Adaptive hydrological flow field modeling based on water body extraction and surface information

Geomatics, Natural Hazards and Risk

2020

Self Cite

Flood verification and mitigation based on ground survey has been impeded by many factors. For instance, damage assessment exclusively by onsite expedition could be delayed by restricted access, especially during heavy flooding. To devise appropriate mitigation measures, resources required to thoroughly investigate the incidents in response to disaster could be overwhelming. Moreover, inadequate equipment and non-standardized flood reporting process could also undermine the maneuver. As a consequent, rescue mission was inevitably deferred until the reported incidents had been confirmed. To address these issues, this paper presents an internetworking system for assisting flooding disaster mitigation. Its main contributions were two folds. Firstly, its data intelligent was driven by convergence of both user and official reports of flood incidents and those automatically detected from remotely sensed images. Secondly, the reliability of reported information was ensured by two-factor verification, i.e. by using a state-of-the-art deep learning strategy and by official investigations. The verified incidents were then presented in augmented graphical reports, which were practical in public inquiry and official uses in devising efficient and cost-effective disaster mitigation measures. The developed system was deployed in different cities, most affected by recent floods. Numerical and subjective assessments herein demonstrate the merits of the system.

Section: Remote Sensing For Flood Detectionmentioning

confidence: 99%

Section: Overview Of the Proposed Systemmentioning

confidence: 99%

See 1 more Smart Citation

Internetworking flood disaster mitigation system based on remote sensing and mobile GIS

Geomatics, Natural Hazards and Risk

2020

Self Cite

“…Data fusion has often been employed in remote sensing studies to verify and consolidate both acquired and processed information, normally from different imaging modalities. Fusion in post processing, for instances, was applied after land cover classification such as building [27], river [28] and road [16], etc. The two most prominent fusion methods are Majority Voting [29] and Dempster-Shafer [30].…”

Section: Related Literaturementioning

confidence: 99%

“…Nonetheless, this modality is most suitable for discriminating buildings and constructions [39,40]. Some studies analyzed DSM and used it to determine flooded basin [41] or fused it with Landsat images to extract water bodies, passages and small branching [28]. Integrating DSM with aerial data was also proposed by Herumurti et al in the recent road extraction studies, [42] and [43].…”

Section: Related Literaturementioning

confidence: 99%

Multi-spectral and Topographic Fusion for Automated Road Extraction

2018

Open Geosciences

Self Cite

Road geometry is pertinent information in various GIS studies. Reliable and updated road information thus calls for conventional on-site survey being replaced by more accurate and efficient remote sensing technology. Generally, this approach involves image enhancement and extraction of relevant features, such as elongate gradient and intersecting corners. Thus far, its implication is often impeded by wrongly extraction of other urban peripherals with similar pixel characteristics. This paper therefore proposes the fusion of THEOS satellite image and topographic derivatives, obtained from underlying Digital Surface Models (DSM). Multi-spectral indices in thematic layers and surface properties of designated roads were both fed into state-of-the-art machine learning algorithms. The results were later fused, taken into account consistently leveled road surface. The proposed technique was thus able to eliminate irrelevant urban structures such as buildings and other constructions, otherwise left by conventional index based extraction. The numerical assessment indicates recall of 84.64%, precision of 97.40% and overall accuracy of 97.78%, with 0.89 Kappa statistics. Visual inspection reported herewith also confirms consistency with ground truth reference.

Flood Forecasting System Based on Integrated Big and Crowdsource Data by Using Machine Learning Techniques

2020

IEEE Access

Self Cite

Flood is one of the most disruptive natural hazards, responsible for loss of lives and damage to properties. A number of cities are subject to monsoons influences and hence face the disaster almost every year. Early notification of flood incident could benefit the authorities and public to devise both short and long terms preventive measures, to prepare evacuation and rescue mission, and to relieve the flood victims. Geographical locations of affected areas and respective severities, for instances, are among the key determinants in most flood administration. Thus far, an effective means of anticipating flood in advance remains lacking. Existing tools were typically based on manually input and prepared data. The processes were tedious and thus prohibitive for real-time and early forecasts. Furthermore, these tools did not fully exploit more comprehensive information available in current big data platforms. Therefore, this paper proposes a novel flood forecasting system based on fusing meteorological, hydrological, geospatial, and crowdsource big data in an adaptive machine learning framework. Data intelligence was driven by stateof-the-art learning strategies. Subjective and objective evaluations indicated that the developed system was able to forecast flood incidents, happening in specific areas and time frames. It was also later revealed by benchmarking experiments that the system configured with an MLP ANN gave the most effective prediction, with correct percentage, Kappa, MAE and RMSE of 97.93, 0.89, 0.01 and 0.10, respectively. INDEX TERMS Flood forecasting system, big data, machine learning, crowdsource, deep learning. PARAMATE HORKAEW received the B.Eng. degree (Hons.