scholarly journals Data-based wildfire risk model for Mediterranean ecosystems – case study of the Concepción metropolitan area in central Chile

2021 ◽  
Vol 21 (12) ◽  
pp. 3663-3678
Author(s):  
Edilia Jaque Castillo ◽  
Alfonso Fernández ◽  
Rodrigo Fuentes Robles ◽  
Carolina G. Ojeda
Keyword(s):  
Metropolitan Area ◽  
Urban Areas ◽  
Risk Model ◽  
Fire Hazard ◽  
Principal Component ◽  
Mediterranean Ecosystems ◽  
Machine Learning Algorithms ◽  
Native Forest ◽  
Wildfire Risk ◽  
Very High

Abstract. Wildfire risk is latent in Chilean metropolitan areas characterized by the strong presence of wildland–urban interfaces (WUIs). The Concepción metropolitan area (CMA) constitutes one of the most representative samples of that dynamic. The wildfire risk in the CMA was addressed by establishing a model of five categories (near zero, low, moderate, high, and very high) that represent discernible thresholds in fire occurrence, using geospatial data and satellite images describing anthropic–biophysical factors that trigger fires. Those were used to deliver a model of fire hazard using machine learning algorithms, including principal component analysis and Kohonen self-organizing maps in two experimental scenarios: only native forest and only forestry plantation. The model was validated using fire hotspots obtained from the forestry government organization. The results indicated that 12.3 % of the CMA's surface area has a high and very high risk of a forest fire, 29.4 % has a moderate risk, and 58.3 % has a low and very low risk. Lastly, the observed main drivers that have deepened this risk were discussed: first, the evident proximity between the increasing urban areas with exotic forestry plantations and, second, climate change that threatens triggering more severe and large wildfires because of human activities.

scholarly journals Data-based wildfire risk model for Mediterranean ecosystems. Study case of Concepcion Metropolitan Area in Central Chile

2021 ◽  
Author(s):  
Edilia Jaque Castillo ◽  
Alfonso Fernández ◽  
Rodrigo Fuentes Robles ◽  
Carolina G. Ojeda
Keyword(s):  
Metropolitan Area ◽  
Urban Areas ◽  
Risk Model ◽  
Fire Hazard ◽  
Principal Component ◽  
Mediterranean Ecosystems ◽  
Machine Learning Algorithms ◽  
Native Forest ◽  
Wildfire Risk ◽  
Very High

Abstract. Wildfire risk is latent in Chilean metropolitan areas characterized by the strong presence of Wildland-Urban Interfaces (WUI). The Metropolitan Area of Concepción (CMA) constitutes one of the most representative samples of that dynamic. The wildfire risk in the CMA was addressed by establishing a model of 5 categories (Near Zero, Low, Medium, High, and Very High) that represent discernible thresholds in fire occurrence, using geospatial data and satellite images describing anthropic - biophysical factors that trigger fires. Those were used to deliver a model of fire hazard using machine learning algorithms, including Principal Component Analysis and Kohonen Self-Organizing Maps in two experimental scenarios: only native forest and only forestry plantation. The model was validated using fire spots obtained from the forestry government organization. The results indicated that 12.3 % of the CMA’s surface area has a high and very high risk of a forest fire, 29.4 % has a medium risk, and 58.3 % has a low and very low risk. Lastly, the observed main drivers that have deepened this risk were discussed: first, the evident proximity between the increasing urban areas with exotic forestry plantations, and second, climate change that threatens to trigger more severe and large wildfires because of human activities.

scholarly journals Behavior and Preparedness to Fire Hazard in High Density Settlements in Bandung

2016 ◽  
Vol 28 (1) ◽  
Author(s):  
Saut Sagala ◽  
Ramanditya Wimbardana ◽  
Ferdinand Patrick Pratama
Keyword(s):  
Urban Areas ◽  
Fire Hazard ◽  
Fire Behavior ◽  
Disaster Risk ◽  
High Density ◽  
Fire Hazards ◽  
Fire Disaster ◽  
And Behavior ◽  
Very High

Fire is one of the hazards that may affect urban areas with high density settlements. Thus, research on fire mitigation is important to be conducted. This paper examines the behavior and preparedness of occupants in high density settlements towards fire risks in urban area. The case study is located at Kelurahan Sukahaji, Kecamatan Babakan Ciparay, Bandung that has very high density settlement as well as prone to fire hazards. This study assess 232 respondents in the study areas on information related to demography, understanding about fire, behavior and preparedness. The respondents understanding on the types of fire sources are still low. Similarly, the behavior related to the activites using fire are still dangerous because some activities are conducted with other activities which make people less aware of the fire hazards. Nevertheless, their knowledge on how to extinguish fires are quite good. This paper recommends more trainings on knowledge of fire source and behavior to be conducted to occupants living in high density settlements in order to reduce fire disaster risk.

scholarly journals AN ANALYSIS OF WILDFIRE RISK AND HISTORICAL OCCURRENCE FOR A MEDITERRANEAN BIOSPHERE RESERVE, CENTRAL CHILE

2018 ◽  
Vol 26 (2) ◽  
pp. 128-140 ◽  
Author(s):  
Camila Bańales-Seguel ◽  
Francisco De La Barrera ◽  
Alejandro Salazar
Keyword(s):  
Biosphere Reserve ◽  
Mediterranean Ecosystems ◽  
Historical Records ◽  
Gis Analysis ◽  
Central Chile ◽  
Wildfire Risk ◽  
Wildfire Occurrence ◽  
Future Events ◽  
Landsat Satellite ◽  
Very High

Wildfires are one of the main processes that currently shape Mediterranean ecosystems. The analysis of wildfire risk combined with historical records allows for a greater understanding of trends and their relation to territorial variables that are favourable to future events. Using GIS analysis, we assess wildfire risk in La Campana – Peñuelas Biosphere Reserve, in Central Chile. Additionally, with official historical records and LANDSAT satellite images from 1985–2015 and GIS we determine historical occurrence in the Reserve. We found that the areas with very high risk of wildfire occurrence have a strong combination of ignition factors such as presence of human settlements and road connectivity, and variables that would be negatively impacted by the occurrence of wildfires, such as degraded soils and vulnerable vegetation. These findings highlight the need to destine resources to fire prevention in these areas and develop adaptation strategies for risk management at different scales.

scholarly journals Semantic segmentation of PolSAR image data using advanced deep learning model

2021 ◽  
Vol 11 (1) ◽  
Author(s):  
Rajat Garg ◽  
Anil Kumar ◽  
Nikunj Bansal ◽  
Manish Prateek ◽  
Shashi Kumar
Keyword(s):  
Machine Learning ◽  
Remote Sensing ◽  
Deep Learning ◽  
Urban Area ◽  
Urban Areas ◽  
Learning Algorithms ◽  
Semantic Segmentation ◽  
Learning Model ◽  
Machine Learning Algorithms ◽  
Deep Learning Model

AbstractUrban area mapping is an important application of remote sensing which aims at both estimation and change in land cover under the urban area. A major challenge being faced while analyzing Synthetic Aperture Radar (SAR) based remote sensing data is that there is a lot of similarity between highly vegetated urban areas and oriented urban targets with that of actual vegetation. This similarity between some urban areas and vegetation leads to misclassification of the urban area into forest cover. The present work is a precursor study for the dual-frequency L and S-band NASA-ISRO Synthetic Aperture Radar (NISAR) mission and aims at minimizing the misclassification of such highly vegetated and oriented urban targets into vegetation class with the help of deep learning. In this study, three machine learning algorithms Random Forest (RF), K-Nearest Neighbour (KNN), and Support Vector Machine (SVM) have been implemented along with a deep learning model DeepLabv3+ for semantic segmentation of Polarimetric SAR (PolSAR) data. It is a general perception that a large dataset is required for the successful implementation of any deep learning model but in the field of SAR based remote sensing, a major issue is the unavailability of a large benchmark labeled dataset for the implementation of deep learning algorithms from scratch. In current work, it has been shown that a pre-trained deep learning model DeepLabv3+ outperforms the machine learning algorithms for land use and land cover (LULC) classification task even with a small dataset using transfer learning. The highest pixel accuracy of 87.78% and overall pixel accuracy of 85.65% have been achieved with DeepLabv3+ and Random Forest performs best among the machine learning algorithms with overall pixel accuracy of 77.91% while SVM and KNN trail with an overall accuracy of 77.01% and 76.47% respectively. The highest precision of 0.9228 is recorded for the urban class for semantic segmentation task with DeepLabv3+ while machine learning algorithms SVM and RF gave comparable results with a precision of 0.8977 and 0.8958 respectively.

A principal component analysis of the determinants of spatial disparity between rural and urban localities of Ghana

2017 ◽  
Vol 44 (6) ◽  
pp. 715-731 ◽  
Author(s):  
Ivy Drafor
Keyword(s):  
Principal Component Analysis ◽  
Rural Areas ◽  
Urban Areas ◽  
Principal Component ◽  
Component Analysis ◽  
Spatial Inequality ◽  
Necessary Condition ◽  
Spatial Disparity ◽  
Content Type ◽  
Rural And Urban

Purpose The purpose of this paper is to analyse the spatial disparity between rural and urban areas in Ghana using the Ghana Living Standards Survey’s (GLSS) rounds 5 and 6 data to advance the assertion that an endowed rural sector is necessary to promote agricultural development in Ghana. This analysis helps us to know the factors that contribute to the depravity of the rural sectors to inform policy towards development targeting. Design/methodology/approach A multivariate principal component analysis (PCA) and hierarchical cluster analysis were applied to data from the GLSS-5 and GLSS-6 to determine the characteristics of the rural-urban divide in Ghana. Findings The findings reveal that the rural poor also spend 60.3 per cent of their income on food, while the urban dwellers spend 49 per cent, which is an indication of food production capacity. They have low access to information technology facilities, have larger household sizes and lower levels of education. Rural areas depend a lot on firewood for cooking and use solar/dry cell energies and kerosene for lighting which have implications for conserving the environment. Practical implications Developing the rural areas to strengthen agricultural growth and productivity is a necessary condition for eliminating spatial disparities and promoting overall economic development in Ghana. Addressing rural deprivation is important for conserving the environment due to its increased use of fuelwood for cooking. Absence of alternatives to the use of fuelwood weakens the efforts to reduce deforestation. Originality/value The application of PCA to show the factors that contribute to spatial inequality in Ghana using the GLSS-5 and GLSS-6 data is unique. The study provides insights into redefining the framework for national poverty reduction efforts.

scholarly journals Characterizing the Spatial and Temporal Availability of Very High Resolution Satellite Imagery in Google Earth and Microsoft Bing Maps as a Source of Reference Data

Land ◽  
2018 ◽  
Vol 7 (4) ◽  
pp. 118 ◽  
Author(s):  
Myroslava Lesiv ◽  
Linda See ◽  
Juan Laso Bayas ◽  
Tobias Sturn ◽  
Dmitry Schepaschenko ◽  
...  
Keyword(s):  
High Resolution ◽  
Satellite Imagery ◽  
Urban Areas ◽  
Reference Data ◽  
Temporal Distribution ◽  
Google Earth ◽  
Training Data ◽  
Visual Interpretation ◽  
The Usa ◽  
Very High

Very high resolution (VHR) satellite imagery from Google Earth and Microsoft Bing Maps is increasingly being used in a variety of applications from computer sciences to arts and humanities. In the field of remote sensing, one use of this imagery is to create reference data sets through visual interpretation, e.g., to complement existing training data or to aid in the validation of land-cover products. Through new applications such as Collect Earth, this imagery is also being used for monitoring purposes in the form of statistical surveys obtained through visual interpretation. However, little is known about where VHR satellite imagery exists globally or the dates of the imagery. Here we present a global overview of the spatial and temporal distribution of VHR satellite imagery in Google Earth and Microsoft Bing Maps. The results show an uneven availability globally, with biases in certain areas such as the USA, Europe and India, and with clear discontinuities at political borders. We also show that the availability of VHR imagery is currently not adequate for monitoring protected areas and deforestation, but is better suited for monitoring changes in cropland or urban areas using visual interpretation.

scholarly journals Environmental Vulnerability by Floods and Occupation of Permanent Preservation Area: An Approach about Three Cities of Midwest of Brazil

2017 ◽  
Vol 10 (2) ◽  
pp. 45
Author(s):  
Greyce Bernardes de Mello Rezende ◽  
Telma Lucia Bezerra Alves
Keyword(s):  
Urban Areas ◽  
Local Level ◽  
Urban Expansion ◽  
Google Earth ◽  
Satellite Imaging ◽  
Environmental Vulnerability ◽  
Industrial Buildings ◽  
Araguaia River ◽  
The Government ◽  
Very High

The purpose of this article is to identify the areas of environmental vulnerability by flooding in urban areas of the municipalities of Barra dos Garças - MT, Pontal do Araguaia - MT and Aragarças - GO; and demarcate the occupations in permanent preservation areas (PPAs) in the study area. The methodology uses variables such as time series of maximum quotas of the Araguaia River, from 1968 to 2014, the frequency of those floods, as well as the local level curves. From the junction of these data, it was stipulated the levels of environmental vulnerability by floods in five levels: very high, high, medium, low and very low. The results indicate that areas with very high vulnerability correspond to approximately 1,58 square kilometers which equals to 0.5% of the total area studied; the high vulnerability areas, have only 3.19 square kilometers, corresponding to 1% of the area; the medium vulnerability areas have 7.66 square kilometers, which corresponds to 2.41% of the area; low vulnerability areas, have 11.18 square kilometers of extension relating to 3.52% of the area; and finally the remainder of the study area was characterized as very low vulnerability. After this mapping, it was found by satellite imaging from Google earth software dated 2014, the main occupations in PPAs. The main uses and occupations refer to human activities related to tourism, as well as commercial, residential and industrial buildings. It was found that it is of salutary importance that the Government enforces the fulfillment of the restrictions set out in the Forest Code, preventing that more occupations occur in PPAs and areas subject to flooding. Moreover, the mapping of areas of flooding is also a tool for future public policies that aim to guide the recommended areas to urban expansion, as well as ordering the use and occupation of land by developing zoning.

Sign in / Sign up

Export Citation Format

Share Document