Model Construction and Evaluation of Flood Area Estimation Based on SAR and GPS Data DOI
Yifan Yang,

Ohira Naoki,

Hideomi Gokon

и другие.

IGARSS 2022 - 2022 IEEE International Geoscience and Remote Sensing Symposium, Год журнала: 2024, Номер unknown, С. 1362 - 1365

Опубликована: Июль 7, 2024

Язык: Английский

High-precision flood detection and mapping via multi-temporal SAR change analysis with semantic token-based transformer DOI Creative Commons
Tamer Saleh, Shimaa Holail, Xiongwu Xiao

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 131, С. 103991 - 103991

Опубликована: Июнь 24, 2024

Язык: Английский

Процитировано

8

Local and regional climate trends and variabilities in Ethiopia: Implications for climate change adaptations DOI Creative Commons
Temesgen Gashaw,

Gizachew Belay Wubaye,

Abeyou W. Worqlul

и другие.

Environmental Challenges, Год журнала: 2023, Номер 13, С. 100794 - 100794

Опубликована: Ноя. 14, 2023

Ethiopia is experiencing considerable impact of climate change and variability in the last five decades. Analyzing trends essential to develop effective adaptation strategies, particularly for countries vulnerable change. This study analyzed variabilities (rainfall, maximum temperature (Tmax), minimum (Tmin)) at local regional scales Ethiopia. The analysis was carried out considering each meteorological station, while analyses were based on agro-ecological zones (AEZs). used observations from 47 rainfall 37 stations obtained Ethiopian Meteorological Institute (EMI) period 1986 2020. Modified Mann-Kendall (MMK) trend test Theil Sen's slope estimator analyze magnitudes change, respectively, as well temperature. coefficient variation (CV) standardized anomaly index (SAI) also employed evaluate variabilities. level revealed that Bega (dry season), Kiremt (main rainy annual showed increasing trend, albeit no significant, most stations, but Belg (small rainy) season a non-significant decreasing trend. levels indicated an Bega, Kiremt, AEZs, greater number AEZs. result both discerned spatially temporally more homogeneous warming Both Tmax Tmin seasonal stations. Likewise, increase recorded mean entire/most observed have several implications adaptations. For example, decrease AEZs would negative areas heavily depend season's crop production. Some options include identifying short maturing varieties, soil moisture conservation, supplemental irrigation crops using harvested water during main season. Conversely, since first three months (October December) are harvest parts Ethiopia, loss, hence, early planting date some strategies. Because temperature, demand will due increased evapotranspiration. On other hand, can be small season, planting. In view these findings, it imperative implement climate-smart agricultural strategies specific zone (AEZ) adapt changes

Язык: Английский

Процитировано

14

Evaluating the association of flood mapping with land use and land cover patterns in the Kosi River Basin (India) DOI
Aditya Kumar Singh, Thendiyath Roshni, V. P. Singh

и другие.

Acta Geophysica, Год журнала: 2024, Номер 72(6), С. 4649 - 4669

Опубликована: Май 15, 2024

Язык: Английский

Процитировано

5

Integrating Satellite Images and Machine Learning for Flood Prediction and Susceptibility Mapping for the Case of Amibara, Awash Basin, Ethiopia DOI Creative Commons
Gizachew Kabite Wedajo,

Tsegaye Demisis Lemma,

Tesfaye Fufa Gedefa

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(12), С. 2163 - 2163

Опубликована: Июнь 14, 2024

Flood is one of the most destructive natural hazards affecting environment and socioeconomic system world. The effects are higher in developing countries due to their vulnerability disaster limited coping capacity. Awash basin flood-prone basins Ethiopia where frequency severity flooding has been increasing. Amibara district flood-affected areas basin. To minimize flooding, reliable up-to-date information on highly required. However, flood monitoring forecasting systems lacking including Therefore, this study aimed (i) identify important causative factors, (ii) evaluate performance random forest (RF), linear regression, support vector machine (SVM), long short-term memory (LSTM) learning models for prediction susceptibility mapping area. For modeling, nine factors were considered, namely elevation, slope, aspect, curvature, topographic wetness index, soil texture, rainfall, land use/land cover, curve number. Pearson correlation coefficient gain ratio (InGR) techniques used relative importance factors. trained tested using 400 historic points collected from 10 September 2020 Sentinel 2 image, during which a event occurred Multiple metrics, precession, recall, F1-score, accuracy, receiver operating characteristics (area under curve), models. results showed that all considered important; slope more while number, texture less important. Furthermore, outperformed predicting area whereas regression model next best RF. SVM performed poorly mapping. integration satellite field datasets coupled with state-of-the-art-machine novel approaches thus improved accuracy Such methodology improves state-of-the-art knowledge fills gaps traditional techniques. Thus, can provide crucial informed decision-making processes designing control strategies risk management.

Язык: Английский

Процитировано

5

Flood Index-Enhanced deep learning model for coastal inundation mapping in SAR imagery DOI
W Chen, Yinfei Zhou, Xiaofeng Li

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2025, Номер 139, С. 104550 - 104550

Опубликована: Апрель 19, 2025

Язык: Английский

Процитировано

0

Improved integrated framework for flooded crop damage and recovery assessment: A multi-source earth observation and participatory mapping in Hadejia, Nigeria DOI Creative Commons
Lukumon Olaitan Lateef, Hugo Costa, Pedro Cabral

и другие.

Journal of Environmental Management, Год журнала: 2025, Номер 384, С. 125542 - 125542

Опубликована: Май 1, 2025

Flooding has increasingly significant adverse effects on global food security, and there is a lack of framework to effectively integrate remote sensing with survey data for accurate damage recovery assessment. Also, optical satellite images flood mapping face cloud interference, free synthetic aperture radar (SAR) the temporal frequency needed capture flooding dynamics. This study developed new modelling crop damage, loss, due flash using time-series multi-sensor images. Crop from was validated extensive participatory data. were assessed during Nigeria's 2020 2022 floods. Consistency found between farmer-reported losses sensing-based assessments: 91 % farmers reporting total loss had no recovery. Flood maps assessments achieved over 90 accuracy, demonstrating reliability multi-source SAR combined machine learning technique. Severe evident, only 13 16 flooded cropland recovered in 2022, respectively. The integrated approach this eliminates uncertainties other techniques, overcomes limitations, offers scalability national-level implementation, providing critical information post-disaster planning, farmer compensation, sustainable agricultural practices enhance security changing climate.

Язык: Английский

Процитировано

0

A Novel Flood Risk Analysis Framework Based on Earth Observation Data to Retrieve Historical Inundations and Future Scenarios DOI Creative Commons
Kezhen Yao, Saini Yang, Zhihao Wang

и другие.

Remote Sensing, Год журнала: 2024, Номер 16(8), С. 1413 - 1413

Опубликована: Апрель 16, 2024

Global warming is exacerbating flood hazards, making the robustness of risk management a critical issue. Without considering future scenarios, analysis built only on historical knowledge may not adequately address coming challenges posed by climate change. A comprehensive framework based both inundations and projections to tackle uncertainty still lacking. In this view, scenario-based, data-driven that for first time integrates recent floods trends here presented, consisting inundation-prone high-risk zones. Considering Poyang Lake Eco-Economic Zone (PLEEZ) in China as study area, we reproduced inundation scenarios major events using Sentinel-1 imagery from 2015 2021, used them build baseline model. The results show 11.7% PLEEZ currently exposed zone. SSP2-RCP4.5 scenario, would gradually decrease after peaking around 2040 (with 19.3% increase areas), while under traditional fossil fuel-dominated development pathway (SSP5-RCP8.5), peak occur with higher intensity about decade earlier. attribution reveal intensification heavy rainfall dominant driver exploitation unused land such wetlands induces significant risk. Finally, hierarchical panel recommended measures was developed. We hope our inspires newfound awareness provides basis more effective river basins.

Язык: Английский

Процитировано

2

Detection of flood-affected areas using multitemporal remote sensing data: a machine learning approach DOI
Robert Kurniawan,

Imam Sujono,

Wahyu Caesarendra

и другие.

Earth Science Informatics, Год журнала: 2024, Номер 18(1)

Опубликована: Дек. 12, 2024

Язык: Английский

Процитировано

1

Flood Inundation Mapping of Krishnaraja Nagar, Mysore Using Sentinel-1 Sar Images DOI
Mukul Kumar Sahu,

S. Rangaswamy,

G. S. Dwarakish

и другие.

Lecture notes in civil engineering, Год журнала: 2024, Номер unknown, С. 229 - 241

Опубликована: Янв. 1, 2024

Язык: Английский

Процитировано

0

CIBENet: A channel interaction and bridging-enhanced change detection network for optical and SAR remote sensing images DOI Creative Commons
Liang Huang, Min Wang, Bo‐Hui Tang

и другие.

International Journal of Applied Earth Observation and Geoinformation, Год журнала: 2024, Номер 131, С. 103969 - 103969

Опубликована: Июнь 15, 2024

Язык: Английский

Процитировано

0