Remote sensing technology in recent years has been regarded the most important source to provide substantial information for delineating the flooding extent to the disaster management authority. There have been numerous studies proposing mathematical or statistical classification models for flood mapping. However, conventional pixel-wise classifications methods rely on the exact match of the spectral signature to label the target pixel. In this study, we propose a fully convolutional neural networks (F-CNNs) classification model to map the flooding extent from Landsat satellite images. We utilised the spatial information from the neighbouring area of target pixel in classification. A total of 64 different models were generated and trained with a variable neighbourhood size of training samples and number of learnable filters. The training results revealed that the model trained with neighbourhood sized training samples and with 32 convolutional filters achieved the best performance out of the experiments. A new set of different Landsat images covering flooded areas across Australia were used to evaluate the classification performance of the model. A comparison of our proposed classification model to the conventional support vector machines (SVM) classification model shows that the F-CNNs model was able to detect flooded areas more efficiently than the SVM classification model. For example, the F-CNNs model achieved a maximum precision rate (true positives) of 76.7% compared to 45.27% for SVM classification.
This paper presents an improved spectral unmixing framework for remote sensing data interpretation. Instead of unmixing every pixel in an image into a fixed set of endmembers, approaches of adaptive subsets of endmember selection for individual pixels are presented which can improve the performance of spectral unmixing. An integrated hard and soft classification map is then generated by applying the mixture analysis based on extended Support Vector Machines. The proposed treatment is effective and easy to implement. Unmixing is more reliable with the controlled mixture model. It can cope with the endmembers' spectral variation as a result of system noise encountered during data collection from the space. Experiments were conducted with Landsat ETM data and satisfactory results were achieved.
Many regions in Australia have experienced substantial damage to their natural, social, and environmental infrastructure from natural hazards. The scale and impact of these events have increased in recent decades due to the growing exposure and vulnerability of larger populations, economic activities, and infrastructure (both built and natural), as well as the intensification of natural hazards induced by climate change. Despite the increasing challenges, there is still limited investment in building resilience. Moreover, many local governments throughout Australia lack the necessary technical capabilities, knowledge, and funding to ensure the reliable ongoing delivery of essential services to communities, much less to identify, assess, and implement resilience interventions. The implementation becomes more challenging in the case of Nature-based Solutions for disaster resilience and climate adaptation where there are significant gaps in understanding and evidence of their effectiveness in the short and long term. This study proposes a discursive, place-based, and cross-scale approach to overcoming these challenges and enabling councils to develop resilient investment cases (RICs) as part of regional planning processes involving local governments, research institutions, and private sector stakeholders. The approach involves: collectively identifying values and vulnerabilities in a hazard-prone region in south-east Australia; prioritizing focal infrastructure asset types for investigation, in this case transport but relevant to all forms of critical infrastructure including nature; identifying suitable interventions for resilience planning under scenarios of change; and formulating RICs by assessing the effectiveness, costs, and benefits of bundles of resilience interventions under scenarios of change. We present the approach as applied in the Bega Valley Local Government Area which is highly exposed and vulnerable to impacts from natural hazards. Insights and lessons from the case study are applicable to a range of critical infrastructure types, including nature-based solutions (green and blue infrastructure), as well as other regions in Australia and abroad that require resilient investment planning.
This paper addresses the challenge of introducing a Bayes rules to measure flood probability from multispectral data. Machine learning classifiers were applied to map the extent of flood inun- dation from multispectral remote sensing imagery. The paper applies Extended Support Vector Machine classifier along with linear spectral un-mixing to obtain the classification output. K-means clustering is applied on pre and post flood images to select SVM training samples from clustering outcome of the most in-formative spectral band. Experiments were conducted by divid-ing training and testing samples into two groups. The efficiency of classifier was enhanced by introducing the Bayesian probabil-ity measure and performance was assessed by using precision and recall metrics on the pre and post Bayesian flood probability estimation. It has been observed that for some test cases in this study there was a substantial improvement in precision-recall curve with high precision values and low recall rate. The optimal flood probability threshold value has also been easily calculated by calculating and analising iteratively precision and recall.
The application of ICESAT-2 altimetry data in river hydrology critically depends on the accuracy of the mean water surface elevation (WSE) at a virtual station (VS) where satellite observations intersect solely with water. It is acknowledged that the ATL13 product has noise elevations of the adjacent land, resulting in biased high mean WSEs at VSs. Earlier studies have relied on human intervention or water masks to resolve this. Both approaches are unsatisfactory solutions for large river basins where the issue becomes pronounced due to many tributaries and meanders. There is no automated procedure to partition the truly representative water height from the totality of the along-track ICESAT-2 photon segments (portions of photon points along a beam) for increasing precision of the mean WSE at VSs. We have developed an automated approach called “auto-segmentation”. The accuracy of our method was assessed by comparing the ATL13-derived WSEs with direct water level observations at 10 different gauging stations on 37 different dates along the Lower Murray River, Australia. The concordance between the two datasets is significantly high and without detectable bias. In addition, we evaluated the effects of four methods for calculating the mean WSEs at VSs after auto-segmentation processing. Our results reveal that all methods perform almost equally well, with the same R2 value (0.998) and only subtle variations in RMSE (0.181–0.189 m) and MAE (0.130–0.142 m). We also found that the R2, RMSE and MAE are better under the high flow condition (0.999, 0.124 and 0.111 m) than those under the normal-low flow condition (0.997, 0.208 and 0.160 m). Overall, our auto-segmentation method is an effective and efficient approach for deriving accurate mean WSEs at river VSs. It will contribute to the improvement of ICESAT-2 ATL13 altimetry data utility on rivers.
This paper addresses the challenges of flood mapping using multispectral images. Quantitative flood mapping is critical for flood damage assessment and management. Remote sensing images obtained from various satellite or airborne sensors provide valuable data for this application, from which the information on the extent of flood can be extracted. However the great challenge involved in the data interpretation is to achieve more reliable flood extent mapping including both the fully inundated areas and the `wet' areas where trees and houses are partly covered by water. This is a typical combined pure pixel and mixed pixel problem. In this paper, an extended Support Vector Machines method for spectral unmixing developed recently has been applied to generate an integrated map showing both pure pixels (fully inundated areas) and mixed pixels (trees and houses partly covered by water). The outputs were compared with the conventional mean based linear spectral mixture model, and better performance was demonstrated with a subset of Landsat ETM+ data recorded at the Daly River Basin, NT, Australia, on 3rd March, 2008, after a flood event.