Flood Mapping Based on Multiple Endmember Spectral Mixture Analysis and Random Forest Classifier—The Case of Yuyao, China

Feng, Quanlong; Gong, Jianhua; Liu, Jiantao; Li, Yang

doi:10.3390/rs70912539

Cited by 46 publications

(31 citation statements)

References 45 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The relatively low accuracy of the latter study was attributed to the presence of vegetation in the flooded area. Feng et al [27] employed supervised classification to map surface waterbodies with 30 m multispectral HJ-1B imagery and achieved 94% overall accuracies. Similarly, Verpoorter et al [28] achieved an accuracy of 95% using Landsat 7 ETM+ imagery.…”

Section: Introductionmentioning

confidence: 99%

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

et al. 2019

View full text Add to dashboard Cite

S.M.alfieri-1@tudelft.nl (S.M.A.); M.Menenti@tudelft.nl (M.M.)Abstract: Small reservoirs play an important role in mining, industries, and agriculture, but storage levels or stage changes are very dynamic. Accurate and up-to-date maps of surface water storage and distribution are invaluable for informing decisions relating to water security, flood monitoring, and water resources management. Satellite remote sensing is an effective way of monitoring the dynamics of surface waterbodies over large areas. The European Space Agency (ESA) has recently launched constellations of Sentinel-1 (S1) and Sentinel-2 (S2) satellites carrying C-band synthetic aperture radar (SAR) and a multispectral imaging radiometer, respectively. The constellations improve global coverage of remotely sensed imagery and enable the development of near real-time operational products. This unprecedented data availability leads to an urgent need for the application of fully automatic, feasible, and accurate retrieval methods for mapping and monitoring waterbodies. The mapping of waterbodies can take advantage of the synthesis of SAR and multispectral remote sensing data in order to increase classification accuracy. This study compares automatic thresholding to machine learning, when applied to delineate waterbodies with diverse spectral and spatial characteristics. Automatic thresholding was applied to near-concurrent normalized difference water index (NDWI) (generated from S2 optical imagery) and VH backscatter features (generated from S1 SAR data). Machine learning was applied to a comprehensive set of features derived from S1 and S2 data. During our field surveys, we observed that the waterbodies visited had different sizes and varying levels of turbidity, sedimentation, and eutrophication. Five machine learning algorithms (MLAs), namely decision tree (DT), k-nearest neighbour (k-NN), random forest (RF), and two implementations of the support vector machine (SVM) were considered. Several experiments were carried out to better understand the complexities involved in mapping spectrally and spatially complex waterbodies. It was found that the combination of multispectral indices with SAR data is highly beneficial for classifying complex waterbodies and that the proposed thresholding approach classified waterbodies with an overall classification accuracy of 89.3%. However, the varying concentrations of suspended sediments (turbidity), dissolved particles, and aquatic plants negatively affected the classification accuracies of the proposed method, whereas the MLAs (SVM in particular) were less sensitive to such variations. The main disadvantage of using MLAs for operational waterbody mapping is the requirement for suitable training samples, representing both water and non-water land covers. The dynamic nature of reservoirs (many reservoirs are depleted at least once a year) makes the re-use of training data unfeasible. The study found that aggregating (combining) the thresholding results of two SAR and multispectral features, namely the S1 VH polari...

show abstract

Section: Introductionmentioning

confidence: 99%

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

et al. 2019

View full text Add to dashboard Cite

show abstract

“…Other approaches rely on machine-learning algorithms to extract water bodies from optical imagery. Prevalent supervised classification algorithms that have been used include Random Forests [14,15], neural networks [16], decision trees [17], support vector machines [18,19] and the perceptron model [20]. Classification-based approaches may achieve higher accuracy than thresholding methods; however, ground truth data are required to select appropriate training samples.…”

mentioning

confidence: 99%

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

et al. 2018

View full text Add to dashboard Cite

Satellite data offer the opportunity for monitoring the temporal flooding dynamics of seasonal wetlands, a parameter that is essential for the ecosystem services these areas provide. This study introduces an unsupervised approach to estimate the extent of flooded areas in a satellite image relying on the physics of light interaction with water, vegetation and their combination. The approach detects automatically thresholds on the Short-Wave Infrared (SWIR) band and on a Modified-Normalized Difference Vegetation Index (MNDVI), derived from radiometrically-corrected Sentinel-2 data. Then, it combines them in a meaningful way based on a knowledge base coming out of an iterative trial and error process. Classes of interest concern water and non-water areas. The water class is comprised of the open-water and water-vegetation subclasses. In parallel, a supervised approach is implemented mainly for performance comparison reasons. The latter approach performs a random forest classification on a set of bands and indices extracted from Sentinel-2 data. The approaches are able to discriminate the water class in different types of wetlands (marshland, rice-paddies and temporary ponds) existing in the Doñana Biosphere Reserve study area, located in southwest Spain. Both unsupervised and supervised approaches are examined against validation data derived from Landsat satellite inundation time series maps, generated by the local administration and offered as an online service since 1983. Accuracy assessment metrics show that both approaches have similarly high classification performance (e.g., the combined kappa coefficient of the unsupervised and the supervised approach is 0.8827 and 0.9477, and the combined overall accuracy is 97.71% and 98.95, respectively). The unsupervised approach can be used by non-trained personnel with a potential for transferability to sites of, at least, similar characteristics.

show abstract

“…The classification output is computed as the mode of predictions made by each decision tree within the random forest structure. A flood mapping approach based also on random forests was developed where the maps were exclusive of any risk categorization and instead concentrated on identifying and classifying flooded and non-flooded regions using unmanned aerial vehicle imagery [13].…”

Section: Related Workmentioning

confidence: 99%

Flood Risk Assessment in Urban Areas Based on Spatial Analytics and Social Factors

Armenakis

Natesan

et al. 2017

Geosciences

View full text Add to dashboard Cite

Flood maps alone are not sufficient to determine and assess the risks to people, property, infrastructure, and services due to a flood event. Simply put, the risk is almost zero to minimum if the flooded region is "empty" (i.e., unpopulated, has not properties, no industry, no infrastructure, and no socio-economic activity). High spatial resolution Earth Observation (EO) data can contribute to the generation and updating of flood risk maps based on several aspects including population, economic development, and critical infrastructure, which can enhance a city's flood mitigation and preparedness planning. In this case study for the Don River watershed, Toronto, the flood risk is determined and flood risk index maps are generated by implementing a methodology for estimating risk based on the geographic coverage of the flood hazard, vulnerability of people, and the exposure of large building structures to flood water. Specifically, the spatial flood risk index maps have been generated through analytical spatial modeling which takes into account the areas in which a flood hazard is expected to occur, the terrain's morphological characteristics, socio-economic parameters based on demographic data, and the density of large building complexes. Generated flood risk maps are verified through visual inspection with 3D city flood maps. Findings illustrate that areas of higher flood risk coincide with areas of high flood hazard and social and building exposure vulnerability.

show abstract

Flood Mapping Based on Multiple Endmember Spectral Mixture Analysis and Random Forest Classifier—The Case of Yuyao, China

Cited by 46 publications

References 45 publications

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

Comparing Thresholding with Machine Learning Classifiers for Mapping Complex Water

Fast and Automatic Data-Driven Thresholding for Inundation Mapping with Sentinel-2 Data

Flood Risk Assessment in Urban Areas Based on Spatial Analytics and Social Factors

Contact Info

Product

Resources

About