U-net-based semantic classification for flood extent extraction using SAR imagery and GEE platform: A case study for 2019 central US flooding

Li, Zhouyayan; Demir, İbrahim

doi:10.1016/j.scitotenv.2023.161757

Cited by 54 publications

(25 citation statements)

References 84 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…U-Net is one of the most common CNN models for water body mapping in various scenarios [38][39][40], especially for small water body mapping on high-resolution images [27,41,42]. In this study, we used the U-Net model to map all the water bodies in Xinjiang from 2392 Sentinel-2 images from April to October 2022.…”

Section: Water Body Mapping Via the U-net Modelmentioning

confidence: 99%

“…Furthermore, we tested the model performance using 4 indicators [38,44], which are Precision, Overall Accuracy (OA), Recall, and the F1 score (F1). The Precision, Overall Accuracy, and Recall results of the model are 93%, 91%, and 88%, respectively, indicating a good mapping performance similar to that of Pi et al [27].…”

Section: Water Body Mapping Via the U-net Modelmentioning

confidence: 99%

See 1 more Smart Citation

Combining Satellite Images and the Hydraulic Engineering Archive to Map the Processes of Reservoir Construction in Xinjiang

Li,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

Reservoirs are essential hydraulic facilities for water resource allocation in Xinjiang. Since the 1950s, many reservoirs have been constructed for oasis water resource utilization in Xinjiang, enhancing the storage capacity of water resources. There are a few intact and open reservoir archives containing both geolocations and hydraulic attributes, such as the reservoir completion year, which can facilitate our understanding of the correlation between hydraulic engineering and oasis expansion. This paper mapped all the reservoirs of Xinjiang using Sentinel-2 MSI images from 2022. It associated their attributes with the reservoir’s extent, such as the capacity, area, complete year, altitude, etc., by consulting historical almanac data to establish a full elemental dataset with both geographic and attribute information. Furthermore, the spatial variability and historical process of the reservoirs were discussed against geomorphic information and oasis evolution. The results showed that 804 reservoirs were mapped cumulatively in Xinjiang up to 2022, and 1960–1980 and 2005–2010 are the rapidly developed periods. The construction history of the reservoirs indicates that reservoirs’ locations have the spatial tendency to shift from being in oasis plain areas to mountainous areas, and the newly built reservoirs showed a trend of miniaturization in area and maximization in volume.

show abstract

Section: Water Body Mapping Via the U-net Modelmentioning

confidence: 99%

Section: Water Body Mapping Via the U-net Modelmentioning

confidence: 99%

Combining Satellite Images and the Hydraulic Engineering Archive to Map the Processes of Reservoir Construction in Xinjiang

Li,

et al. 2024

Remote Sensing

View full text Add to dashboard Cite

show abstract

“…HAND has been widely used as an independent simplified flood model in flood inundation applications (Li & Demir, 2022;. In the realm of remote-sensing-aided flood mapping applications, HAND has been widely used as an auxiliary dataset in postprocessing (Li & Demir, 2023a;Zeng et al, 2020) and a key input layer for deep-learning-based surface flood mapping frameworks (Li & Demir, 2023b). Liu et al (2016) created the 10-m resolution HAND dataset for the conterminous US (CONUS).…”

Section: Geomorphic Layersmentioning

confidence: 99%

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

Li,

Sermet,

Demir

2024

Preprint

View full text Add to dashboard Cite

Remote Sensing imagery serves as an important data source for Earth surface monitoring and surface processes studies. It is highly likely that RS imagery will become more and more indispensable in the future due to its high scalability and compatibility with data-driven models and ever-evolving software and hardware that become increasingly good at processing large datasets. Although its promising future, the usage of Earth surface observation imagery, such as Landsat, Sentinel-2, and Sentinel-1 images, has been largely limited to retrospective studies, where those images serve mainly as documentations of past events. Recently, there are attempts to expand the current usage of RS Earth surface observation images to forward-looking applications to support decision-making and fast response against future natural hazards. Unlike many well-defined and well-studied topics such as change detection and semantic segmentation for which many benchmark datasets are openly available, so far, there are limited public datasets for Earth surface observation image synthesis tasks for fast prototyping and comparison. To close this gap, we introduced a comprehensive dataset containing previous Earth surface observations, precipitation, soil moisture, land cover, Height Above Nearest Drainage (HAND), DEM, and slope collected during the catastrophic 2019 Central US Flooding events that lasted more than two seasons in Mississippi and Missouri River tributaries. We also incorporated reference labels to allow further investigation of the usefulness of the synthesized images in downstream applications, such as flood inundation mapping. We hope to provide an essential dataset for Earth observation image synthesis studies, with the goal of attracting more attention and inspiring more efforts to broaden the usage of Earth surface observation images into forward-looking applications.

show abstract

“…CNNs are designed to capture features or objects (Li and Demir, 2023) from images from any kind of source and data augmentation (Demiray et al, 2021;Sit et al, 2021) and synthetic image generation (Gautam et al, 2022). LSTMs are successful for predicting time series as they can learn long-term dependencies in complex multivariate sequences (Xiang et al, 2021).…”

Section: Introductionmentioning

confidence: 99%

Crop Yield Prediction based on Reanalysis and Crop Phenology Data in the Agroclimatic Zones

Yeșilköy¹,

Demir²

2023

Preprint

View full text Add to dashboard Cite

Crop yield and phenological stages are remarkably sensitive to not only environmental factors like atmospheric conditions and physical properties of soils but also agricultural activities. Accurate crop yield prediction plays a crucial role in food security and agricultural sustainability. There are several approaches that a wide range of researchers have tried to predict crop yield at different scales. In this study, we tested AgERA5 reanalysis product and crop phenological stage data to predict winter wheat yields in the agricultural lands of the agroclimatic regions of Turkey. The main objective is to propose a deep learning approach based on the combination of the reanalysis, which was extracted for the agricultural lands of the five most productive agroclimatic zones, and crop phenology data to predict winter wheat yields. Five performance indicators, such as normalized root mean squared error (NRMSE), mean absolute percentage error (MAPE), root mean squared error (RMSE), Nash-Sutcliffe Efficiency (NSE), and coefficient of determination (R2), are chosen to test the model’s accuracy and effectiveness. We have obtained promising findings and suggested that AgERA5 reanalysis data can be used as an input for the crop yield prediction of winter wheat with an error below 10% and a coefficient of determination above 0.9.

show abstract

U-net-based semantic classification for flood extent extraction using SAR imagery and GEE platform: A case study for 2019 central US flooding

Cited by 54 publications

References 84 publications

Combining Satellite Images and the Hydraulic Engineering Archive to Map the Processes of Reservoir Construction in Xinjiang

Combining Satellite Images and the Hydraulic Engineering Archive to Map the Processes of Reservoir Construction in Xinjiang

EarthObsNet: A Comprehensive Benchmark Dataset for Data-Driven Earth Observation Image Synthesis

Crop Yield Prediction based on Reanalysis and Crop Phenology Data in the Agroclimatic Zones

Contact Info

Product

Resources

About