Hindcast and forecast of daily inundation extents using satellite SAR and altimetry data with rotated empirical orthogonal function analysis: Case study in Tonle Sap Lake Floodplain

Chang, Chin‐Yu; Lee, Hyongki; Kim, Dong Hwan; Hwang, Eui-Ho; Hossain, Faisal; Chishtie, Farrukh; Jayasinghe, Susantha; Basnayake, Senaka

doi:10.1016/j.rse.2020.111732

Cited by 21 publications

(14 citation statements)

References 98 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…IoU, mIoU, and OA are standard evaluation metrics for image segmentation tasks. Omission and commission error rates are reported for comparison to remote sensing literature [5,56]. Omission rates are false negative water detection rates, and commission rates are false positive water detection rates.…”

Section: Evaluation Metricsmentioning

confidence: 99%

Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

Bai

Yang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

Identifying permanent water and temporary water in flood disasters efficiently has mainly relied on change detection method from multi-temporal remote sensing imageries, but estimating the water type in flood disaster events from only post-flood remote sensing imageries still remains challenging. Research progress in recent years has demonstrated the excellent potential of multi-source data fusion and deep learning algorithms in improving flood detection, while this field has only been studied initially due to the lack of large-scale labelled remote sensing images of flood events. Here, we present new deep learning algorithms and a multi-source data fusion driven flood inundation mapping approach by leveraging a large-scale publicly available Sen1Flood11 dataset consisting of roughly 4831 labelled Sentinel-1 SAR and Sentinel-2 optical imagery gathered from flood events worldwide in recent years. Specifically, we proposed an automatic segmentation method for surface water, permanent water, and temporary water identification, and all tasks share the same convolutional neural network architecture. We utilize focal loss to deal with the class (water/non-water) imbalance problem. Thorough ablation experiments and analysis confirmed the effectiveness of various proposed designs. In comparison experiments, the method proposed in this paper is superior to other classical models. Our model achieves a mean Intersection over Union (mIoU) of 52.99%, Intersection over Union (IoU) of 52.30%, and Overall Accuracy (OA) of 92.81% on the Sen1Flood11 test set. On the Sen1Flood11 Bolivia test set, our model also achieves very high mIoU (47.88%), IoU (76.74%), and OA (95.59%) and shows good generalization ability.

show abstract

Section: Evaluation Metricsmentioning

confidence: 99%

Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

Bai

Yang

et al. 2021

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…An alternative way of reducing dimensionality of spatial‐temporal data is to extract key features in the form of patterns or trends (feature extraction methods). A common feature extraction method is Empirical Orthogonal Function (EOF) analysis, which has been used in areas of remote sensing, climate science and oceanography (e.g., Aires et al., 2014, 2020; Alvarez & Pan, 2016; Chang et al., 2020; Ghosh et al., 2021; Golestani & Sørensen, 2013; Jolliffe & Cadima, 2016; Marques et al., 2009). EOF analysis reduces the spatial‐temporal data into pairs (modes) of spatial patterns (EOF) and temporal variability functions, termed expansion coefficients (EC) (Jolliffe & Cadima, 2016; Zhang & Moore, 2015).…”

Section: Introductionmentioning

confidence: 99%

Upskilling Low‐Fidelity Hydrodynamic Models of Flood Inundation Through Spatial Analysis and Gaussian Process Learning

Fraehr

Wang

et al. 2022

Water Resources Research

View full text Add to dashboard Cite

Floods are some of the most destructive natural disasters in the world and they are projected to become more severe and frequent with climate change (IPCC, 2021). During a flood event normally dry areas are inundated until a maximum inundation extent is reached (flooding period), whereafter the water recedes back to the normal state (recession period). Capturing the dynamics of this behavior is of great importance for risk management and has led to the development of advanced hydrodynamic models. Hydrodynamic models can represent different levels of complexity and precision. For simulating the dynamics of flood inundation, two-dimensional hydrodynamic models that numerically solve the depth-averaged Navier-Stokes equations on a high-resolution grid is normally applied (Teng et al., 2017). These high-resolution hydrodynamic models are often referred to as high-fidelity models, where the fidelity refers to the model's degree of realism (Razavi et al., 2012). However,

show abstract

“…Notice that occasional events, such as El Niño Southern Oscillation (ENSO), cannot be underestimated in the Mekong Basin, since it seriously distorts the spatiotemporal precipitation pattern, and consequently, the runoff [45,46]. Besides climate, the regulation effect due to Tonle Sap Lake [47] and the tidal backwater effect causing salt intrusion [48] also provide substantial effects on the water level and runoff in the river delta. Additionally, human activities, such as sand mining, dike construction, groundwater extraction, and reservoir operations [49] also amplify the tidal backwater effect and salt intrusion [50].…”

Section: Study Areamentioning

confidence: 99%

Prospects for Reconstructing Daily Runoff from Individual Upstream Remotely-Sensed Climatic Variables

2022

View full text Add to dashboard Cite

Basin water supply, planning, and its allocation requires runoff measurements near an estuary mouth. However, insufficient financial budget results in no further runoff measurements at critical in situ stations. This has recently promoted the runoff reconstruction via regression between the runoff and nearby remotely-sensed variables on a monthly scale. Nonetheless, reconstructing daily runoff from individual basin-upstream remotely-sensed climatic variables is yet to be explored. This study investigates standardized data regression approach to reconstruct daily runoff from the individual remotely-sensed climatic variables at the Mekong Basin’s upstream. Compared to simple linear regression, the daily runoff reconstructed and forecasted from the presented approach were improved by at most 5% and 10%, respectively. Reconstructed runoffs using neural network models yielded ~0.5% further improvement. The improvement was largely a function of the reduced discrepancy during dry and wet seasons. The best forecasted runoff obtained from the basin-upstream standardized precipitation index, yielded the lowest normalized root-mean-square error of 0.093.

show abstract

Hindcast and forecast of daily inundation extents using satellite SAR and altimetry data with rotated empirical orthogonal function analysis: Case study in Tonle Sap Lake Floodplain

Cited by 21 publications

References 98 publications

Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

Enhancement of Detecting Permanent Water and Temporary Water in Flood Disasters by Fusing Sentinel-1 and Sentinel-2 Imagery Using Deep Learning Algorithms: Demonstration of Sen1Floods11 Benchmark Datasets

Upskilling Low‐Fidelity Hydrodynamic Models of Flood Inundation Through Spatial Analysis and Gaussian Process Learning

Prospects for Reconstructing Daily Runoff from Individual Upstream Remotely-Sensed Climatic Variables

Contact Info

Product

Resources

About