Comparison of U-Net and Fully Convolutional Networks (FCN) for concrete cracks detection using raw images under various conditions DOI
Mohammed AL-Qadri, Peiwei Gao, Hui Zhang

et al.

Journal of Intelligent & Fuzzy Systems, Journal Year: 2024, Volume and Issue: unknown, P. 1 - 13

Published: May 6, 2024

Crack detection in concrete buildings is crucial for assessing structural health, but it poses challenges due to complex backgrounds, real-time requirements, and high accuracy demands. Deep learning techniques, including U-Net Fully Convolutional Networks (FCN), have shown promise crack detection. However, they are sensitive real-world environmental variations, impacting robustness accuracy. This paper compares the performance of FCN on bridges using raw images under various conditions. A dataset 157 (100 training, 57 testing) was used, models were evaluated based Dice similarity coefficient Jaccard index. slightly outperformed (94.88% vs. 94.21%), while had a slight advantage validation (93.55% 92.99%). These findings provide valuable insights automated infrastructure maintenance repair.

Language: Английский

Neuroforecasting of daily streamflows in the UK for short- and medium-term horizons: A novel insight DOI
Francesco Granata, Fabio Di Nunno

Journal of Hydrology, Journal Year: 2023, Volume and Issue: 624, P. 129888 - 129888

Published: July 1, 2023

Language: Английский

Citations

58
A stacked machine learning model for multi-step ahead prediction of lake surface water temperature DOI Open Access
Fabio Di Nunno, Senlin Zhu, Mariusz Ptak

et al.

The Science of The Total Environment, Journal Year: 2023, Volume and Issue: 890, P. 164323 - 164323

Published: May 20, 2023

Language: Английский

Citations

54
Hydraulic flow unit and rock types of the Asmari Formation, an application of flow zone index and fuzzy C-means clustering methods DOI Creative Commons
Seyedeh Hajar Eftekhari, Mahmoud Memariani, Zahra Maleki

et al.

Scientific Reports, Journal Year: 2024, Volume and Issue: 14(1)

Published: Feb. 29, 2024

Rock types are the reservoir's most essential properties for special facies modeling in a defined range of porosity and permeability. This study used clustering techniques to identify rock 280 core samples from one wells drilled Asmari reservoir Mansouri field, SW Iran. Four hydraulic flow units (HFUs) were determined studied data utilizing histogram analysis, normal probability sum squared errors (SSE) statistical methods. Then, two zone index (FZI) fuzzy c-means (FCM) methods determine given well according results obtained HFU continuity acts in-depth. The FCM method, with number 3.12, compared FZI, 2.77, shows more depth. relationship between permeability improved considerably by techniques. improvement is achieved using FZI method study. Generally, all increased 0.55 0.81 first finally 0.94 fourth HFU. Similar an characterized samples. In comparison, correlation coefficients less than those general case HFUs. aims flowing fluid porous medium employing c-mean logic. Also, determining units, especially siliceous-clastic log Formation, third have highest quality Results can be nearby wellbores without cores.

Language: Английский

Citations

21
Drought Impact, Vulnerability, Risk Assessment, Management and Mitigation under Climate Change: A Comprehensive Review DOI Creative Commons
Ghani Rahman, Minkyu Jung, Tae‐Woong Kim

et al.

KSCE Journal of Civil Engineering, Journal Year: 2025, Volume and Issue: 29(1), P. 100120 - 100120

Published: Jan. 1, 2025

Language: Английский

Citations

7
Analysis of SPI index trend variations in the United Kingdom - A cluster-based and bayesian ensemble algorithms approach DOI Creative Commons
Fabio Di Nunno, Giovanni de Marinis, Francesco Granata

et al.

Journal of Hydrology Regional Studies, Journal Year: 2024, Volume and Issue: 52, P. 101717 - 101717

Published: Feb. 27, 2024

United Kingdom (UK). A regional investigation of the Standard Precipitation Index (SPI) trends and abrupt changes in UK has been carried out. The K-means algorithm was employed to partition study area into six homogeneous regions, each distinguished by specific SPI characteristics. Subsequently, seasonal Mann-Kendall (MK) test Bayesian Changepoint Detection Time Series Decomposition (BEAST) were used evaluate overall for cluster time scale, as well identify trend seasonality along series, respectively. MK revealed statistically significant increasing all clusters, except southeastern UK, where decreasing, but not significant, observed. Moreover, despite a scenario suggesting an increasingly humid BEAST analysis allowed detection decreasing trends, resulting sudden from wet dry conditions, that cannot be identified using test. Alongside these, also positive across or negative variations seasonality, which are followed longer shorter periods, Overall, approach provides detailed picture changes, light impact climate change on different areas UK.

Language: Английский

Citations

16
Short-term drought Index forecasting for hot and semi-humid climate Regions: A novel empirical Fourier decomposition-based ensemble Deep-Random vector functional link strategy DOI
Mehdi Jamei, Mumtaz Ali, Sayed M. Bateni

et al.

Computers and Electronics in Agriculture, Journal Year: 2024, Volume and Issue: 217, P. 108609 - 108609

Published: Jan. 11, 2024

Language: Английский

Citations

8
Mapping drought evolution in Ethiopia: trends, clustering, and Bayesian estimation of abrupt changes DOI
Fabio Di Nunno, Mehmet Berkant Yıldız,

Yordanos Gebru Afework

et al.

Natural Hazards, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 13, 2024

Language: Английский

Citations

8
A Combined Clustering and Trends Analysis Approach for Characterizing Reference Evapotranspiration in Veneto DOI Open Access
Fabio Di Nunno,

Marco De Matteo,

Giovanni Izzo

et al.

Sustainability, Journal Year: 2023, Volume and Issue: 15(14), P. 11091 - 11091

Published: July 16, 2023

Climate change is having an increasing effect on the water cycle, hindering proper management of resources for different purposes. Veneto, Northern Italy, a region characterized by various climatic conditions, ranging from coastal area to inland, which exhibits significant agricultural productivity with high irrigation demand, up mountainous north. This study assesses key aspect climate in Veneto focusing crucial hydrological parameter, reference evapotranspiration (ETo), calculated using Penman–Monteith equation. The K-means algorithm was employed divide into nine homogeneous regions, each specific and features. Furthermore, seasonal Mann–Kendall (MK) test innovative trends analysis (ITA) method were used investigate related monthly precipitation, ETo, variables. MK revealed negative precipitation all clusters. In contrast, ETo appear be decreasing some clusters, both coast others. ITA indicated more pronounced higher values highlighting variations that primarily impact extreme values. Overall, this study’s approach, incorporates clustering methods, provides detailed depiction enabling identification distinct areas assessment evolutionary concerning regions.

Language: Английский

Citations

15
An innovative method integrating run theory and DBSCAN for complete three-dimensional drought structures DOI Creative Commons
Jing Zhang, Min Zhang,

Yang Yu

et al.

The Science of The Total Environment, Journal Year: 2024, Volume and Issue: 926, P. 171901 - 171901

Published: March 22, 2024

Drought displays dynamic and uncertain spatiotemporal characteristics, thus it is typically not confined to fixed temporal-spatial boundaries. Existing drought clustering methods often involve spatially points or grids into patches, subsequently connected over time form three-dimensional structures. Despite this process being able extract clusters, likely overlook mild relatively small, isolated patches. To overcome limitation, paper presented an effective method (named STD-CLUSTER) for identifying clusters with complete The initially employed run theory events as "lines" clustered these using the Density-Based Spatial Clustering of Applications Noise (DBSCAN) algorithm. A case study on 2006 flash in Yangtze River Basin demonstrated that STD-CLUSTER successfully ensured integrity by considering isolated, disconnected Additionally, in-depth analysis examined seasonal China from 1991 2022, a total 35 clusters. These began ended small-area exhibiting features expansion, contraction, spread, merging, splitting time. Furthermore, changes significantly influenced evolution affected area severity increasing spring summer decreasing autumn winter. applicability proposed extends beyond various geographical regions scales, providing support comprehensively investigating drought.

Language: Английский

Citations

5
The socioeconomic impact of severe droughts on agricultural lands over different provinces of Iran DOI Creative Commons
Yusef Kheyruri, Ahmad Sharafati, Aminreza Neshat

et al.

Agricultural Water Management, Journal Year: 2023, Volume and Issue: 289, P. 108550 - 108550

Published: Oct. 15, 2023

The lack of rainfall is the primary cause drought, reduced crop harvest (CH), and socioeconomic drought. Agriculture source income for most Iranians, drought can harm people's lives irreparably. This study examines changes in CHs prices (CPs) across provinces Iran during severe all time its impact on producers (farmers), consumers, public prosperity using Surplus Economic Method (SEM). Our focused crops that have a big Iranian life, such as wheat, barley, potato, onion, tomato, lentils, chickpeas, alfalfa. results indicated Iran's hydrological occurred from 2000 to 2002. rainfed farms experienced pronounced terms CH, while financial damages were highest irrigated areas. Among investigated, wheat has greatest reduction 80%. Moreover, grains price change (40% increase) Wheat underwent steepest CH reduction. Legumes rise. During had lower yields, causing losses but some still made profit. affected northwest west farmers adversely, southern central gained through increased product prices. Drought adverse effects examined it. corresponds barley western regions Zagros Mountains. diversity northwestern these important areas farming supply Iran. Agricultural droughts affect people lead demonstrated are chiefly caused by shortage winter spring rains. Identifying factors showed depth snow winter. Additionally, data analysis revealed combined effect precipitation with coverage (61%). make policies based region climate, marketing plans droughts, solutions address harmful

Language: Английский

Citations

10