Article
Environmental Sciences
Muhittin Ozan Karaman, Saye Nihan Cabuk, Emrah Pekkan
Summary: Geographical information systems (GIS) were used to create landslide susceptibility maps in the Karaburun Peninsula in Izmir. This study provides important inputs for sustainable planning in the region.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2022)
Article
Engineering, Environmental
Hossein Hamedi, Ali Asghar Alesheikh, Mahdi Panahi, Saro Lee
Summary: Using deep learning algorithms including CNN and LSTM, landslide prone areas were identified in Ardabil province, Iran. The LSTM model showed slightly better performance compared to the CNN model, but both models have close performance with acceptable accuracy. AUC values for CNN and LSTM models were 0.821 and 0.832, respectively, indicating the effectiveness of the models in landslide susceptibility mapping.
STOCHASTIC ENVIRONMENTAL RESEARCH AND RISK ASSESSMENT
(2022)
Article
Engineering, Aerospace
Zhan'ao Zhao, Yi He, Sheng Yao, Wang Yang, Wenhui Wang, Lifeng Zhang, Qiang Sun
Summary: This study compares four neural network models for landslide susceptibility mapping (LSM) and finds that the multi-scale convolutional neural network (MSCNN) model performs the best in the training process and mapping results. The MSCNN model outperforms other models in evaluation indicators such as the confusion matrix, ROC curve, and PR curve. Additionally, the prediction models considering neighborhood features perform better than those considering sequence features, indicating that neighborhood features can better represent landslide occurrence characteristics.
ADVANCES IN SPACE RESEARCH
(2022)
Article
Remote Sensing
Yi He, Zhan'ao Zhao, Wang Yang, Haowen Yan, Wenhui Wang, Sheng Yao, Lifeng Zhang, Tao Liu
Summary: This study proposed a new neural network model that integrates landslide factors sequence and pixel spatial neighbourhood features for landslide susceptibility mapping. Experimental results show that the model has higher prediction accuracy compared to individual GRU and MSCNN models, with a 6.1% improvement in terms of AUC.
INTERNATIONAL JOURNAL OF APPLIED EARTH OBSERVATION AND GEOINFORMATION
(2021)
Article
Environmental Sciences
Pankaj Prasad, Victor Joseph Loveson, Sumit Das, Priyankar Chandra
Summary: The study evaluated and compared the landslide susceptibility mapping using six machine learning models in the mountainous regions of western India, finding that the random forest model had the highest precision. It was concluded that random forest is an effective and promising technique for landslide susceptibility assessment in both the research area and regions with similar geo-environmental configurations.
ENVIRONMENTAL EARTH SCIENCES
(2021)
Article
Engineering, Electrical & Electronic
Pingheng Li
Summary: This study explores the pollution risk and resource utilization potential of vegetable waste on land resources through the analysis of remote sensing data and literature collection. By establishing a land use reference database and using geographical information system, key areas for controlling vegetable waste pollution are determined, and the possibility of waste utilization is compared. In addition, the study conducts a preliminary analysis of the causes and cumulative characteristics of polluted soil.
JOURNAL OF SENSORS
(2022)
Article
Geosciences, Multidisciplinary
Nguyen Van Dung, Nguyen Hieu, Tran Van Phong, Mahdis Amiri, Romulus Costache, Nadhir Al-Ansari, Indra Prakash, Hiep Van Le, Hanh Bich Thi Nguyen, Binh Thai Pham
Summary: Novel hybrid models BRS and ABRS were used to generate landslide susceptibility maps in Son La hydropower reservoir basin, Vietnam. The performance of the models was evaluated and compared with other models, showing that BRS model was the most accurate in predicting landslide susceptibility.
GEOMATICS NATURAL HAZARDS & RISK
(2021)
Article
Environmental Sciences
Renata Pacheco Quevedo, Daniel Andrade Maciel, Tatiana Dias Tardelli Uehara, Matej Vojtek, Camilo Daleles Renno, Biswajeet Pradhan, Jana Vojtekova, Quoc Bao Pham
Summary: This study evaluated the performance of geographical random forest (GRF) compared to random forest (RF) and extreme gradient boosting (XGBoost) for landslide susceptibility mapping. GRF showed better performance in predicting susceptibility and provided the most suitable susceptibility map with concentrated vulnerability areas. The spatial assessment improved model performance and spatial models have great potential for landslide susceptibility mapping.
GEOCARTO INTERNATIONAL
(2022)
Article
Geosciences, Multidisciplinary
Marco Loche, Massimiliano Alvioli, Ivan Marchesini, Haakon Bakka, Luigi Lombardo
Summary: Landslide susceptibility was analyzed using the Italian national landslide inventory. The study revealed potential discrepancies in the inventory, leading to biased national-scale susceptibility maps. To address this issue, the researchers further analyzed the national database and attempted to build unbiased susceptibility models. A consistent dominant pattern was found in the Alpine and Apennine sectors.
EARTH-SCIENCE REVIEWS
(2022)
Article
Environmental Sciences
Biswajeet Pradhan, Maher Ibrahim Sameen, Husam A. H. Al-Najjar, Daichao Sheng, Abdullah M. Alamri, Hyuck-Jin Park
Summary: The study presents an optimization method based on meta-learning for spatial prediction of landslides, which starts with promising configurations based on basic and statistical meta-features. Compared to the Bayesian method, this approach achieved slightly lower accuracies on the training and test datasets.
Article
Environmental Sciences
Vasileios Antoniadis, Evangelia E. Golia
Summary: The study aimed to monitor the levels of Cd and Cr in surface soils in the Karditsa region of Central Greece over a span of three years. Spatial variability was significant, with Cd showing enrichment likely due to long-term phosphate fertilizer use. Further studies are recommended to investigate the bioavailability of metal pools in the soil and the potential risks of metal transfer to plants and humans.
ENVIRONMENTAL SCIENCE AND POLLUTION RESEARCH
(2021)
Article
Multidisciplinary Sciences
Alireza Arabameri, Nitheshnirmal Sadhasivam, Hamza Turabieh, Majdi Mafarja, Fatemeh Rezaie, Subodh Chandra Pal, M. Santosh
Summary: The study introduced novel hybrid ensemble models for gully erosion susceptibility mapping in Northern Iran, evaluating the relative importance of predictor factors and identifying the most influential variables for mapping GES. The CDT-RF model was found to be the most robust and accurate in predicting gully erosion susceptibility.
SCIENTIFIC REPORTS
(2021)
Article
Chemistry, Multidisciplinary
Xing Du, Yongfu Sun, Yupeng Song, Zongxiang Xiu, Zhiming Su
Summary: This research aims to analyze the potential of unsupervised machine learning methods in modeling the susceptibility of submarine landslides and compare the performance of three different models. The findings show that the spectral clustering method performs best in forecasting submarine landslide susceptibility.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Sciences
Izabela Skrzypczak, Wanda Kokoszka, Dawid Zientek, Yongjing Tang, Janusz Kogut
Summary: Landslides and rock falls have a significant impact on sustainable construction and infrastructure safety. Environmental monitoring and geotechnical hazard assessment are crucial in building design and construction processes, especially in areas with steep slopes prone to landslides. A detailed landslide hazard map using statistical methods can provide valuable information for risk evaluation and future construction safety measures.
Article
Green & Sustainable Science & Technology
Jaydip Dey, Saurabh Sakhre, Ritesh Vijay, Hemant Bherwani, Rakesh Kumar
Summary: Landslides pose a significant challenge in mountainous regions like Nainital district in India, where geological structures make the area particularly susceptible. In order to mitigate the risk of landslides, susceptibility mapping using remote sensing and geographic information systems is crucial for identifying vulnerable areas and implementing appropriate measures.
ENVIRONMENT DEVELOPMENT AND SUSTAINABILITY
(2021)
Article
Green & Sustainable Science & Technology
Antonis V. Papadopoulos, Dionissios P. Kalivas
Summary: Practicing agriculture involves thorough strategic planning considering multiple factors. Utilizing modern technologies for site-specific crop management offers promising perspectives towards rationalizing agricultural waste management. Spatial variations in soil and plant properties were found to be significant, highlighting the importance of informed agricultural decisions and efficiency improvements.
Article
Geography, Physical
George D. Bathrellos, Hariklia D. Skilodimou, Vasiliki Zygouri, Ioannis K. Koukouvelas
Summary: The study focused on analyzing the recurrence of landslides and creating a hazard assessment map for a mountainous region in central Greece. Results showed that high and very high landslide hazards were mainly concentrated in the western, south-western, and southern parts of the study area.
ZEITSCHRIFT FUR GEOMORPHOLOGIE
(2021)
Article
Geography, Physical
Ahmed M. Youssef, Mazen M. Abu-Abdullah, Emad Abu AlFadail, Hariklia D. Skilodimou, George D. Bathrellos
Summary: The study aimed to identify the causes of the Al-Lith earthen dam failure and ways to prevent and mitigate the potential consequences of future flood occurrences. By utilizing remote sensing images, DEM, field observations, and rainfall data, a geospatial integrated approach combining GIS, remote sensing, hydromorphological analysis, and rainfall-runoff modeling was used to better understand the hydrology of the study area.
ZEITSCHRIFT FUR GEOMORPHOLOGIE
(2021)
Article
Green & Sustainable Science & Technology
Hariklia D. Skilodimou, George D. Bathrellos, Dimitrios E. Alexakis
Summary: This study proposes a simple method to produce a flood hazard assessment map in burned and urban areas with limited data. The study found that the areas with highest flood hazard are in the eastern and southern parts of the study area. The model predictions were robust, and the map was shown to be reliable and accurate, with potential applications in land use planning, disaster mitigation, and post-fire management.
Article
Geosciences, Multidisciplinary
Maria Karpouza, Konstantinos Chousianitis, George D. Bathrellos, Hariklia D. Skilodimou, George Kaviris, Assimina Antonarakou
Summary: This study aims to propose an approach for simultaneous hazard zonation mapping of earthquake-induced secondary effects. The methodology involves evaluating the hazard of seismically induced landslides and soil liquefaction separately, then combining them into a single hazard map to assess areas exposed to both phenomena. Using spatial multi-criteria method and Geographic Information Systems, the methodology can categorize regions threatened by coseismic landslides, soil liquefaction, or both, especially in seismically active regions with mountainous terrain and coastal plain areas.
Article
Geography, Physical
George D. Bathrellos, Hariklia D. Skilodimou
Summary: This paper presents a multi-criteria spatial data analysis method to evaluate suitable locations for sand and gravel extractions. The study area was the upper reaches of Pinios River in central Greece. The results show that the most suitable extraction sites are located in the northern, western, eastern, and southeastern parts of the study area.
ZEITSCHRIFT FUR GEOMORPHOLOGIE
(2022)
Article
Environmental Sciences
Hariklia D. Skilodimou, Vasileios Antoniou, George D. Bathrellos, Eleni Tsami
Summary: Mapping and monitoring coastline changes in Athens Riviera over the past 76 years have revealed significant alterations mainly caused by human interference. The study shows that human interventions have led to major coastline changes in areas such as Faliro Bay, Alimos, and Glyfada, while the coastal regions adjacent to Athens metropolitan area have experienced the highest modifications. The analysis indicates that the rate of coastline changes slowed down after 1987, with 40% increase in coastline length and 2.67 km(2) of land reclaimed to the sea over the past 76 years. The applied method using aerial photographs and GIS techniques proves effective for coastal monitoring and management.
Article
Green & Sustainable Science & Technology
Dimitrios E. Alexakis, George D. Bathrellos, Hariklia D. Skilodimou, Dimitra E. Gamvroula
Summary: The study investigated the soil quality in the Ioannina polje in north-west Greece concerning arsenic (As) and zinc (Zn), finding high concentrations of As and Zn in the soil, mainly distributed on very gentle slopes and strongly correlated with geological parent materials and human-induced contamination sources. The results showed that urban and agricultural land use covered 92% of the total area, with higher levels of As and Zn in the soil compared to European topsoils.
Article
Chemistry, Multidisciplinary
Fakhrul Islam, Muhammad Nasar Ahmad, Hammad Tariq Janjuhah, Matee Ullah, Ijaz Ul Islam, George Kontakiotis, Hariklia D. Skilodimou, George D. Bathrellos
Summary: This study used geospatial modelling and machine learning techniques to identify areas susceptible to soil erosion in Murree, Pakistan. By considering multiple independent variables, the FR model showed the highest accuracy in predicting soil erosion. The results and susceptibility maps of this study are important for decision-makers in preventing soil erosion.
APPLIED SCIENCES-BASEL
(2022)
Article
Environmental Studies
Liaqat Ali, Shehzad Ali, Seema Anjum Khattak, Hammad Tariq Janjuhah, George Kontakiotis, Rahib Hussain, Shah Rukh, Mohammad Tahir Shah, George D. D. Bathrellos, Hariklia D. D. Skilodimou
Summary: This study investigated the health and environmental impacts of coal mining activities in the Makarwal coal mining area in Pakistan. Soil samples collected from the affected areas showed high concentrations of toxic metals such as Ni, Cd, Cr, Cu, Zn, and Pb. Factor analysis indicated that the contamination in the area is likely associated with the geological ore strata in the coalfield. Based on geoaccumulation and ecological risk indices, certain trace elements pose a high risk to humans and the ecosystem. The source of metal contamination is likely from exposed sedimentary rocks, including limestone, dolomite, sandstone, and coal.
Article
Chemistry, Multidisciplinary
Jehanzeb Khan, Waqas Ahmed, Muhammad Waseem, Wajid Ali, Inayat ur Rehman, Ihtisham Islam, Hammad Tariq Janjuhah, George Kontakiotis, George D. Bathrellos, Hariklia D. Skilodimou
Summary: This study presents a detailed analysis of water ingress problems in the Lowari Tunnel in Pakistan and evaluates its suitability for different purposes. The water quality varied depending on geological conditions, with the south portal dominated by Mg cations and bicarbonate anions. The water was suitable for tunnel support systems but not for drinking, and it was classified as excellent for irrigation, benefiting local agriculture.
APPLIED SCIENCES-BASEL
(2023)
Article
Geosciences, Multidisciplinary
Maria Karpouza, George D. Bathrellos, George Kaviris, Assimina Antonarakou, Hariklia D. Skilodimou
Summary: This study focuses on the hazard assessment of the Xerias River drainage basin in Greece, particularly in terms of flooding and tsunami inundation. It identifies safe locations and routes for schools and highlights the importance of scientific analysis in disaster management and planning.
INTERNATIONAL JOURNAL OF DISASTER RISK REDUCTION
(2023)
Article
Geosciences, Multidisciplinary
Kanella Valkanou, Efthimios Karymbalis, George Bathrellos, Hariklia Skilodimou, Konstantinos Tsanakas, Dimitris Papanastassiou, Kalliopi Gaki-Papanastassiou
Summary: This study estimates the annual soil loss in a fire-affected area using the Universal Soil Loss Equation (USLE). The results show a significant increase in soil loss after the fire, with an increase in the area of high erosion rates.