Detection of tropical cyclone genesis via quantitative satellite ocean surface wind pattern and intensity analyses using decision trees

Park, Myung‐Sook; Kim, Minsang; Lee, Myong‐In; Im, Jungho; Park, Seonyoung

doi:10.1016/j.rse.2016.06.006

Cited by 42 publications

(30 citation statements)

References 35 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…The samples from 2013 to 2014 were used as training data (n = 20,787), and validation was conducted using the samples in 2015 (n = 15,625). This hindcast validation approach is commonly used in the operational applications of satellite remote sensing, especially for meteorological applications [51,[78][79][80][81]. Six independent variables, ASCAT, AMSR2, MODIS, and SRTM products, and the dependent variable of GLDAS soil moisture were fed into machine learning (dotted lines in Figure 2).…”

Section: Methodsmentioning

confidence: 99%

Downscaling GLDAS Soil Moisture Data in East Asia through Fusion of Multi-Sensors by Optimizing Modified Regression Trees

Park

et al. 2017

Water

Self Cite

View full text Add to dashboard Cite

Soil moisture is a key part of Earth's climate systems, including agricultural and hydrological cycles. Soil moisture data from satellite and numerical models is typically provided at a global scale with coarse spatial resolution, which is not enough for local and regional applications. In this study, a soil moisture downscaling model was developed using satellite-derived variables targeting Global Land Data Assimilation System (GLDAS) soil moisture as a reference dataset in East Asia based on the optimization of a modified regression tree. A total of six variables, Advanced Microwave Scanning Radiometer 2 (AMSR2) and Advanced SCATterometer (ASCAT) soil moisture products, Shuttle Radar Topography Mission (SRTM) Digital Elevation Model (DEM), and MODerate resolution Imaging Spectroradiometer (MODIS) products, including Land Surface Temperature, Normalized Difference Vegetation Index, and land cover, were used as input variables. The optimization was conducted through a pruning approach for operational use, and finally 59 rules were extracted based on root mean square errors (RMSEs) and correlation coefficients (r). The developed downscaling model showed a good modeling performance (r = 0.79, RMSE = 0.056 m 3 ·m −3 , and slope = 0.74). The 1 km downscaled soil moisture showed similar time series patterns with both GLDAS and ground soil moisture and good correlation with ground soil moisture (average r = 0.47, average RMSD = 0.038 m 3 ·m −3 ) at 14 ground stations. The spatial distribution of 1 km downscaled soil moisture reflected seasonal and regional characteristics well, although the model did not result in good performance over a few areas such as Southern China due to very high cloud cover rates. The results of this study are expected to be helpful in operational use to monitor soil moisture throughout East Asia since the downscaling model produces daily high resolution (1 km) real time soil moisture with a low computational demand. This study yielded a promising result to operationally produce daily high resolution soil moisture data from multiple satellite sources, although there are yet several limitations. In future research, more variables including Global Precipitation Measurement (GPM) precipitation, Soil Moisture Active Passive (SMAP) soil moisture, and other vegetation indices will be integrated to improve the performance of the proposed soil moisture downscaling model.

show abstract

Section: Methodsmentioning

confidence: 99%

Downscaling GLDAS Soil Moisture Data in East Asia through Fusion of Multi-Sensors by Optimizing Modified Regression Trees

Park

et al. 2017

Water

Self Cite

View full text Add to dashboard Cite

show abstract

“…Despite the overall decrease in landed typhoons (supporting information Figure S6), it is noticeable that most of the hotspot regions have experienced increasing regime shifts (90% confidence) in APDI ( Figure 4). However, regardless of whether the landfalling typhoons have become more intense, the less resilient communities in the identified hotspots are more likely to be affected (Park et al, 2016). Therefore, enhancing community resilience should be the key consideration for stakeholders and officials.…”

Section: Typhoon Destructive Potential and Community Resiliencementioning

confidence: 99%

Integrating Typhoon Destructive Potential and Social‐Ecological Systems Toward Resilient Coastal Communities

Sajjad

et al. 2019

Earth's Future

View full text Add to dashboard Cite

The resilience of coastal communities becomes a critical issue of the social-ecological system adapting to impacts from hazards on coastal well-being. This paper formulates a framework integrating typhoon destructive potential and social-ecological system from a perspective of coastal resilience. Typhoon destructive potential is interpreted using the Power Dissipation Index as a metric. We use the distributional models in geographic information systems to identify the spatial hotspots of high Power Dissipation Index along the coast of Mainland China. Furthermore, we evaluate the community resilience in all identified hotspots with place-based indicators within five potential dimensions (Social, Ecological, Institutional, Economic, and Safety). Though the results show no significant long-term trends in the typhoon destructive potential, statistically significant interdecadal variations are identified in different hotspots during 1949-2014. The resilience assessment results reveal that ecological (predisaster defense) and safety resilience (postdisaster support) are critical issues in achieving coastal community resilience. We argue that improving the ecological stewardship (having great predisaster defense) and adopting integrated approaches contribute to resilience enhancement, providing opportunities to support all the dimensions of community resilience via improving the social-economic-ecological nexus. The integration of typhoon destructive potential and social-ecological system helps to achieve Sustainable Development Goal 13 through risk-informed decision-making. The results from this study have important policy implications for local-scale planning incorporating place-based indicators.Plain Language Summary Tropical cyclones pose serious threats to human well-being globally.Governments and policymakers are particularly interested in risk reduction through effective risk-informed planning and resilience enhancement. To facilitate this, we formulate a framework integrating hazard behavior-explained by landfalling typhoon intensity-and social-ecological systems, which enables us to identify the Power Dissipation Index-based hotspots of typhoon destructive potential. These hotspots are further evaluated for the community resilience assessment to inform the decision makers. While the results show no significant overall increasing trend in typhoon destructive potential for most of the hotspot regions during the study period , interdecadal variations are found, with a significant increasing trend for some regions (90% confidence). It is important to note that the results from the resilience assessment show that many communities lack in the ecological and safety dimensions of community resilience, which is critical. We recommend an improved ecological stewardship for community resilience enhancement. Adopting the proposed framework can also attribute toward Sustainable Development Goal 13 achievement through the corrective decision-making for risk reduction related policy implications.

show abstract

“…Decision tree (DT) is one of the most popular classification algorithms in the current use in data mining and machine learning. Briefly, decision tree can be defined as a recursive procedure, through splitting the original data into more homogenous subgroups using generated rules or decisions which are called as nodes (Park, Kim, Lee, Im, & Park, 2016;Sharma, Ghosh, & Joshi, 2013). The decision tree algorithm includes three different nodes (the root node, internal node, end node or target), it breaks an end node to construct a tree with certain splitting criteria (Shi, 2014;Tayefi et al, 2017).…”

Section: Decision Tree Algorithmmentioning

confidence: 99%

Fast nutritional characterization of different pigmented rice grains using a combination of NMR and decision tree analysis

Huo

Liu

et al. 2019

CyTA - Journal of Food

View full text Add to dashboard Cite

2019) Fast nutritional characterization of different pigmented rice grains using a combination of NMR and decision tree analysis, ABSTRACT Different rice cultivars contain various metabolites which are closely related with their nutritional and functional effects. In the current study, NMR and chemometrics methodsdecision tree analysis (DTA) were applied to explore the chemical characteristics in different rice cultivars. The pigmented rice were completely discriminated from each other, and the key metabolites that mostly contributed to the rice discrimination were explored, including sugars compounds (sucrose, fructose and glucose) and non-sugar compounds (γ-amino butyric acid (GABA), asparagine, citric acid and malic acid) with DTA approach and 1 HNMR metabolite fingerprints. The purple rice has the highest concentrations of sucrose, citric acid and asparagine (p < 0.05), but lowest fructose (p < 0.05); red rice has the lowest GABA concentration comparing with the other three groups (p < 0.05). This study implies that DTA method is a powerful tool to discriminate different pigmented rice varieties. Furthermore, it also reveals the crucial nutrients based on 1 H-NMR metabolic profiling. ARTICLE HISTORY

show abstract

Detection of tropical cyclone genesis via quantitative satellite ocean surface wind pattern and intensity analyses using decision trees

Cited by 42 publications

References 35 publications

Downscaling GLDAS Soil Moisture Data in East Asia through Fusion of Multi-Sensors by Optimizing Modified Regression Trees

Downscaling GLDAS Soil Moisture Data in East Asia through Fusion of Multi-Sensors by Optimizing Modified Regression Trees

Integrating Typhoon Destructive Potential and Social‐Ecological Systems Toward Resilient Coastal Communities

Fast nutritional characterization of different pigmented rice grains using a combination of NMR and decision tree analysis

Contact Info

Product

Resources

About