistinguishably (0.534 ± 0.004 vs. 0.543 ± 0.004). A practical decision guide, grounded in these empirical results, summarises method selection based on sample size, data type, and research goal—whether inference, prediction, or uncertainty quantification. All code is open and reproducible, providing a template for future method comparisons. Full article

Temperature plays a key role in climate systems, with significant implications for environmental sustainability, agricultural productivity, and water resource management. Accurate spatiotemporal forecasting of temperature is, therefore, essential for supporting sustainable development and informing climate adaptation strategies. However, traditional modeling approaches often treat spatial and temporal dimensions separately, thereby limiting their ability to capture the full spectrum of spatiotemporal dependencies. This paper proposes a hybrid approach that integrates a machine learning model with a geostatistical prediction technique to forecast daily mean air temperature over the study area. The best-performing spatiotemporal correlation model is selected among various time series and machine learning models including Holt–Winters, Seasonal Autoregressive Integrated Moving Average (SARIMA), Neural Network Autoregression (NNAR), and Artificial Neural Networks (ANNs). The findings demonstrate that the proposed hybrid approach consistently outperforms traditional, non-integrated methods. Importantly, this study contributes to sustainability by enabling high-resolution temperature forecasting that supports climate-resilient agriculture, efficient water resource allocation, and evidence-based environmental management. The generated predictive maps provide actionable insights for policymakers and stakeholders, enhancing adaptive capacity and promoting sustainable resource management under changing climate conditions. Full article

The brown marmorated stink bug (Halyomorpha halys) is a major invasive pest threatening fruit production across Europe. This study integrates spatiotemporal geostatistical modelling with degree-day and photoperiod analyses to characterise its seasonal dynamics in Emilia-Romagna (Italy) from 2020 to 2022. Weekly pheromone trap data were used to quantify developmental succession among Small nymphs (early instars, N1–N3), Large nymphs (late instars, N4–N5), and Adults. Time-series and cross-correlation analyses confirmed consistent developmental delays across years, with Small preceding Large by approximately two weeks and Adults emerging after an additional two to three weeks. However, global inter-stage correlations were moderate (r ≈ 0.4–0.5), indicating substantial spatial heterogeneity among monitoring sites and suggesting that regional averages do not fully capture local population dynamics. To address this variability, a three-dimensional spatiotemporal geostatistical model (space × time) was implemented using Direct Sequential Simulation. The model successfully reproduced seasonal population waves and interannual differences in onset and persistence. The identification of persistent hotspots and stage-specific temporal windows is biologically relevant because it highlights where and when H. halys populations are most likely to increase. As such, from an IPM perspective, these outputs can support earlier monitoring, more precise timing of management interventions, and spatial prioritization of control efforts. These findings demonstrate that combining stage-specific temporal analysis with spatially explicit modelling improves forecasting accuracy and supports more precise timing of biological and chemical interventions. The proposed framework provides a scalable tool for climate-responsive integrated pest management in fruit-growing systems. Full article

In the geographic environment, mesoscale ocean eddies and similar phenomena exhibit continuous and gradual changes. However, due to limitations in remote sensing observation technology, the obtained observational data are discrete, which contradicts the continuously evolving characteristics of these phenomena. Although spatiotemporal interpolation is a key tool for bridging this gap, existing single-model methods fail to fully consider continuous process features, making it difficult to obtain consistent high-quality datasets. To solve this problem, this paper combines deep learning and geostatistics to propose an Evolutionary Process-embedded Marine Spatiotemporal Interpolation Model (EPMSIM). EPMSIM first applies Seasonal and Trend decomposition using Loess (STL) to decompose marine time-series fields into trend, seasonal, and evolutionary components. Then, a Convolutional Bidirectional Long Short-Term Memory (ConvBiLSTM) model is adopted to interpolate the trend and seasonal components. Meanwhile, a Process-based Spatiotemporal Dynamic Tracking Interpolation Method (PSDTIM) is designed to interpolate the evolutionary component. Finally, these components are combined through additive coupling to produce the final interpolation result. In case studies of mesoscale eddy interpolation using SST and SLA data, EPMSIM outperforms traditional geostatistical and deep learning baselines in RMSE, MAE, and SSIM. Experimental results confirm that the model achieves significant interpolation effects in marine environmental element fields with evolutionary characteristics, validating its effectiveness in capturing continuous evolution features of marine phenomena and its feasibility for generating high-temporal-resolution spatiotemporal datasets. This study provides a methodological reference for data interpolation of evolutionary process phenomena in marine information science, and this method can be extended to other similar marine environmental variables, serving research on marine ecological environments and dynamic processes. Full article

The spatial heterogeneity and dynamic changes in soil organic matter (SOM) are key indicators for assessing cultivated land quality and the carbon cycle. Currently, large-scale SOM monitoring relies primarily on limited ground sampling, making it difficult to capture continuous spatiotemporal variation patterns. Taking Anhui Province, China as the study area, this research integrates multi-source remote sensing and geostatistical methods to construct a multi-source collaborative SOM inversion model and analyze its spatiotemporal evolution patterns, thereby achieving high-precision, continuous spatiotemporal monitoring of SOM. A total of 3026 sampling points in Huangshan, Chuzhou and Fuyang cities in Anhui Province were selected as model training samples. The study divided the terrain into three elevation zones (<20 m, 20–40 m, >40 m) and employed the Synthetic Minority Oversampling Technique (SMOTE) method to optimize sample distribution. Based on MODIS data, this study screened spectral bands and key phenological periods significantly correlated with SOM. By integrating spectral information from Landsat 8/9 OLI imagery, meteorological data and topographic factors, a random forest (RF) inversion model incorporating multi-source environmental variables was constructed. The results indicate that (1) the RF-based SOM inversion model exhibits moderate predictive accuracy acceptable for regional-scale SOM mapping, with a coefficient of determination (R²) of 0.55 and a root-mean-square error (RMSE) of 3.3 g/kg, effectively enabling the quantitative estimation of SOM at a regional scale. (2) The model’s inversion results reflect the spatial distribution of SOM in cultivated land in Anhui Province for the years 2019, 2022 and 2024. The provincial average SOM value shows an upward trend, with SOM content exhibiting a pattern of higher levels in the south and lower levels in the north, higher levels in the west and lower levels in the east, as well as a tendency to cluster. (3) Analysis using GeoDetector indicates that topography and precipitation are the primary drivers influencing SOM distribution, and the interaction between these two factors provides significantly greater explanatory power for SOM distribution than either factor alone. Through the integration of multi-source remote sensing data and model optimization, this study has validated the feasibility of multi-scale remote sensing-based SOM inversion, revealed the spatial differentiation characteristics and driving mechanisms of SOM in Anhui Province’s cultivated land, and provided a scientific basis for improving cultivated land quality and soil carbon sink management. Full article

This study examines the social burden and systemic infrastructure vulnerabilities associated with fatal road traffic incidents in Medellín, Colombia, over the period 2008–2025. Using official records from the Secretaría de Movilidad de Medellín, the analysis quantifies impact through Years of Potential Life Lost (YPLL) and high-resolution spatiotemporal clustering, moving beyond simple fatality counts or economic valuation alone. Phase I applies an age-group proportional allocation method to estimate YPLL for 2762 fatal road traffic incidents, while Phase II employs a spatiotemporal geostatistical framework (ICCE-T) to detect statistically significant concentration clusters. Results indicate that these incidents generated 100,851 years of potential life lost, with individuals aged 15–35 accounting for 64.7% of total YPLL, and the 20–25 age group alone contributing 21.5% of the overall burden. Spatial analysis reveals persistent clustering along key urban corridors, particularly in Comuna 10 (La Candelaria), identifying recurrent nodes of elevated systemic vulnerability. By integrating epidemiological measurement with spatiotemporal analysis, the study provides a decision-oriented analytical framework to support resilient, evidence-based urban mobility interventions and guide strategic public investment under the Safe System approach. Full article

Advancements in earth observation technologies are ushering in the big data era, yet this potential is compromised by intrinsic challenges: inherent uncertainty, spatiotemporal heterogeneity, multi-scale character, and pervasive data gaps. Traditional methods often fail to address these issues within a single, coherent system. The main contributions of this review are to systematically establish the Remote Sensing Geostatistical Paradigm (RSGP) as a comprehensive, unified framework. Powered by its core theory, Bayesian Maximum Entropy (BME), RSGP is a broadly designed epistemic framework that transcends a mere conceptual reorganization of established methods. It addresses the above challenges by highlighting two pivotal concepts within a spatiotemporal random field: (1) uncertainty quantification via probabilistic soft data, which redefines observations as probability density functions, representing a fundamental epistemological shift from deterministic scalars to probabilistic entities, and provides a universal interface for rigorous assimilation of heterogeneous remote sensing or in situ observations and synergy with other computational models, such as machine learning; and (2) spatiotemporal structure exploitation, which integrates the underlying structure embedded in remote sensing data of natural attributes, moving beyond mere optical properties to incorporate a broader range of available spatiotemporal information, for robust estimation and mapping purposes. Furthermore, the evolution of key technologies is illustrated by using real-world application cases, guiding how to implement RSGP in terms of different scenarios. Finally, the paradigm’s features and limitations are discussed. This synthesis provides the remote sensing community with a robust foundation for uncertainty-aware analysis and multi-source integration, bridging geostatistical logic with next-generation AI-driven Earth observation. Full article

Affordable optical data from Unmanned Aerial Vehicles (UAVs) coupled with process-based models could constitute an integrative platform to map complex spatio-temporal patterns of nitrate leaching and reduce uncertainties in tightening the nitrogen (N) cycle of silvopastoral systems. This study uses field data from a commercial farm in Denmark with lactating sows housed in paddocks with pastures flanking a central zone of poplars, either pruned (P) or unpruned (tall, T), each with resources (feed and hut) on the same (S) or opposite side (O) of the tree zone. The poplar leaf area index derived from canopy cover using a computer vision approach on true-colour UAV imagery was fed to a process-based model alongside soil data and geostatistical analyses to derive the soil water balance across the paddocks and explicitly map the variation in soil nitrate leaching. The results showed clear patterns not seen before of nitrate leaching hotspots shifting from high values in the pre-study year without animals to diluted lower values in the main study year involving the pigs. The results also showed a seasonal and spatial variation of 7 to 860 kg N ha⁻¹ year⁻¹, a wide leaching range otherwise difficult to capture, by employing only a process-based model using mean effective parameters. Nitrate leaching was in the order PO > PS > TO > TS. The N cycle was tightened with T regardless of S/O. The approach could be improved with more machine learning-aided process-based modelling to operationally monitor complex silvopastoral systems to alleviate nitrate leaching in outdoor pig systems. Full article

Soil organic carbon (SOC) is a key indicator for assessing pasture degradation. This study presents an integrated, field-based approach to analyzing SOC dynamics in pastures of Rio de Janeiro state (Brazil). Unlike methods based exclusively on remote sensing or modeling, our analysis is based on 350 georeferenced soil samples collected by Embrapa Solos and complemented by historical land use data, providing robust and reliable empirical evidence. Statistical methods (ANOVA, Tukey test), geostatistical interpolation (kriging), and unsupervised clustering (k-means) were used to characterize the spatiotemporal distribution of SOC. The results revealed patterns linked to both topographic and anthropogenic drivers, enabling the objective delineation of degraded versus non-degraded pastures. SOC levels below 40 g/kg in areas under 300 m elevation were strongly associated with degradation due to intensive use. In contrast, degradation at higher altitudes was primarily linked to sloping terrain more prone to water erosion. This methodological approach demonstrates the potential of combining field data with data mining tools to detect degradation patterns and inform targeted land management. The findings reaffirm SOC as a vital indicator of soil quality and highlight the importance of sustainable pasture practices in conserving carbon stocks and mitigating climate change. The proposed threshold-based method offers a practical foundation for diagnosing degraded pastures and identifying priority areas for restoration. Full article

Understanding how different population groups interact with urban environments is essential for analyzing spatial dynamics and informing urban planning, especially in cities experiencing high visitor pressure. This study presents a methodological framework for the spatial and temporal delineation of urban areas based on user-generated location-based data. By collecting nearly 1 million Google Maps reviews in the municipality of Donostia-San Sebastián, we identify and classify user profiles based on their spatiotemporal behavior. First, we collect points of interest (POIs) and associated reviews, including profile identifiers and timestamps. Then, we perform user-level webscraping to reconstruct review histories, enabling us to infer the predominant geographical origin of each user. Users are classified as residents or tourists using both spatial prevalence and temporal activity patterns. The resulting data is aggregated onto a hexagonal grid for geostatistical analysis. Using the Getis-Ord Gi* statistic and Mann-Kendall trend tests, we identify hotspots and long-term trends of activity for different population segments. Additionally, we propose novel indicators such as predominant periods of activity and diversity of geographical origin per cell to characterize heterogeneous patterns of urban use. Our results reveal distinct behavioral patterns, highlighting a more evenly distributed use of urban space by residents, with spatially overlapping yet temporally offset activities across central areas where tourists tend to concentrate their interactions. This spatiotemporal concentration is intensified as the tourists’ origin becomes more distant, suggesting that proximity shapes urban engagement. The proposed methodology offers a replicable strategy for urban analysis using publicly accessible user-generated data and contributes to the understanding of sociospatial dynamics in tourism-intensive cities. Full article

African swine fever (ASF) is a highly contagious viral disease with significant impacts on domestic pigs and wild boar populations. This study applies GIS-based spatial analysis to monitor ASF outbreaks in northwestern Italy (Piedmont and Liguria) and identify areas at increased risk. Key factors considered include pig density, wildlife proximity, and environmental conditions. The spatial analysis revealed that central–western municipalities exhibited higher risk due to favorable environmental conditions and dense wild boar populations, while peripheral areas showed a temporal delay in outbreak emergence. Mapping the spreading rate and habitat interfaces allowed the development of a spatial risk model, which was further analyzed using geostatistical techniques to understand disease dynamics. The results demonstrate the effectiveness of geospatial modeling in identifying high-risk zones, characterizing spatio-temporal patterns, and supporting targeted prevention and surveillance strategies. These findings provide actionable insights for ASF management and resource allocation. Future studies may refine these models by integrating additional datasets and environmental variables, enhancing predictive capacity and applicability across different regions. Full article

This study examines the impact of physicochemical and geological factors on radon concentrations in groundwater throughout the Mexican Altiplano. Geological diversity, uranium deposits, seismic zones, and geothermal areas with high heat flow are all potential factors contributing to the presence of radon in groundwater. To move beyond local-scale assessments, this research employs spatial prediction methodologies that incorporate geological and geochemical variables recognized for their role in radon transport and geogenic potential. Certain properties of radon enable it to serve as an ideal tracer, viz., short half-life, inertness, and higher incidence in groundwater than surface water. Twenty-five variables were analyzed in samples from 135 water wells. Geostatistical techniques, including inverse distance weighted interpolation and kriging, were used in conjunction with multivariate statistical analyses. Salinity and geothermal heat flow are key indicators for determining groundwater origin, revealing a dynamic interplay between geothermal activity and hydrogeochemical evolution, where high temperatures do not necessarily correlate with increased solute concentrations. The occurrence of toxic trace elements such as Cd, Cr, and Pb is primarily governed by lithogenic sources and proximity to mineralized zones. Radon levels in groundwater are mainly influenced by geological and structural features, notably rhyolitic formations and deep hydrothermal systems. These findings underscore the importance of site-specific groundwater examination, combined with spatiotemporal models, to account for uranium–radium dynamics and flow paths, thereby enhancing radiological risk assessment. Full article

Background: The Amazon biome exhibits complex arboviral transmission dynamics influenced by accelerating deforestation, climate change, and socioeconomic inequities. Objectives/Methods: This study integrates official epidemiological records with socioeconomic, environmental, and climate variables by applying advanced geostatistical methods (Moran’s I, SaTScan, kernel density estimation) combined with principal component analysis and negative binomial regression to assess the spatiotemporal dynamics of dengue incidence and its association with socio-environmental determinants across municipalities in Pará state (eastern Brazilian Amazon) from 2010 to 2024. Results: Dengue incidence showed an overall decline but with marked epidemic peaks in 2010–2012, 2016, and 2024. The spatial analysis revealed significant clustering (Moran’s I = 0.221, p < 0.01), with persistent high-risk hotspots across most of Pará. Of 144 municipalities, 104 exhibited significant dengue risk, while 58 maintained sustained transmission. Negative binomial regression model identified key determinants: illiteracy, low urbanization, reduced GDP, and climate variables. Conclusions: Dengue transmission in the Amazon is driven by synergistic socio-environmental disruptions, necessitating intersectoral policies that bridge public health surveillance, sustainable land-use governance, and poverty alleviation. Priority actions include targeted vector control in high-risk clusters, coupled with integrated deforestation and climate monitoring to predict outbreak risks. The findings emphasize the urgency of implementing multisectoral interventions tailored to the territorial and socio-environmental complexities of vulnerable Amazonian regions for effective dengue control. Full article

Multivariate space–time datasets are often collected at discrete, regularly monitored time intervals and are typically treated as components of time series in environmental science and other applied fields. To effectively characterize such data in geostatistical frameworks, valid and practical covariance models are essential. In this work, we propose several classes of multivariate spatio-temporal covariance matrix functions to model underlying stochastic processes whose discrete temporal margins correspond to well-known autoregressive and moving average (ARMA) models. We derive sufficient and/or necessary conditions under which these functions yield valid covariance matrices. By leveraging established methodologies from time series analysis and spatial statistics, the proposed models are straightforward to identify and fit in practice. Finally, we demonstrate the utility of these multivariate covariance functions through an application to Kansas weather data, using co-kriging for prediction and comparing the results to those obtained from traditional spatio-temporal models. Full article

Geological storage is an integral element of the green energy transition. Geological formations, such as aquifers, depleted reservoirs, and hard rock caverns, are used mainly for the storage of hydrocarbons, carbon dioxide and increasingly hydrogen. However, potential adverse effects such as ground movements, leakage, seismic activity, and environmental pollution are observed. Existing research focuses on monitoring subsurface elements of the storage, while on the surface it is limited to ground movement observations. The review was carried out based on 191 research contributions related to geological storage. It emphasizes the importance of monitoring underground gas storage (UGS) sites and their surroundings to ensure sustainable and safe operation. It details surface monitoring methods, distinguishing geodetic surveys and remote sensing techniques. Remote sensing, including active methods such as InSAR and LiDAR, and passive methods of multispectral and hyperspectral imaging, provide valuable spatiotemporal information on UGS sites on a large scale. The review covers modelling and prediction methods used to analyze the environmental impacts of UGS, with data-driven models employing geostatistical tools and machine learning algorithms. The limited number of contributions treating geological storage sites holistically opens perspectives for the development of complex approaches capable of monitoring and modelling its environmental impacts. Full article