Search Results (5)

Forest fires pose significant threats to ecosystems, economies, and human lives. However, existing forest fire risk assessments are over-reliant on field data and expert-derived indices. Here, we assessed the nationwide forest fire risk in South Korea using a dataset of 2289 and 4578 fire and non-fire events between 2020 and 2023. Twelve remote sensing-based environmental variables were exclusively derived from Google Earth Engine, including climate, vegetation, topographic, and socio-environmental factors. After removing the snow equivalent variable owing to high collinearity, we trained three machine learning models: random forest, XGBoost, and artificial neural network, and evaluated their ability to predict forest fire risks. XGBoost showed the best performance (F1 = 0.511; AUC = 0.76), followed by random forest (F1 = 0.496) and artificial neural network (F1 = 0.468). DEM, NDVI, and population density consistently ranked as the most influential predictors. Spatial prediction maps from each model revealed consistent high-risk areas with some local prediction differences. These findings demonstrate the potential of integrating cloud-based remote sensing with machine learning for large-scale, high-resolution forest fire risk modeling and have implications for early warning systems and effective fire management in vulnerable regions. Future predictions can be improved by incorporating seasonal, real-time meteorological, and human activity data. Full article

The Czech Republic is one of the countries along the Belt and Road Initiative, and classifying land cover in the Czech Republic helps to understand the distribution of its forest resources, laying the foundation for forestry cooperation between China and the Czech Republic. This study aims to develop a practical approach for land cover classification in the Czech Republic, with the goal of efficiently acquiring spatial distribution information regarding its forest resources. This approach is based on multi-level feature extraction and selection, integrated with advanced machine learning or deep learning models. To accomplish this goal, the study concentrated on two typical experimental regions in the Czech Republic and conducted a series of classification experiments, using Sentinel-2 and DEM data in 2018 as the main data sources. Initially, this study extracted various features, including spectral, vegetation, and terrain features, from the study area, then assessed and selected key features based on their importance. Additionally, this study also explored multi-level spatial contextual features to improve classification performance. The extracted features include texture and morphological features, as well as deep semantic information learned by utilizing a deep learning model, 3D CNN. Finally, an AdaBoost ensemble learning model with the random forest as the base classifier is designed to produce land cover classification maps, thus obtaining the spatial distribution of forest resources. The experimental results demonstrate that feature optimization significantly enhances the extraction of high-quality features of surface objects, thereby improving classification performance. Specifically, morphological and texture features can effectively enhance the discriminability between different features of surface objects, thereby improving classification accuracy. Utilizing deep learning networks enables more efficient extraction of deep feature information, further enhancing classification accuracy. Moreover, employing an ensemble learning model effectively boosts the accuracy of the original classification results from different individual classifiers. Ultimately, the classification accuracy of the two experimental areas reaches 92.84% and 93.83%, respectively. The user accuracies for forests are 92.24% and 93.14%, while the producer accuracies are 97.71% and 97.02%. This study applies the proposed approach for nationwide classification in the Czech Republic, resulting in an overall classification accuracy of 90.98%, with forest user accuracy at 91.97% and producer accuracy at 96.2%. The results in this study demonstrate the feasibility of combining feature optimization with the 3D Convolutional Neural Network (3DCNN) model for land cover classification. This study can serve as a reference for research methods in deep learning for land cover classification, utilizing optimized features. Full article

Different methods have been proposed to create seismic site condition maps. Ground-based methods are time-consuming in many places and require a lot of manual work. One method suggests topographic data as a proxy for seismic site condition of large areas. In this study, we mainly focused on the use of an ASTER 1c digital elevation model (DEM) to produce Vs30 maps throughout Iran using a GIS-based regression analysis of Vs30 measurements at 514 seismic stations. These maps were found to be comparable with those that were previously created from SRTM 30c data. The Vs30 results from ASTER 1c estimated the higher velocities better than those from SRTM 30c. In addition, a combination of ASTER 1c and SRTM 30c amplification maps can be useful for the detection of geological and geomorphological units. We also classified the terrain surface of six seismotectonic regions in Iran into 16 classes, considering three important criteria (slope, convexity and texture) to extract more information about the location and morphological characteristics of the stations. The results show that 98% of the stations are situated in six classes, 30% of which are in class 12, 27% in class 6, 17% in class 9, 16% in class 3, 4% in class 3and the rest of the stations are located in other classes. Full article

Digital terrain models (DTMs) are a fundamental source of information in Earth sciences. DTM-based studies, however, can contain remarkable biases if limitations and inaccuracies in these models are disregarded. In this work, four freely available datasets, including Shuttle Radar Topography Mission C-Band Synthetic Aperture Radar (SRTM C-SAR V3 DEM), Advanced Spaceborne Thermal Emission and Reflection Radiometer Global Digital Elevation Map (ASTER GDEM V2), and two nationwide airborne light detection and ranging (LiDAR)-derived DTMs (at 5-m and 1-m spatial resolution, respectively) were analysed in three geomorphologically contrasting, small (3–5 km²) catchments located in Mediterranean landscapes under intensive human influence (Mallorca Island, Spain). Vertical accuracy as well as the influence of each dataset’s characteristics on hydrological and geomorphological modelling applicability were assessed by using ground-truth data, classic geometric and morphometric parameters, and a recently proposed index of sediment connectivity. Overall vertical accuracy—expressed as the root mean squared error (RMSE) and normalised median deviation (NMAD)—revealed the highest accuracy for the 1-m (RMSE = 1.55 m; NMAD = 0.44 m) and 5-m LiDAR DTMs (RMSE = 1.73 m; NMAD = 0.84 m). Vertical accuracy of the SRTM data was lower (RMSE = 6.98 m; NMAD = 5.27 m), but considerably higher than for the ASTER data (RMSE = 16.10 m; NMAD = 11.23 m). All datasets were affected by systematic distortions. Propagation of these errors and coarse horizontal resolution caused negative impacts on flow routing, stream network, and catchment delineation, and to a lower extent, on the distribution of slope values. These limitations should be carefully considered when applying DTMs for catchment hydrogeomorphological modelling. Full article

Topographic depressions have an important role in hydrological processes as they affect the water balance and runoff response of a watershed. Nevertheless, research has focused in detail neither on the effects of acquisition and processing methods nor on the effects of resolution of nationwide grid digital terrain models (DTMs) on topographic depressions or the hydrological impacts of depressions. Here, we quantify the variation of hydrological depression variables between DTMs with different acquisition methods, processing methods and grid sizes based on nationwide 25 m × 25 m and 10 m × 10 m DTMs and 2 m × 2 m ALS-DTM in Finland. The variables considered are the mean depth of the depression, the number of its pixels, and its area and volume. Shallow and single-pixel depressions and the effect of mean filtering on ALS-DTM were also studied. Quantitative methods and error models were employed. In our study, the depression variables were dependent on the scale, area and acquisition method. When the depths of depression pixels were compared with the most accurate DTM, the maximum errors were found to create the largest differences between DTMs and hence dominated the amount and statistical distribution of the depth error. On the whole, the ability of a DTM to accurately represent depressions varied uniquely according to each depression, although DTMs also displayed certain typical characteristics. Thus, a DTM’s higher resolution is no guarantee of a more accurate representation of topographic depressions, even though acquisition and processing methods have an important bearing on the accuracy. Full article