Search Results (71)

On 20 April 2024, an extreme rainfall event occurred in Jiangwan Town Shaoguan City, Guangdong Province, China, where a historic 24 h precipitation of 206 mm was recorded. This triggered extensive landslides that destroyed residential buildings, severed roads, and drew significant societal attention. Rapid acquisition of landslide inventories, distribution patterns, and key controlling factors is critical for post-disaster emergency response and reconstruction. Based on high-resolution Planet satellite imagery, landslide areas in Jiangwan Town were automatically extracted using the Normalized Difference Vegetation Index (NDVI) differential method, and a detailed landslide inventory was compiled. Combined with terrain, rainfall, and geological environmental factors, the spatial distribution and causes of landslides were analyzed. Results indicate that the extreme rainfall induced 1426 landslides with a total area of 4.56 km², predominantly small-to-medium scale. Landslides exhibited pronounced clustering and linear distribution along river valleys in a NE–SW orientation. Spatial analysis revealed concentrations on slopes between 200–300 m elevation with gradients of 20–30°. Four machine learning models—Logistic Regression, Support Vector Machine (SVM), Random Forest (RF), and Extreme Gradient Boosting (XGBoost)—were employed to assess landslide susceptibility mapping (LSM) accuracy. RF and XGBoost demonstrated superior performance, identifying high-susceptibility zones primarily on valley-side slopes in Jiangwan Town. Shapley Additive Explanations (SHAP) value analysis quantified key drivers, highlighting elevation, rainfall intensity, profile curvature, and topographic wetness index as dominant controlling factors. This study provides an effective methodology and data support for rapid rainfall-induced landslide identification and deep learning-based susceptibility assessment. Full article

The National Museum of Natural History and Science holds a historical collection of 279 small African mammal specimens (Macroscelidea and Rodentia), representing 32 species, gathered during the Portuguese colonial period in Mozambique, Angola, and Guinea-Bissau. This study examines the collection, updates the small mammal species lists for each country, and highlights its importance as a historical baseline for biodiversity research. Rodents dominate the collection, reflecting their natural abundance and diversity, while Macroscelidea are less represented. The Angolan subset of the collection has the highest number of both specimens and species represented. Mozambique is underrepresented, and the Guinea-Bissau subset offers an extensive rodent representation of the country’s inventory. The most well-represented species are Gerbilliscus leucogaster, Lemniscomys striatus, Lemniscomys griselda (from Angola), and Heliosciurus gambianus (from Guinea-Bissau). Notably, the collection includes the neo-paratype of Dasymys nudipes (from Angola). Most species are common and not currently threatened, with geographic origin corresponding to savanna and forest habitats. These findings underscore the importance of integrating historical data and current biodiversity assessments to support multidisciplinary studies on target species, regions, or countries. In this context, the collection remains a valuable key resource for advanced research on African small mammals. Full article

Beijing’s plain-region villages face significant shortages of internal green space, yet studies on village enclosure forests as a supplementary green infrastructure to serve rural communities are limited. So, this study examines village enclosure forests in Beijing Plain to address rural forest shortages. Using 2019 aerial imagery (0.5 m resolution) and forest inventory data, we analysed 1271 villages’ 300 m radius forest coverage via ArcGIS Pro. Key findings show (1) overall forest coverage is 45.30%, higher in outer suburbs (OA), traditional villages (TSH), and large villages; (2) functional types are mainly ecological landscape (37.58%) and ecological–economic forests (36.37%); and (3) afforestation projects (Million-Mu Project rounds 1–2) account for 47.37% coverage. Regression analyses reveal human activities as dominant influencers, with cultivated land area (CLA) having the highest explanatory power. Other significant factors (p < 0.05) include distance from commercial residences (DCR), village size (VS), distance from famous historical sites based on developmental zoning, and forest functions to optimize rural habitats. Full article

This study presents a complete and updated checklist of the vascular flora of the SAC “Bosco di Santo Pietro”, an important natural area located in south-eastern Sicily. Through an integrated approach combining field research, analysis of historical herbariums and a literature review, 583 taxa belonging to 78 families and 339 genera were identified. A comparison with an older floristic list of the Santo Pietro Forest dating back to 1889 highlights some significant changes, such as a decrease in several hygrophilous and nemoral species probably due to climate change and habitat degradation. In particular, our diachronic analysis reveals the disappearance of 178 taxa and the persistence of 199 taxa representing 47% and 53% of the 377 taxa listed in the first inventory, respectively. From the study of the Ellenberg indicator of the two lists, lower values of L and T and higher values of M and N emerge in the older flora, testifying to the significant environmental modifications for more than a century of this Sicilian and Mediterranean hotspot. Full article

Foresters and natural resource managers are increasingly exploring opportunities for the early detection of emerging forest health concerns. One of these emerging concerns is the eastern larch beetle (ELB, Dendroctonus simplex LeConte), a native insect of tamarack (Larix laricina (Du Roi) K., Koch). Historically, the ELB attacked only dead or dying trees, but with climate change, it is now becoming a damaging disturbance agent that affects healthy trees as well. This shift creates a need to evaluate the methods used to detect and quantify the impacted areas. In northern Wisconsin, USA, 50 tamarack stands or aerial detection polygons were surveyed in the field during the 2023 growing season to explore different detection tools for ELBs. We visited 20 polygons identified by aerial sketch map surveys as having ELB mortality, 20 tamarack stands identified by the Astrape satellite imagery algorithm as disturbed, and 10 randomly selected stands from the Wisconsin forest inventory database (WisFIRs) for landscape-level context. For each of the detection methods and the Random stands, information on species composition, mortality, signs of ELB, invasive species, and water presence was quantified. ELBs were common across the landscape, but were not always associated with high levels of mortality. While overstory tree mortality was frequently observed in both aerial sketch map surveys and Astrape, it was not always linked to tamarack mortality. Current methods of detection may need to be re-evaluated in this environment. Tamarack stands in northern Wisconsin were highly heterogeneous in species, which is likely contributing to the difficulties in identifying both tamarack mortality and tamarack mortality specifically caused by ELBs across the two detection methods. Given the evolving impacts of climate change and the shifting dynamics between forests and insects, it is essential to evaluate and innovate detection methods to manage these ecosystems effectively. Full article

The completeness of landslide inventories and the selection of evaluation models significantly impact the accuracy of landslide susceptibility assessments. Conventional field geological survey methods and single remote-sensing technology struggle to reliably identify landslides under complex environmental conditions. Moreover, prevalent landslide susceptibility evaluation models are often plagued by issues such as subjectivity and overfitting. Therefore, we investigated the uncertainty in susceptibility modeling from the aspects of landslide inventory quality and model selection. The study focused on Luquan County in Yunnan Province, China. Leveraging multisource remote-sensing technologies, particularly emphasizing optical remote sensing and InSAR time-series deformation detection, the existing historical landslide inventory was refined and updated. This updated inventory was subsequently used to serve as samples. Nine evaluation indicators, encompassing factors such as distance to faults and tributaries, lithology, distance to roads, elevation, slope, terrain undulation, distance to the main streams, and average annual precipitation, were selected on the basis of the collation and organization of regional geological data. The information value and two coupled machine-learning models were formulated to evaluate landslide susceptibility. The evaluation results indicate that the two coupled models are more appropriate for susceptibility modeling than the single information value (IV) model, with the random forest model optimized by genetic algorithm in Group I2 exhibiting higher predictive accuracy (AUC = 0.796). Furthermore, comparative evaluation results reveal that, under equivalent model conditions, the incorporation of a remote-sensing landslide inventory significantly enhances the accuracy of landslide susceptibility assessment results. This study not only investigates the impact of landslide inventories and models on susceptibility outcomes but also validates the feasibility and scientific validity of employing multisource remote-sensing technologies in landslide susceptibility assessment. Full article

To comply with the United Nations Sustainable Development Goals (UN SDGs), in particular with SDG 3, SDG 11, and SDG 13, a reliable air pollution prediction model must be developed to construct a sustainable, safe, and resilient city and mitigate climate change for a double win. Machine learning (ML) and deep learning (DL) models have been applied to datasets in Macau to predict the daily levels of roadside air pollution in the Macau peninsula, situated near the historical sites of Macau. Macau welcomed over 28 million tourists in 2023 as a popular tourism destination. Still, an accurate air quality forecast has not been in place for many years due to the lack of a reliable emission inventory. This work will develop a dependable air pollution prediction model for Macau, which is also the novelty of this study. The methods, including random forest (RF), support vector regression (SVR), artificial neural network (ANN), recurrent neural network (RNN), long short-term memory (LSTM), and gated recurrent unit (GRU), were applied and successful in the prediction of daily air pollution levels in Macau. The prediction model was trained using the air quality and meteorological data from 2013 to 2019 and validated using the data from 2020 to 2021. The model performance was evaluated based on the root mean square error (RMSE), mean absolute error (MAE), Pearson’s correlation coefficient (PCC), and Kendall’s tau coefficient (KTC). The RF model best predicted PM₁₀, PM_2.5, NO₂, and CO concentrations with the highest PCC and KTC in a daily air pollution prediction. In addition, the SVR model had the best stability and repeatability compared to other models, with the lowest SD in RMSE, MAE, PCC, and KTC after five model runs. Therefore, the results of this study show that the RF model is more efficient and performs better than other models in the prediction of air pollution for the dataset of Macau. Full article

Landslides are one of the major disasters that exist worldwide, posing a serious threat to human life and property safety. Rapid and accurate detection and mapping of landslides are crucial for risk assessment and humanitarian assistance in affected areas. To achieve this goal, this study proposes a landslide recognition method based on machine learning (ML) and terrain feature fusion. Taking the Dawan River Basin in Detuo Township and Tianwan Yi Ethnic Township as the research area, firstly, landslide-related data were compiled, including a landslide inventory based on field surveys, satellite images, historical data, high-resolution remote sensing images, and terrain data. Then, different training datasets for landslide recognition are constructed, including full feature datasets that fusion terrain features and remote sensing features and datasets that only contain remote sensing features. At the same time, different ratios of landslide to non-landslide (or positive/negative, P/N) samples are set in the training data. Subsequently, five ML algorithms, including Extreme Gradient Boost (XGBoost), Adaptive Boost (AdaBoost), Light Gradient Boost (LightGBM), Random Forest (RF), and Convolutional Neural Network (CNN), were used to train each training dataset, and landslide recognition was performed on the validation area. Finally, accuracy (A), precision (P), recall (R), F1 score (F1), and intersection over union (IOU) were selected to evaluate the landslide recognition ability of different models. The research results indicate that selecting ML models suitable for the study area and the ratio of the P/N samples can improve the A, R, F1, and IOU of landslide identification results, resulting in more accurate and reasonable landslide identification results; Fusion terrain features can make the model recognize landslides more comprehensively and align better with the actual conditions. The best-performing model in the study is LightGBM. When the input data includes all features and the P/N sample ratio is optimal, the A, P, R, F1, and IOU of landslide recognition results for this model are 97.47%, 85.40%, 76.95%, 80.95%, and 71.28%, respectively. Compared to the landslide recognition results using only remote sensing features, this model shows improvements of 4.51%, 35.66%, 5.41%, 22.27%, and 29.16% in A, P, R, F1, and IOU, respectively. This study serves as a valuable reference for the precise and comprehensive identification of landslide areas. Full article

Assessing glaciers using recent and historical data and predicting the future impacts on them due to climate change are crucial for understanding global glacier mass balance, regional water resources, and downstream hydrology. Computational methods are crucial for analyzing current conditions and forecasting glacier changes using remote sensing and other data sources. Due to the complexity and large data volumes, there is a strong demand for accelerated computing. AI-based approaches are increasingly being adopted for their efficiency and accuracy in these tasks. Thus, in the current state-of-the-art review work, available research results on the application of AI methods for glacier studies are addressed. Using selected search terms, AI-based publications are collected from research databases. They are further classified in terms of their geographical locations and glacier-related research purposes. It was found that the majority of AI-based glacier studies focused on inventorying and mapping glaciers worldwide. AI techniques like U-Net, Random forest, CNN, and DeepLab are mostly utilized in glacier mapping, demonstrating their adaptability and scalability. Other AI-based glacier studies such as glacier evolution, snow/ice differentiation, and ice dynamic modeling are reviewed and classified, Overall, AI methods are predominantly based on supervised learning and deep learning approaches, and these methods have been used almost evenly in glacier publications over the years since the beginning of this research area. Thus, the integration of AI in glacier research is advancing, promising to enhance our comprehension of glaciers amid climate change and aiding environmental conservation and resource management. Full article

Forest health is an attractive concept in forestry research, which environmental, social, and political interests have shaped. Assessing forest health is crucial, but finding a single definition of the concept is complex. It is determined by the aim of the forest study, different areas of knowledge, scales of work, technology, methodologies, the historical moment, or the source of funding, among others. With almost a century of scientific evidence, the aim is to identify and contextualise temporal changes in the relevance of this key concept. Trends are analysed through the construction of three main descriptors (state variables, drivers, and methods) and the main conceptual subdomains (themes). This review reveals the significant geographical bias driven by diverse needs and interests. Methodologies have evolved from traditional inventories to the use of advanced tools such as remote sensing or ecophysiology, improving forest characterisation at both global and individual scales. Research has evolved from unicausality towards holistic and multidisciplinary approaches, influencing research to date and future scenarios. We identified key knowledge gaps in the scientific literature, particularly the concepts of ecosystem services, Essential Biodiversity Variables (EBVs) and the concept of “one health”. These findings highlight the need for a research assessment, future directions, and scenarios for forest health research. Full article

Longleaf pine (Pinus palustris Mill.) is a conifer historically associated with an open forest ecosystem that extended across much of the coastal plain of the Southeastern United States. It now exists mainly in isolated fragments following the conversion of forests and the long-term disruption of the low-intensity fire regime upon which the species depends. Recent decades have seen efforts to restore longleaf pine forests by government and private landowners. This was reflected in analyses of national forest inventory data during two time periods, ca. 2009–2015 and 2016–2021, that showed increases in the estimated number of longleaf pine trees, the area of the longleaf pine forest type, and the number and area of planted longleaf pine, along with growth in mean plot-level longleaf pine carbon and importance value. At the same time, we found a decrease in the overall forest area containing longleaf pine, manifested across a variety of other forest types. These results point to a dynamic through which forests dominated by longleaf pine are becoming more widespread via restoration, while forests in which the species is a less important component are transitioning to other forest types or land uses. We also detected a decrease over time in the estimated number of longleaf seedlings across most states and forest types and a decline in naturally regenerated longleaf pine. To further assess regeneration trends in longleaf pine, we calculated the estimated proportion of small trees (seedlings and saplings) for the entire species and for seed zone sub-populations. We found a species-wide decrease in the proportion of small trees, from 82.1 percent to 75.1 percent. This reduction was most pronounced along the edges of the species distribution and could indicate less sustainable levels of regeneration in some areas. These results underscore the challenges of facilitating natural regeneration in this important species. Full article

This study developed a comprehensive framework using Google Earth Engine to efficiently generate a forest fire inventory dataset, which enhanced data accessibility without specialized knowledge or access to private datasets. The framework is applicable globally, and the datasets generated are freely accessible and shareable. By implementing the framework in Peninsular Malaysia, significant forest fire factors were successfully extracted, including the Keetch–Byram Drought Index (KBDI), soil moisture, temperature, windspeed, land surface temperature (LST), Palmer Drought Severity Index (PDSI), Normalized Vegetation Index (NDVI), landcover, and precipitation, among others. Additionally, this study also adopted large language models, specifically GPT-4 with the Noteable plugin, for preliminary data analysis to assess the dataset’s validity. Although the plugin effectively performed basic statistical analyses and visualizations, it demonstrated limitations, such as selectively dropping or choosing only relevant columns for tests and automatically modifying scales. These behaviors underscore the need for users to perform additional checks on the codes generated to ensure that they accurately reflect the intended analyses. The initial findings indicate that factors such as KBDI, LST, climate water deficit, and precipitation significantly impact forest fire occurrences in Peninsular Malaysia. Future research should explore extending the framework’s application to various regions and further refine it to accommodate a broader range of factors. Embracing and rigorously validating large language model technologies, alongside developing new tools and plugins, are essential for advancing the field of data analysis. Full article

The land-use, land-use change and forestry (LULUCF) sector is receiving increasing attention in climate change mitigation and greenhouse gas (GHG) emission offsetting. The sector itself and measures applied to mobilize this sector in order to tackle climate change are dominant in nationally determined contributions under the Paris Agreement as well as in national strategies, as in the case of Lithuania. Lithuania has set the goal of becoming a carbon-neutral country in 2050, reducing GHGs by 80% compared to 1990 and offsetting the remaining 20% through the LULUCF sector. Therefore, this paper aims at analyzing historical land-use changes in 1990–2021, as reported for the United Nations Framework Convention on Climate Change (UNFCCC) secretariat, and LULUCF’s potential to achieve climate change mitigation goals, taking into account different land-use change scenarios (business as usual, forest development, forest development + additional measures and forest land 40% + additional measures) for 2030 and 2050 in Lithuania. The scenarios are based on historical and potential future policy-based land-use changes. Projections of GHG emissions/removals for different scenarios are prepared according to the Good Practice Guidance and Uncertainty Management in National Greenhouse Gas Inventories (2006) by the Intergovernmental Panel on Climate Change (IPCC). The results indicate that land-use changes over the period 1990–2021 remained rather stable, with some increases in forest area and grassland at the expense of cropland. The whole LULUCF sector acted as a carbon sink in most cases, forests being a key category for removal. However, reaching climate neutrality in 2050 might be challenging, as the goal to offset 20% of remaining GHG emission compared to 1990 through LULUCF would not be met in any of the scenarios analyzed, even the scenario of maximal forest-area development and additional measures. Considering the high historical GHG-removal fluctuations and the uncertainties of the sector itself, caution should be taken when relying on LULUCF’s potential to reach the set goals. Full article

Accurately predicting the condition rating of a bridge deck is crucial for effective maintenance and repair planning. Despite significant research efforts to develop deterioration models, the efficacy of Random Forest, eXtreme Gradient Boosting (XGBoost), and Artificial Neural Network (ANN) in predicting the condition rating of the nation’s bridge decks has remained unexplored. This study aims to assess the effectiveness of these algorithms for deck condition rating prediction at the national level. To achieve this, the study collected bridge data, which includes National Bridge Inventory (NBI), traffic, and climate regions gathered using Geospatial Information Science (GIS) and remote sensing techniques. Two datasets were collected: bridge data for a single year of 2020 and historical bridge data covering a five-year period from 2016 to 2020. Three models were trained using 319,404 and 1,246,261 bridge decks in the single-year bridge data and the five-year historical bridge data, respectively. Results show that the use of historical bridge data significantly improves the performance of the models compared to the single-year bridge data. Specifically, the Random Forest model achieved an overall accuracy of 83.4% and an average F1 score of 79.7%. In contrast, the XGBoost model achieved an overall accuracy of 79.4% and an average F1 score of 77.5%, while the ANN model obtained an overall accuracy of 79.7% and an average F1 score of 78.4%. Permutation-based variable importance reveals that NBI, traffic, and climate regions significantly contribute to model development. In conclusion, the Random Forest, XGBoost, and ANN models, trained using updated historical bridge data, provide useful tools for accurately predicting the condition rating of bridge decks in the United States, allowing infrastructure managers to efficiently schedule inspections and allocate maintenance resources. Full article

Due to the complex interaction of urban and mountainous floods, assessing flood susceptibility in mountainous urban areas presents a challenging task in environmental research and risk analysis. Data-driven machine learning methods can evaluate flood susceptibility in mountainous urban areas lacking essential hydrological data, utilizing remote sensing data and limited historical inundation records. In this study, two ensemble learning algorithms, Random Forest (RF) and XGBoost, were adopted to assess the flood susceptibility of Kunming, a typical mountainous urban area prone to severe flood disasters. A flood inventory was created using flood observations from 2018 to 2022. The spatial database included 10 explanatory factors, encompassing climatic, geomorphic, and anthropogenic factors. Artificial Neural Network (ANN) and Support Vector Machine (SVM) were selected for model comparison. To minimize the influence of expert opinions on model training, this study employed a strategy of uniformly random sampling in historically non-flooded areas for negative sample selection. The results demonstrated that (1) ensemble learning algorithms offer higher accuracy than other machine learning methods, with RF achieving the highest accuracy, evidenced by an area under the curve (AUC) of 0.87, followed by XGBoost at 0.84, surpassing both ANN (0.83) and SVM (0.82); (2) the interpretability of ensemble learning highlighted the differences in the potential distribution of the training data’s positive and negative samples. Feature importance in ensemble learning can be utilized to minimize human bias in the collection of flooded-site samples, more targeted flood susceptibility maps of the study area’s road network were obtained; and (3) ensemble learning algorithms exhibited greater stability and robustness in datasets with varied negative samples, as evidenced by their performance in F1-Score, Kappa, and AUC metrics. This paper further substantiates the superiority of ensemble learning in flood susceptibility assessment tasks from the perspectives of accuracy, interpretability, and robustness, enhances the understanding of the impact of negative samples on such assessments, and optimizes the specific process for urban flood susceptibility assessment using data-driven methods. Full article