2025-12-29
Sander Kovaci, Alfred Lako
The aim of this study was to examine the methods, tools, and platforms used for the analysis of spatial data, as well as to assess their potential for solving environmental challenges. The study considers geostatistical methods, including kriging, variogram analysis, semivariance, the Thiessen polygon method, inverse distance weighting (IDW) interpolation, and regression models such as linear regression, multiple regression, and geographically weighted regression (GWR). A literature search turned up 52 peer-reviewed and indexed articles on methods including regression models, variogram analysis, and kriging. The selection criteria included: (1) relevance to geostatistical analysis of environmental data, (2) methodological rigor, (3) publication in high-impact peerreviewed journals, and (4) citation frequency indicating scientific significance. These studies highlight the effectiveness of geostatistical methods, geospatial platforms, and Python in environmental monitoring and predictive modeling. For classification tasks, logistic regression and decision trees were examined. The study results demonstrate that the application of modern geostatistical methods allows for the identification of spatial distribution patterns of environmental data and improves prediction accuracy. In particular, it was found that the spatial autocorrelation index effectively determines areas with high levels of similarity in environmental parameters, while local indicators of spatial association (LISA) help identify regional clusters with high pollution intensity or other anomalous characteristics. It was demonstrated that the use of spatial modelling platforms, such as Geographic Information System (GIS) software like ArcGIS and Quantum GIS (QGIS), along with the Python programming language and spatial data analysis libraries such as GeoPandas and the Python Spatial Analysis Library (PySAL), significantly enhances the effectiveness of environmental phenomenon analysis. The integration of satellite image data with geostatistical methods was found to contribute to the creation of more accurate maps for forecasting environmental risks. The proposed approaches demonstrate significant potential for environmental monitoring and natural resource management, enhancing the understanding of spatial patterns and serving as a basis for further research in this field.
2025-12-29
Paul P. A. Mazza
Present-day landscapes and biomes result from interactions among climate, landform dynamics, and atmospheric processes, driving environmental risks such as soil erosion, hydrological changes, and land degradation. Geological records show transitions between cool-cold and temperatewarm climate cycles, shaping both landforms and ecosystems. The geopaleontological record, from deep geological time to present, shows climate as the cumulative result of tens of thousands of years of sub-climate phenomena, which stem from weather events unfolding over decades to centuries. These long-term records provide vital context for assessing geological hazards and guiding sustainable land and water management. Geological evidence shows that climatic fluctuations occur over millennial time scales, far beyond the lifespan of any organism and human influence. This reveals the inadequacy of current meteorological and climatic definitions, which overlook geological complexities. A precise redefinition is needed, distinguishing decadal, centennial, and millennial phenomena to prevent flawed definitions that misguide climate mitigation efforts. Revising meteorological terminology would refocus efforts on adapting to climate realities and implementing effective land and water management policies. This study emphasizes adaptive management integrating geological and climatic data. Clear definitions of climate, sub-climate, and meteorological events at global, regional, and local levels are vital for forecasting risks and promoting sustainable solutions.
2025-12-29
Qin Guan, Bin Wang, Fengzuo Guo, Zhenlong Xue, Yuqi Wang
As disasters are occurring more frequently and weather extremes get harsher, communities and governments around the world are facing more and more difficulties. In order to address these problems, disaster preparedness must be done precisely. This research examines in detail the transformative impact that machine learning algorithms have on bolstering disaster preparedness and response systems. Beyond a simple synopsis, our study’s Enhanced Pelican Optimization based on Disaster Prediction long short-term Memory (EPO-DPLSTM) is remarkable and shows off the advanced capabilities of Machine Learning (ML) in predicting a wide range of patterns of the weather and natural disasters, such as waves in heat, hurricanes, floods, droughts, and more. In order to assist the improved efficacy of prediction models in disaster preparedness, we made useful observations into the intricacies of application using ML. In addition to outlining the theoretical underpinnings, the study offers empirical evidence of the substantial advantages that machine learning algorithms offer. By using these precise forecasts of past geological disasters and new weather trends, preventative measures might be put in place, ultimately saving lives and lessening the extent of the damage. Regional landslide catastrophe early-warning is a crucial tool for disaster prevention and mitigation in China, where disasters are severe. A proposed approach to regional disaster warning was presented in this research. The model creation process includes warning output, model parameter optimization, sample learning and training, sample-set construction, and so forth. Eighty percent of the training sample set was used as the trained set, and twenty percent was utilized as the testing set for cross-validation in the sample learning and training process. The model parameters were optimized using the Enhanced Pelican Optimization based on the Disaster Prediction Long Short-Term Memory (LSTM) algorithm, and the accuracy, Receiver Operating Characteristic (ROC curve), and Area Under the Curve (AUC) value were utilized to confirm the model’s generalization capacity and accuracy. To improve model training, five machine learning methods were used; the results indicated that the suggested algorithm was the model with the best generalization capacity (AUC was 0.989) and performed the best, with an accuracy of 99.5%. The findings of this study provide critical scientific support for policymakers, emergency planners, and local stakeholders, enabling the development of more targeted, data-driven disaster mitigation strategies and strengthening regional resilience against future geological hazards.
2025-12-29
Giovanni Maria Di Buduo
The paper illustrates the 2024-geomorphological setting of the Civita di Bagnoregio area (Central Italy, Lazio region), defined on geomorphological survey, drone footage examination and bibliographic data analysis. It also emphasizes how the peculiar and enchanting geomorphological features of this area (the ‘geomorphological heritage’) has deeply conditioned the lives of the inhabitants from Protohistory to the 20th century, therefore appearing to constitute the primary shaping factor of the identity, memory, and history (the ‘cultural heritage’) of the communities settled on the cliff through time.